From 3bd898b6ce94f34bcc7685672f0e4318d2d86b33 Mon Sep 17 00:00:00 2001 From: invincibledude <> Date: Sat, 21 Jan 2023 23:14:59 +0300 Subject: First test of different sampler for hi-res fix --- modules/processing.py | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'modules/processing.py') diff --git a/modules/processing.py b/modules/processing.py index 6e6371a1..b3206f80 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -710,7 +710,7 @@ def old_hires_fix_first_pass_dimensions(width, height): class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): sampler = None - def __init__(self, enable_hr: bool = False, denoising_strength: float = 0.75, firstphase_width: int = 0, firstphase_height: int = 0, hr_scale: float = 2.0, hr_upscaler: str = None, hr_second_pass_steps: int = 0, hr_resize_x: int = 0, hr_resize_y: int = 0, **kwargs): + def __init__(self, enable_hr: bool = False, denoising_strength: float = 0.75, firstphase_width: int = 0, firstphase_height: int = 0, hr_scale: float = 2.0, hr_upscaler: str = None, hr_second_pass_steps: int = 0, hr_resize_x: int = 0, hr_resize_y: int = 0, hr_sampler: int = 0, **kwargs): super().__init__(**kwargs) self.enable_hr = enable_hr self.denoising_strength = denoising_strength @@ -721,6 +721,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): self.hr_resize_y = hr_resize_y self.hr_upscale_to_x = hr_resize_x self.hr_upscale_to_y = hr_resize_y + self.hr_sampler = hr_sampler if firstphase_width != 0 or firstphase_height != 0: self.hr_upscale_to_x = self.width @@ -862,6 +863,10 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): shared.state.nextjob() img2img_sampler_name = self.sampler_name if self.sampler_name != 'PLMS' else 'DDIM' # PLMS does not support img2img so we just silently switch ot DDIM + + if self.hr_sampler != 0 and sd_samplers.samplers[self.hr_sampler].name != 'PLMS': + img2img_sampler_name = sd_samplers.samplers[self.hr_sampler].name + self.sampler = sd_samplers.create_sampler(img2img_sampler_name, self.sd_model) samples = samples[:, :, self.truncate_y//2:samples.shape[2]-(self.truncate_y+1)//2, self.truncate_x//2:samples.shape[3]-(self.truncate_x+1)//2] -- cgit v1.2.3 From 6c0566f937ba212e3faf1d30c337850543e85a12 Mon Sep 17 00:00:00 2001 From: invincibledude <> Date: Sat, 21 Jan 2023 23:25:36 +0300 Subject: Type mismatch fix --- modules/processing.py | 4 ++-- modules/txt2img.py | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'modules/processing.py') diff --git a/modules/processing.py b/modules/processing.py index b3206f80..65673a9d 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -864,8 +864,8 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): img2img_sampler_name = self.sampler_name if self.sampler_name != 'PLMS' else 'DDIM' # PLMS does not support img2img so we just silently switch ot DDIM - if self.hr_sampler != 0 and sd_samplers.samplers[self.hr_sampler].name != 'PLMS': - img2img_sampler_name = sd_samplers.samplers[self.hr_sampler].name + if self.hr_sampler != 0 and self.hr_sampler != 'PLMS': + img2img_sampler_name = self.hr_sampler self.sampler = sd_samplers.create_sampler(img2img_sampler_name, self.sd_model) diff --git a/modules/txt2img.py b/modules/txt2img.py index 21f48d12..3d16ac5b 100644 --- a/modules/txt2img.py +++ b/modules/txt2img.py @@ -39,7 +39,7 @@ def txt2img(id_task: str, prompt: str, negative_prompt: str, prompt_styles, step hr_resize_x=hr_resize_x, hr_resize_y=hr_resize_y, hr_sampler=sd_samplers.samplers[hr_sampler_index].name - if hr_sampler_index != 0 else sd_samplers.samplers[sampler_index].name + if hr_sampler_index != 0 else 0 ) p.scripts = modules.scripts.scripts_txt2img -- cgit v1.2.3 From 9e1f49c4e5b169eecbf075c49a304774dfdc6035 Mon Sep 17 00:00:00 2001 From: invincibledude <> Date: Sun, 22 Jan 2023 00:03:16 +0300 Subject: PLMS edge-case handling fix --- modules/processing.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'modules/processing.py') diff --git a/modules/processing.py b/modules/processing.py index 65673a9d..6e04b064 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -864,7 +864,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): img2img_sampler_name = self.sampler_name if self.sampler_name != 'PLMS' else 'DDIM' # PLMS does not support img2img so we just silently switch ot DDIM - if self.hr_sampler != 0 and self.hr_sampler != 'PLMS': + if self.hr_sampler != 0 and sd_samplers.samplers[self.hr_sampler].name != 'PLMS': img2img_sampler_name = self.hr_sampler self.sampler = sd_samplers.create_sampler(img2img_sampler_name, self.sd_model) -- cgit v1.2.3 From 3ffe2e768b542c837927cfdf0310a2e0fdd48683 Mon Sep 17 00:00:00 2001 From: invincibledude <> Date: Sun, 22 Jan 2023 00:07:46 +0300 Subject: PLMS edge-case handling fix 2 --- modules/processing.py | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'modules/processing.py') diff --git a/modules/processing.py b/modules/processing.py index 6e04b064..83c65948 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -710,7 +710,7 @@ def old_hires_fix_first_pass_dimensions(width, height): class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): sampler = None - def __init__(self, enable_hr: bool = False, denoising_strength: float = 0.75, firstphase_width: int = 0, firstphase_height: int = 0, hr_scale: float = 2.0, hr_upscaler: str = None, hr_second_pass_steps: int = 0, hr_resize_x: int = 0, hr_resize_y: int = 0, hr_sampler: int = 0, **kwargs): + def __init__(self, enable_hr: bool = False, denoising_strength: float = 0.75, firstphase_width: int = 0, firstphase_height: int = 0, hr_scale: float = 2.0, hr_upscaler: str = None, hr_second_pass_steps: int = 0, hr_resize_x: int = 0, hr_resize_y: int = 0, hr_sampler: int | str = 0, **kwargs): super().__init__(**kwargs) self.enable_hr = enable_hr self.denoising_strength = denoising_strength @@ -864,7 +864,11 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): img2img_sampler_name = self.sampler_name if self.sampler_name != 'PLMS' else 'DDIM' # PLMS does not support img2img so we just silently switch ot DDIM - if self.hr_sampler != 0 and sd_samplers.samplers[self.hr_sampler].name != 'PLMS': + if self.hr_sampler == 0: + pass + elif self.hr_sampler == 'PLMS': + img2img_sampler_name = 'DDIM' + else: img2img_sampler_name = self.hr_sampler self.sampler = sd_samplers.create_sampler(img2img_sampler_name, self.sd_model) -- cgit v1.2.3 From 6cd7bf9f860dff3b61a50ec2d41915536cbcf448 Mon Sep 17 00:00:00 2001 From: invincibledude <> Date: Sun, 22 Jan 2023 00:08:58 +0300 Subject: PLMS edge-case handling fix 3 --- modules/processing.py | 4 ++-- modules/txt2img.py | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'modules/processing.py') diff --git a/modules/processing.py b/modules/processing.py index 83c65948..6f6efe06 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -710,7 +710,7 @@ def old_hires_fix_first_pass_dimensions(width, height): class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): sampler = None - def __init__(self, enable_hr: bool = False, denoising_strength: float = 0.75, firstphase_width: int = 0, firstphase_height: int = 0, hr_scale: float = 2.0, hr_upscaler: str = None, hr_second_pass_steps: int = 0, hr_resize_x: int = 0, hr_resize_y: int = 0, hr_sampler: int | str = 0, **kwargs): + def __init__(self, enable_hr: bool = False, denoising_strength: float = 0.75, firstphase_width: int = 0, firstphase_height: int = 0, hr_scale: float = 2.0, hr_upscaler: str = None, hr_second_pass_steps: int = 0, hr_resize_x: int = 0, hr_resize_y: int = 0, hr_sampler: str = '---', **kwargs): super().__init__(**kwargs) self.enable_hr = enable_hr self.denoising_strength = denoising_strength @@ -864,7 +864,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): img2img_sampler_name = self.sampler_name if self.sampler_name != 'PLMS' else 'DDIM' # PLMS does not support img2img so we just silently switch ot DDIM - if self.hr_sampler == 0: + if self.hr_sampler == '---': pass elif self.hr_sampler == 'PLMS': img2img_sampler_name = 'DDIM' diff --git a/modules/txt2img.py b/modules/txt2img.py index 8560b74f..9c8ec621 100644 --- a/modules/txt2img.py +++ b/modules/txt2img.py @@ -39,7 +39,7 @@ def txt2img(id_task: str, prompt: str, negative_prompt: str, prompt_styles, step hr_resize_x=hr_resize_x, hr_resize_y=hr_resize_y, hr_sampler=sd_samplers.samplers[hr_sampler_index - 1].name - if hr_sampler_index != 0 else 0 + if hr_sampler_index != 0 else '---' ) p.scripts = modules.scripts.scripts_txt2img -- cgit v1.2.3 From 0f6862ef3041f3ee18e8236765b1c1958c84385b Mon Sep 17 00:00:00 2001 From: invincibledude <> Date: Sun, 22 Jan 2023 00:11:05 +0300 Subject: PLMS edge-case handling fix 5 --- modules/processing.py | 2 -- modules/txt2img.py | 2 +- modules/ui.py | 2 +- 3 files changed, 2 insertions(+), 4 deletions(-) (limited to 'modules/processing.py') diff --git a/modules/processing.py b/modules/processing.py index 6f6efe06..a873498b 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -866,8 +866,6 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): if self.hr_sampler == '---': pass - elif self.hr_sampler == 'PLMS': - img2img_sampler_name = 'DDIM' else: img2img_sampler_name = self.hr_sampler diff --git a/modules/txt2img.py b/modules/txt2img.py index 9c8ec621..c6ea11c2 100644 --- a/modules/txt2img.py +++ b/modules/txt2img.py @@ -38,7 +38,7 @@ def txt2img(id_task: str, prompt: str, negative_prompt: str, prompt_styles, step hr_second_pass_steps=hr_second_pass_steps, hr_resize_x=hr_resize_x, hr_resize_y=hr_resize_y, - hr_sampler=sd_samplers.samplers[hr_sampler_index - 1].name + hr_sampler=sd_samplers.samplers_for_img2img[hr_sampler_index - 1].name if hr_sampler_index != 0 else '---' ) diff --git a/modules/ui.py b/modules/ui.py index 6bbbc0f6..b408379f 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -673,7 +673,7 @@ def create_ui(): hr_resize_y = gr.Slider(minimum=0, maximum=2048, step=8, label="Resize height to", value=0, elem_id="txt2img_hr_resize_y") with FormRow(elem_id="txt2img_hires_fix_row3", variant="compact"): - hr_sampler_index = gr.Dropdown(label='Hires sampling method', elem_id=f"hr_sampler", choices=["---"] + [x.name for x in samplers], value="---", type="index") + hr_sampler_index = gr.Dropdown(label='Hires sampling method', elem_id=f"hr_sampler", choices=["---"] + [x.name for x in samplers_for_img2img], value="---", type="index") elif category == "batch": if not opts.dimensions_and_batch_together: -- cgit v1.2.3 From 8114959e7e937361b719cd85bec246ffd258dca6 Mon Sep 17 00:00:00 2001 From: invincibledude <> Date: Sun, 22 Jan 2023 14:28:53 +0300 Subject: Hr separate prompt test --- modules/processing.py | 23 ++++++++++++++++++++++- modules/txt2img.py | 6 ++++-- modules/ui.py | 10 ++++++++++ 3 files changed, 36 insertions(+), 3 deletions(-) (limited to 'modules/processing.py') diff --git a/modules/processing.py b/modules/processing.py index a873498b..f407e175 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -516,6 +516,23 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: else: p.all_negative_prompts = p.batch_size * p.n_iter * [shared.prompt_styles.apply_negative_styles_to_prompt(p.negative_prompt, p.styles)] + if type(p) == StableDiffusionProcessingTxt2Img: + if p.hr_enabled and p.is_hr_pass: + if p.hr_prompt: + if type(p.prompt) == list: + p.all_prompts = [shared.prompt_styles.apply_styles_to_prompt(x, p.styles) for x in p.hr_prompt] + else: + p.all_prompts = p.batch_size * p.n_iter * [ + shared.prompt_styles.apply_styles_to_prompt(p.hr_prompt, p.styles)] + + if p.hr_negative_prompt: + if type(p.negative_prompt) == list: + p.all_negative_prompts = [shared.prompt_styles.apply_negative_styles_to_prompt(x, p.styles) for x in + p.hr_negative_prompt] + else: + p.all_negative_prompts = p.batch_size * p.n_iter * [ + shared.prompt_styles.apply_negative_styles_to_prompt(p.hr_negative_prompt, p.styles)] + if type(seed) == list: p.all_seeds = seed else: @@ -710,7 +727,7 @@ def old_hires_fix_first_pass_dimensions(width, height): class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): sampler = None - def __init__(self, enable_hr: bool = False, denoising_strength: float = 0.75, firstphase_width: int = 0, firstphase_height: int = 0, hr_scale: float = 2.0, hr_upscaler: str = None, hr_second_pass_steps: int = 0, hr_resize_x: int = 0, hr_resize_y: int = 0, hr_sampler: str = '---', **kwargs): + def __init__(self, enable_hr: bool = False, denoising_strength: float = 0.75, firstphase_width: int = 0, firstphase_height: int = 0, hr_scale: float = 2.0, hr_upscaler: str = None, hr_second_pass_steps: int = 0, hr_resize_x: int = 0, hr_resize_y: int = 0, hr_sampler: str = '---', hr_prompt: str = '', hr_negative_prompt: str = '', **kwargs): super().__init__(**kwargs) self.enable_hr = enable_hr self.denoising_strength = denoising_strength @@ -722,6 +739,9 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): self.hr_upscale_to_x = hr_resize_x self.hr_upscale_to_y = hr_resize_y self.hr_sampler = hr_sampler + self.hr_prompt = hr_prompt if hr_prompt != '' else self.prompt + self.hr_negative_prompt = hr_negative_prompt if hr_negative_prompt != '' else self.negative_prompt + self.is_hr_pass = False if firstphase_width != 0 or firstphase_height != 0: self.hr_upscale_to_x = self.width @@ -808,6 +828,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): if not self.enable_hr: return samples + self.is_hr_pass = True target_width = self.hr_upscale_to_x target_height = self.hr_upscale_to_y diff --git a/modules/txt2img.py b/modules/txt2img.py index 2eb41f3d..c06f9f9d 100644 --- a/modules/txt2img.py +++ b/modules/txt2img.py @@ -8,7 +8,7 @@ import modules.processing as processing from modules.ui import plaintext_to_html -def txt2img(id_task: str, prompt: str, negative_prompt: str, prompt_styles, steps: int, sampler_index: int, restore_faces: bool, tiling: bool, n_iter: int, batch_size: int, cfg_scale: float, seed: int, subseed: int, subseed_strength: float, seed_resize_from_h: int, seed_resize_from_w: int, seed_enable_extras: bool, height: int, width: int, enable_hr: bool, denoising_strength: float, hr_scale: float, hr_upscaler: str, hr_second_pass_steps: int, hr_resize_x: int, hr_resize_y: int, hr_sampler_index: int, *args): +def txt2img(id_task: str, prompt: str, negative_prompt: str, prompt_styles, steps: int, sampler_index: int, restore_faces: bool, tiling: bool, n_iter: int, batch_size: int, cfg_scale: float, seed: int, subseed: int, subseed_strength: float, seed_resize_from_h: int, seed_resize_from_w: int, seed_enable_extras: bool, height: int, width: int, enable_hr: bool, denoising_strength: float, hr_scale: float, hr_upscaler: str, hr_second_pass_steps: int, hr_resize_x: int, hr_resize_y: int, hr_sampler_index: int, hr_prompt: str, hr_negative_prompt, *args): p = StableDiffusionProcessingTxt2Img( sd_model=shared.sd_model, outpath_samples=opts.outdir_samples or opts.outdir_txt2img_samples, @@ -38,7 +38,9 @@ def txt2img(id_task: str, prompt: str, negative_prompt: str, prompt_styles, step hr_second_pass_steps=hr_second_pass_steps, hr_resize_x=hr_resize_x, hr_resize_y=hr_resize_y, - hr_sampler=sd_samplers.samplers_for_img2img[hr_sampler_index - 1].name if hr_sampler_index != 0 else '---' + hr_sampler=sd_samplers.samplers_for_img2img[hr_sampler_index - 1].name if hr_sampler_index != 0 else '---', + hr_prompt=hr_prompt, + hr_negative_prompt=hr_negative_prompt ) p.scripts = modules.scripts.scripts_txt2img diff --git a/modules/ui.py b/modules/ui.py index b408379f..e0a9e40b 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -675,6 +675,14 @@ def create_ui(): with FormRow(elem_id="txt2img_hires_fix_row3", variant="compact"): hr_sampler_index = gr.Dropdown(label='Hires sampling method', elem_id=f"hr_sampler", choices=["---"] + [x.name for x in samplers_for_img2img], value="---", type="index") + with FormRow(elem_id="txt2img_hires_fix_row4", variant="compact"): + with gr.Column(scale=80): + with gr.Row(): + hr_prompt = gr.Textbox(label="Prompt", elem_id=f"hires_prompt", show_label=False, lines=3, placeholder="Prompt that will be used for hires fix pass") + with gr.Column(scale=80): + with gr.Row(): + hr_negative_prompt = gr.Textbox(label="Negative prompt", elem_id=f"hires_neg_prompt", show_label=False, lines=3, placeholder="Negative prompt that will be used for hires fix pass") + elif category == "batch": if not opts.dimensions_and_batch_together: with FormRow(elem_id="txt2img_column_batch"): @@ -734,6 +742,8 @@ def create_ui(): hr_resize_x, hr_resize_y, hr_sampler_index, + hr_prompt, + hr_negative_prompt, ] + custom_inputs, outputs=[ -- cgit v1.2.3 From b331ca784ad831de088ad3915b45da39c2a76fa8 Mon Sep 17 00:00:00 2001 From: invincibledude <> Date: Sun, 22 Jan 2023 14:35:34 +0300 Subject: Fix --- modules/processing.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'modules/processing.py') diff --git a/modules/processing.py b/modules/processing.py index f407e175..161999d5 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -517,7 +517,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: p.all_negative_prompts = p.batch_size * p.n_iter * [shared.prompt_styles.apply_negative_styles_to_prompt(p.negative_prompt, p.styles)] if type(p) == StableDiffusionProcessingTxt2Img: - if p.hr_enabled and p.is_hr_pass: + if p.enable_hr and p.is_hr_pass: if p.hr_prompt: if type(p.prompt) == list: p.all_prompts = [shared.prompt_styles.apply_styles_to_prompt(x, p.styles) for x in p.hr_prompt] -- cgit v1.2.3 From 81e0723d6559729f5b207ae04bc615318af5a11e Mon Sep 17 00:00:00 2001 From: invincibledude <> Date: Sun, 22 Jan 2023 14:41:41 +0300 Subject: Logging for debugging --- modules/processing.py | 3 +++ 1 file changed, 3 insertions(+) (limited to 'modules/processing.py') diff --git a/modules/processing.py b/modules/processing.py index 161999d5..eeab4b0c 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -518,12 +518,14 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: if type(p) == StableDiffusionProcessingTxt2Img: if p.enable_hr and p.is_hr_pass: + logging.info("Running hr pass with custom prompt") if p.hr_prompt: if type(p.prompt) == list: p.all_prompts = [shared.prompt_styles.apply_styles_to_prompt(x, p.styles) for x in p.hr_prompt] else: p.all_prompts = p.batch_size * p.n_iter * [ shared.prompt_styles.apply_styles_to_prompt(p.hr_prompt, p.styles)] + logging.info(p.all_prompts) if p.hr_negative_prompt: if type(p.negative_prompt) == list: @@ -532,6 +534,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: else: p.all_negative_prompts = p.batch_size * p.n_iter * [ shared.prompt_styles.apply_negative_styles_to_prompt(p.hr_negative_prompt, p.styles)] + logging.info(p.all_negative_prompts) if type(seed) == list: p.all_seeds = seed -- cgit v1.2.3 From f774a8d24ec57cf0b795fedb0c54f0304b43b4d9 Mon Sep 17 00:00:00 2001 From: invincibledude <> Date: Sun, 22 Jan 2023 14:52:01 +0300 Subject: Hr-fix separate prompt experimentation --- modules/processing.py | 43 ++++++++++++++++++++++--------------------- 1 file changed, 22 insertions(+), 21 deletions(-) (limited to 'modules/processing.py') diff --git a/modules/processing.py b/modules/processing.py index eeab4b0c..1133619f 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -516,25 +516,25 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: else: p.all_negative_prompts = p.batch_size * p.n_iter * [shared.prompt_styles.apply_negative_styles_to_prompt(p.negative_prompt, p.styles)] - if type(p) == StableDiffusionProcessingTxt2Img: - if p.enable_hr and p.is_hr_pass: - logging.info("Running hr pass with custom prompt") - if p.hr_prompt: - if type(p.prompt) == list: - p.all_prompts = [shared.prompt_styles.apply_styles_to_prompt(x, p.styles) for x in p.hr_prompt] - else: - p.all_prompts = p.batch_size * p.n_iter * [ - shared.prompt_styles.apply_styles_to_prompt(p.hr_prompt, p.styles)] - logging.info(p.all_prompts) - - if p.hr_negative_prompt: - if type(p.negative_prompt) == list: - p.all_negative_prompts = [shared.prompt_styles.apply_negative_styles_to_prompt(x, p.styles) for x in - p.hr_negative_prompt] - else: - p.all_negative_prompts = p.batch_size * p.n_iter * [ - shared.prompt_styles.apply_negative_styles_to_prompt(p.hr_negative_prompt, p.styles)] - logging.info(p.all_negative_prompts) + # if type(p) == StableDiffusionProcessingTxt2Img: + # if p.enable_hr and p.is_hr_pass: + # logging.info("Running hr pass with custom prompt") + # if p.hr_prompt: + # if type(p.prompt) == list: + # p.all_prompts = [shared.prompt_styles.apply_styles_to_prompt(x, p.styles) for x in p.hr_prompt] + # else: + # p.all_prompts = p.batch_size * p.n_iter * [ + # shared.prompt_styles.apply_styles_to_prompt(p.hr_prompt, p.styles)] + # logging.info(p.all_prompts) + # + # if p.hr_negative_prompt: + # if type(p.negative_prompt) == list: + # p.all_negative_prompts = [shared.prompt_styles.apply_negative_styles_to_prompt(x, p.styles) for x in + # p.hr_negative_prompt] + # else: + # p.all_negative_prompts = p.batch_size * p.n_iter * [ + # shared.prompt_styles.apply_negative_styles_to_prompt(p.hr_negative_prompt, p.styles)] + # logging.info(p.all_negative_prompts) if type(seed) == list: p.all_seeds = seed @@ -744,7 +744,6 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): self.hr_sampler = hr_sampler self.hr_prompt = hr_prompt if hr_prompt != '' else self.prompt self.hr_negative_prompt = hr_negative_prompt if hr_negative_prompt != '' else self.negative_prompt - self.is_hr_pass = False if firstphase_width != 0 or firstphase_height != 0: self.hr_upscale_to_x = self.width @@ -831,7 +830,9 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): if not self.enable_hr: return samples - self.is_hr_pass = True + self.prompt = self.hr_prompt + self.negative_prompt = self.hr_negative_prompt + target_width = self.hr_upscale_to_x target_height = self.hr_upscale_to_y -- cgit v1.2.3 From a9f0e7d53611cf11331e2befd34f0351b47795ee Mon Sep 17 00:00:00 2001 From: invincibledude <> Date: Sun, 22 Jan 2023 15:12:00 +0300 Subject: hr conditioning --- modules/processing.py | 72 ++++++++++++++++++++++++++++++++------------------- 1 file changed, 46 insertions(+), 26 deletions(-) (limited to 'modules/processing.py') diff --git a/modules/processing.py b/modules/processing.py index 1133619f..21886bb5 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -235,7 +235,7 @@ class StableDiffusionProcessing: def init(self, all_prompts, all_seeds, all_subseeds): pass - def sample(self, conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength, prompts): + def sample(self, conditioning, unconditional_conditioning, hr_conditioning, hr_uconditional_conditioning, seeds, subseeds, subseed_strength, prompts): raise NotImplementedError() def close(self): @@ -516,25 +516,25 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: else: p.all_negative_prompts = p.batch_size * p.n_iter * [shared.prompt_styles.apply_negative_styles_to_prompt(p.negative_prompt, p.styles)] - # if type(p) == StableDiffusionProcessingTxt2Img: - # if p.enable_hr and p.is_hr_pass: - # logging.info("Running hr pass with custom prompt") - # if p.hr_prompt: - # if type(p.prompt) == list: - # p.all_prompts = [shared.prompt_styles.apply_styles_to_prompt(x, p.styles) for x in p.hr_prompt] - # else: - # p.all_prompts = p.batch_size * p.n_iter * [ - # shared.prompt_styles.apply_styles_to_prompt(p.hr_prompt, p.styles)] - # logging.info(p.all_prompts) - # - # if p.hr_negative_prompt: - # if type(p.negative_prompt) == list: - # p.all_negative_prompts = [shared.prompt_styles.apply_negative_styles_to_prompt(x, p.styles) for x in - # p.hr_negative_prompt] - # else: - # p.all_negative_prompts = p.batch_size * p.n_iter * [ - # shared.prompt_styles.apply_negative_styles_to_prompt(p.hr_negative_prompt, p.styles)] - # logging.info(p.all_negative_prompts) + if type(p) == StableDiffusionProcessingTxt2Img: + if p.enable_hr and p.is_hr_pass: + logging.info("Running hr pass with custom prompt") + if p.hr_prompt: + if type(p.prompt) == list: + p.all_hr_prompts = [shared.prompt_styles.apply_styles_to_prompt(x, p.styles) for x in p.hr_prompt] + else: + p.all_hr_prompts = p.batch_size * p.n_iter * [ + shared.prompt_styles.apply_styles_to_prompt(p.hr_prompt, p.styles)] + logging.info(p.all_prompts) + + if p.hr_negative_prompt: + if type(p.negative_prompt) == list: + p.all_hr_negative_prompts = [shared.prompt_styles.apply_negative_styles_to_prompt(x, p.styles) for x in + p.hr_negative_prompt] + else: + p.all_hr_negative_prompts = p.batch_size * p.n_iter * [ + shared.prompt_styles.apply_negative_styles_to_prompt(p.hr_negative_prompt, p.styles)] + logging.info(p.all_negative_prompts) if type(seed) == list: p.all_seeds = seed @@ -607,6 +607,12 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: prompts = p.all_prompts[n * p.batch_size:(n + 1) * p.batch_size] negative_prompts = p.all_negative_prompts[n * p.batch_size:(n + 1) * p.batch_size] + + if type(p) == StableDiffusionProcessingTxt2Img: + if p.enable_hr: + hr_prompts = p.all_hr_prompts[n * p.batch_size:(n + 1) * p.batch_size] + hr_negative_prompts = p.all_negative_prompts[n * p.batch_size:(n + 1) * p.batch_size] + seeds = p.all_seeds[n * p.batch_size:(n + 1) * p.batch_size] subseeds = p.all_subseeds[n * p.batch_size:(n + 1) * p.batch_size] @@ -620,6 +626,12 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: uc = get_conds_with_caching(prompt_parser.get_learned_conditioning, negative_prompts, p.steps, cached_uc) c = get_conds_with_caching(prompt_parser.get_multicond_learned_conditioning, prompts, p.steps, cached_c) + if type(p) == StableDiffusionProcessingTxt2Img: + if p.enable_hr: + hr_uc = get_conds_with_caching(prompt_parser.get_learned_conditioning, negative_prompts, p.steps, + cached_uc) + hr_c = get_conds_with_caching(prompt_parser.get_multicond_learned_conditioning, prompts, p.steps, + cached_c) if len(model_hijack.comments) > 0: for comment in model_hijack.comments: @@ -629,7 +641,16 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: shared.state.job = f"Batch {n+1} out of {p.n_iter}" with devices.autocast(): - samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength, prompts=prompts) + if type(p) == StableDiffusionProcessingTxt2Img: + if p.enable_hr: + samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, hr_conditioning=hr_c, hr_uconditional_conditioning=hr_uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength, prompts=prompts) + samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, + subseeds=subseeds, + subseed_strength=p.subseed_strength, prompts=prompts) + else: + samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, + subseeds=subseeds, + subseed_strength=p.subseed_strength, prompts=prompts) x_samples_ddim = [decode_first_stage(p.sd_model, samples_ddim[i:i+1].to(dtype=devices.dtype_vae))[0].cpu() for i in range(samples_ddim.size(0))] for x in x_samples_ddim: @@ -744,6 +765,8 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): self.hr_sampler = hr_sampler self.hr_prompt = hr_prompt if hr_prompt != '' else self.prompt self.hr_negative_prompt = hr_negative_prompt if hr_negative_prompt != '' else self.negative_prompt + self.all_hr_prompts = None + self.all_hr_negative_prompts = None if firstphase_width != 0 or firstphase_height != 0: self.hr_upscale_to_x = self.width @@ -817,7 +840,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): if self.hr_upscaler is not None: self.extra_generation_params["Hires upscaler"] = self.hr_upscaler - def sample(self, conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength, prompts): + def sample(self, conditioning, unconditional_conditioning, hr_conditioning, hr_uconditional_conditioning, seeds, subseeds, subseed_strength, prompts): self.sampler = sd_samplers.create_sampler(self.sampler_name, self.sd_model) latent_scale_mode = shared.latent_upscale_modes.get(self.hr_upscaler, None) if self.hr_upscaler is not None else shared.latent_upscale_modes.get(shared.latent_upscale_default_mode, "nearest") @@ -830,9 +853,6 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): if not self.enable_hr: return samples - self.prompt = self.hr_prompt - self.negative_prompt = self.hr_negative_prompt - target_width = self.hr_upscale_to_x target_height = self.hr_upscale_to_y @@ -904,7 +924,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): x = None devices.torch_gc() - samples = self.sampler.sample_img2img(self, samples, noise, conditioning, unconditional_conditioning, steps=self.hr_second_pass_steps or self.steps, image_conditioning=image_conditioning) + samples = self.sampler.sample_img2img(self, samples, noise, hr_conditioning, hr_unconditional_conditioning, steps=self.hr_second_pass_steps or self.steps, image_conditioning=image_conditioning) return samples -- cgit v1.2.3 From 4e0cf7d4eda3d590df3e4b28654037d2dfb7ab94 Mon Sep 17 00:00:00 2001 From: invincibledude <> Date: Sun, 22 Jan 2023 15:15:08 +0300 Subject: hr conditioning --- modules/processing.py | 34 +++++++++++++--------------------- 1 file changed, 13 insertions(+), 21 deletions(-) (limited to 'modules/processing.py') diff --git a/modules/processing.py b/modules/processing.py index 21886bb5..6b49b4e3 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -517,24 +517,16 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: p.all_negative_prompts = p.batch_size * p.n_iter * [shared.prompt_styles.apply_negative_styles_to_prompt(p.negative_prompt, p.styles)] if type(p) == StableDiffusionProcessingTxt2Img: - if p.enable_hr and p.is_hr_pass: - logging.info("Running hr pass with custom prompt") - if p.hr_prompt: - if type(p.prompt) == list: - p.all_hr_prompts = [shared.prompt_styles.apply_styles_to_prompt(x, p.styles) for x in p.hr_prompt] - else: - p.all_hr_prompts = p.batch_size * p.n_iter * [ - shared.prompt_styles.apply_styles_to_prompt(p.hr_prompt, p.styles)] - logging.info(p.all_prompts) - - if p.hr_negative_prompt: - if type(p.negative_prompt) == list: - p.all_hr_negative_prompts = [shared.prompt_styles.apply_negative_styles_to_prompt(x, p.styles) for x in - p.hr_negative_prompt] - else: - p.all_hr_negative_prompts = p.batch_size * p.n_iter * [ - shared.prompt_styles.apply_negative_styles_to_prompt(p.hr_negative_prompt, p.styles)] - logging.info(p.all_negative_prompts) + if p.enable_hr: + if type(p.prompt) == list: + p.all_hr_prompts = [shared.prompt_styles.apply_styles_to_prompt(x, p.styles) for x in p.hr_prompt] + else: + p.all_hr_prompts = p.batch_size * p.n_iter * [shared.prompt_styles.apply_styles_to_prompt(p.hr_prompt, p.styles)] + + if type(p.negative_prompt) == list: + p.all_hr_negative_prompts = [shared.prompt_styles.apply_negative_styles_to_prompt(x, p.styles) for x in p.hr_negative_prompt] + else: + p.all_hr_negative_prompts = p.batch_size * p.n_iter * [shared.prompt_styles.apply_negative_styles_to_prompt(p.hr_negative_prompt, p.styles)] if type(seed) == list: p.all_seeds = seed @@ -628,9 +620,9 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: c = get_conds_with_caching(prompt_parser.get_multicond_learned_conditioning, prompts, p.steps, cached_c) if type(p) == StableDiffusionProcessingTxt2Img: if p.enable_hr: - hr_uc = get_conds_with_caching(prompt_parser.get_learned_conditioning, negative_prompts, p.steps, + hr_uc = get_conds_with_caching(prompt_parser.get_learned_conditioning, hr_negative_prompts, p.steps, cached_uc) - hr_c = get_conds_with_caching(prompt_parser.get_multicond_learned_conditioning, prompts, p.steps, + hr_c = get_conds_with_caching(prompt_parser.get_multicond_learned_conditioning, hr_prompts, p.steps, cached_c) if len(model_hijack.comments) > 0: @@ -840,7 +832,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): if self.hr_upscaler is not None: self.extra_generation_params["Hires upscaler"] = self.hr_upscaler - def sample(self, conditioning, unconditional_conditioning, hr_conditioning, hr_uconditional_conditioning, seeds, subseeds, subseed_strength, prompts): + def sample(self, conditioning, unconditional_conditioning, hr_conditioning, hr_unconditional_conditioning, seeds, subseeds, subseed_strength, prompts): self.sampler = sd_samplers.create_sampler(self.sampler_name, self.sd_model) latent_scale_mode = shared.latent_upscale_modes.get(self.hr_upscaler, None) if self.hr_upscaler is not None else shared.latent_upscale_modes.get(shared.latent_upscale_default_mode, "nearest") -- cgit v1.2.3 From c5d4c87c02ce4c503de149db5ee3e87af4402cf0 Mon Sep 17 00:00:00 2001 From: invincibledude <> Date: Sun, 22 Jan 2023 15:17:43 +0300 Subject: hr conditioning --- modules/processing.py | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'modules/processing.py') diff --git a/modules/processing.py b/modules/processing.py index 6b49b4e3..a81ace6f 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -635,10 +635,11 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: with devices.autocast(): if type(p) == StableDiffusionProcessingTxt2Img: if p.enable_hr: - samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, hr_conditioning=hr_c, hr_uconditional_conditioning=hr_uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength, prompts=prompts) - samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, - subseeds=subseeds, - subseed_strength=p.subseed_strength, prompts=prompts) + samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, hr_conditioning=hr_c, hr_unconditional_conditioning=hr_uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength, prompts=prompts) + else: + samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, subseeds=subseeds, + subseed_strength=p.subseed_strength, prompts=prompts) + else: samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, subseeds=subseeds, -- cgit v1.2.3 From 2ab2bce74d7b7affb80b55da9d1ffb219129c1ef Mon Sep 17 00:00:00 2001 From: invincibledude <> Date: Sun, 22 Jan 2023 15:28:38 +0300 Subject: hr conditioning --- modules/processing.py | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-) (limited to 'modules/processing.py') diff --git a/modules/processing.py b/modules/processing.py index a81ace6f..bab1c101 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -235,7 +235,7 @@ class StableDiffusionProcessing: def init(self, all_prompts, all_seeds, all_subseeds): pass - def sample(self, conditioning, unconditional_conditioning, hr_conditioning, hr_uconditional_conditioning, seeds, subseeds, subseed_strength, prompts): + def sample(self, conditioning, unconditional_conditioning, hr_conditioning=None, hr_unconditional_conditioning=None, seeds, subseeds, subseed_strength, prompts): raise NotImplementedError() def close(self): @@ -517,7 +517,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: p.all_negative_prompts = p.batch_size * p.n_iter * [shared.prompt_styles.apply_negative_styles_to_prompt(p.negative_prompt, p.styles)] if type(p) == StableDiffusionProcessingTxt2Img: - if p.enable_hr: + if p.enable_hr and p.hr_prompt != '': if type(p.prompt) == list: p.all_hr_prompts = [shared.prompt_styles.apply_styles_to_prompt(x, p.styles) for x in p.hr_prompt] else: @@ -601,7 +601,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: negative_prompts = p.all_negative_prompts[n * p.batch_size:(n + 1) * p.batch_size] if type(p) == StableDiffusionProcessingTxt2Img: - if p.enable_hr: + if p.enable_hr and p.hr_prompt != '': hr_prompts = p.all_hr_prompts[n * p.batch_size:(n + 1) * p.batch_size] hr_negative_prompts = p.all_negative_prompts[n * p.batch_size:(n + 1) * p.batch_size] @@ -619,7 +619,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: uc = get_conds_with_caching(prompt_parser.get_learned_conditioning, negative_prompts, p.steps, cached_uc) c = get_conds_with_caching(prompt_parser.get_multicond_learned_conditioning, prompts, p.steps, cached_c) if type(p) == StableDiffusionProcessingTxt2Img: - if p.enable_hr: + if p.enable_hr and p.hr_prompt != '': hr_uc = get_conds_with_caching(prompt_parser.get_learned_conditioning, hr_negative_prompts, p.steps, cached_uc) hr_c = get_conds_with_caching(prompt_parser.get_multicond_learned_conditioning, hr_prompts, p.steps, @@ -635,7 +635,12 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: with devices.autocast(): if type(p) == StableDiffusionProcessingTxt2Img: if p.enable_hr: - samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, hr_conditioning=hr_c, hr_unconditional_conditioning=hr_uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength, prompts=prompts) + if p.hr_prompts != '': + samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, hr_conditioning=hr_c, hr_unconditional_conditioning=hr_uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength, prompts=prompts) + else: + samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, hr_conditioning=c, + hr_unconditional_conditioning=uc, seeds=seeds, subseeds=subseeds, + subseed_strength=p.subseed_strength, prompts=prompts) else: samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength, prompts=prompts) @@ -756,8 +761,8 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): self.hr_upscale_to_x = hr_resize_x self.hr_upscale_to_y = hr_resize_y self.hr_sampler = hr_sampler - self.hr_prompt = hr_prompt if hr_prompt != '' else self.prompt - self.hr_negative_prompt = hr_negative_prompt if hr_negative_prompt != '' else self.negative_prompt + self.hr_prompt = hr_prompt if hr_prompt != '' else '' + self.hr_negative_prompt = hr_negative_prompt if hr_negative_prompt != '' else '' self.all_hr_prompts = None self.all_hr_negative_prompts = None -- cgit v1.2.3 From 125d5c8d96eb374a7ba214dba51da9cf30da6564 Mon Sep 17 00:00:00 2001 From: invincibledude <> Date: Sun, 22 Jan 2023 15:31:11 +0300 Subject: hr conditioning --- modules/processing.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'modules/processing.py') diff --git a/modules/processing.py b/modules/processing.py index bab1c101..f0073d1a 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -235,7 +235,7 @@ class StableDiffusionProcessing: def init(self, all_prompts, all_seeds, all_subseeds): pass - def sample(self, conditioning, unconditional_conditioning, hr_conditioning=None, hr_unconditional_conditioning=None, seeds, subseeds, subseed_strength, prompts): + def sample(self, conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength, prompts, hr_conditioning=None, hr_unconditional_conditioning=None): raise NotImplementedError() def close(self): @@ -838,7 +838,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): if self.hr_upscaler is not None: self.extra_generation_params["Hires upscaler"] = self.hr_upscaler - def sample(self, conditioning, unconditional_conditioning, hr_conditioning, hr_unconditional_conditioning, seeds, subseeds, subseed_strength, prompts): + def sample(self, conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength, prompts, hr_conditioning=None, hr_unconditional_conditioning=None): self.sampler = sd_samplers.create_sampler(self.sampler_name, self.sd_model) latent_scale_mode = shared.latent_upscale_modes.get(self.hr_upscaler, None) if self.hr_upscaler is not None else shared.latent_upscale_modes.get(shared.latent_upscale_default_mode, "nearest") -- cgit v1.2.3 From 34f6d667429ec3d4e0f09c6148fd37e66c460cb7 Mon Sep 17 00:00:00 2001 From: invincibledude <> Date: Sun, 22 Jan 2023 15:32:47 +0300 Subject: hr conditioning --- modules/processing.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'modules/processing.py') diff --git a/modules/processing.py b/modules/processing.py index f0073d1a..b2de8f92 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -635,7 +635,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: with devices.autocast(): if type(p) == StableDiffusionProcessingTxt2Img: if p.enable_hr: - if p.hr_prompts != '': + if p.hr_prompt != '': samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, hr_conditioning=hr_c, hr_unconditional_conditioning=hr_uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength, prompts=prompts) else: samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, hr_conditioning=c, -- cgit v1.2.3 From bbb1e35ea29f8cfc6a6db3b28b10bfbc99033c70 Mon Sep 17 00:00:00 2001 From: invincibledude <> Date: Sun, 22 Jan 2023 15:44:59 +0300 Subject: UI and PNG info improvements --- modules/processing.py | 3 +++ modules/ui.py | 2 ++ 2 files changed, 5 insertions(+) (limited to 'modules/processing.py') diff --git a/modules/processing.py b/modules/processing.py index b2de8f92..0cf4771e 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -789,6 +789,9 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): if self.hr_resize_x == 0 and self.hr_resize_y == 0: self.extra_generation_params["Hires upscale"] = self.hr_scale + self.extra_generation_params["Hires sampler"] = self.hr_sampler + self.extra_generation_params["Hires prompt"] = self.hr_prompt + self.extra_generation_params["Hires negative prompt"] = self.hr_negative_prompt self.hr_upscale_to_x = int(self.width * self.hr_scale) self.hr_upscale_to_y = int(self.height * self.hr_scale) else: diff --git a/modules/ui.py b/modules/ui.py index 1656e76d..64180889 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -800,6 +800,8 @@ def create_ui(): (hr_resize_x, "Hires resize-1"), (hr_resize_y, "Hires resize-2"), (hr_sampler_index, "Hires sampling method"), + (hr_prompt, "Hires prompt"), + (hr_negative_prompt, "Hires negative prompt"), *modules.scripts.scripts_txt2img.infotext_fields ] parameters_copypaste.add_paste_fields("txt2img", None, txt2img_paste_fields) -- cgit v1.2.3 From a5c2b5ed8991e0e1ffea7b595ab13f93715dfa5c Mon Sep 17 00:00:00 2001 From: invincibledude <> Date: Sun, 22 Jan 2023 15:50:20 +0300 Subject: UI and PNG info improvements --- modules/processing.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'modules/processing.py') diff --git a/modules/processing.py b/modules/processing.py index 0cf4771e..8b4b2399 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -790,8 +790,8 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): if self.hr_resize_x == 0 and self.hr_resize_y == 0: self.extra_generation_params["Hires upscale"] = self.hr_scale self.extra_generation_params["Hires sampler"] = self.hr_sampler - self.extra_generation_params["Hires prompt"] = self.hr_prompt - self.extra_generation_params["Hires negative prompt"] = self.hr_negative_prompt + self.extra_generation_params["Hires prompt"] = f"({self.hr_prompt})" + self.extra_generation_params["Hires negative prompt"] = f"({self.hr_negative_prompt})" self.hr_upscale_to_x = int(self.width * self.hr_scale) self.hr_upscale_to_y = int(self.height * self.hr_scale) else: -- cgit v1.2.3 From 7f62300f7d496501a730d28f3aaaee885513998b Mon Sep 17 00:00:00 2001 From: invincibledude <> Date: Sun, 22 Jan 2023 16:29:08 +0300 Subject: Gen params paste improvement --- modules/processing.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'modules/processing.py') diff --git a/modules/processing.py b/modules/processing.py index 8b4b2399..c56717f6 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -790,8 +790,8 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): if self.hr_resize_x == 0 and self.hr_resize_y == 0: self.extra_generation_params["Hires upscale"] = self.hr_scale self.extra_generation_params["Hires sampler"] = self.hr_sampler - self.extra_generation_params["Hires prompt"] = f"({self.hr_prompt})" - self.extra_generation_params["Hires negative prompt"] = f"({self.hr_negative_prompt})" + self.extra_generation_params["Hires prompt"] = f'"{self.hr_prompt}"' + self.extra_generation_params["Hires negative prompt"] = f'"{self.hr_negative_prompt}"' self.hr_upscale_to_x = int(self.width * self.hr_scale) self.hr_upscale_to_y = int(self.height * self.hr_scale) else: -- cgit v1.2.3 From 3bc8ee998db5f461b8011a72e6f167012ccb8bc1 Mon Sep 17 00:00:00 2001 From: invincibledude <> Date: Sun, 22 Jan 2023 16:35:42 +0300 Subject: Gen params paste improvement --- modules/generation_parameters_copypaste.py | 4 ++-- modules/processing.py | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'modules/processing.py') diff --git a/modules/generation_parameters_copypaste.py b/modules/generation_parameters_copypaste.py index 44c8273f..98098cc8 100644 --- a/modules/generation_parameters_copypaste.py +++ b/modules/generation_parameters_copypaste.py @@ -269,9 +269,9 @@ Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 965400086, Size: 512x512, Model res[k] = v if k.startswith("Hires prompt"): - res["Hires prompt"] = v[1:][:-1] + res["Hires prompt"] = v[1:][:-1].replace(';', ',') elif k.startswith("Hires negative prompt"): - res["Hires negative prompt"] = v[1:][:-1] + res["Hires negative prompt"] = v[1:][:-1].replace(';', ',') # Missing CLIP skip means it was set to 1 (the default) if "Clip skip" not in res: diff --git a/modules/processing.py b/modules/processing.py index c56717f6..01c1b53c 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -790,8 +790,8 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): if self.hr_resize_x == 0 and self.hr_resize_y == 0: self.extra_generation_params["Hires upscale"] = self.hr_scale self.extra_generation_params["Hires sampler"] = self.hr_sampler - self.extra_generation_params["Hires prompt"] = f'"{self.hr_prompt}"' - self.extra_generation_params["Hires negative prompt"] = f'"{self.hr_negative_prompt}"' + self.extra_generation_params["Hires prompt"] = f'({self.hr_prompt.replace(",", ";")})' + self.extra_generation_params["Hires negative prompt"] = f'({self.hr_negative_prompt.replace(",", ";")})' self.hr_upscale_to_x = int(self.width * self.hr_scale) self.hr_upscale_to_y = int(self.height * self.hr_scale) else: -- cgit v1.2.3 From c92ec3a9255a8364f4212d5e7434da1785752737 Mon Sep 17 00:00:00 2001 From: invincibledude <> Date: Sun, 29 Jan 2023 19:07:00 +0300 Subject: Extra networks loading fix --- modules/processing.py | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) (limited to 'modules/processing.py') diff --git a/modules/processing.py b/modules/processing.py index 605c541e..da890fb3 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -555,6 +555,10 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: model_hijack.embedding_db.load_textual_inversion_embeddings() _, extra_network_data = extra_networks.parse_prompts(p.all_prompts[0:1]) + if type(p) == StableDiffusionProcessingTxt2Img: + if p.enable_hr and p.hr_prompt != '': + _, hr_extra_network_data = extra_networks.parse_prompts(p.all_hr_prompts[0:1]) + if p.scripts is not None: p.scripts.process(p) @@ -594,7 +598,11 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: sd_vae_approx.model() if not p.disable_extra_networks: - extra_networks.activate(p, extra_network_data) + if type(p) == StableDiffusionProcessingTxt2Img: + if p.enable_hr and p.hr_prompt != '': + extra_networks.activate(p, extra_network_data + hr_extra_network_data) + else: + extra_networks.activate(p, extra_network_data) with open(os.path.join(paths.data_path, "params.txt"), "w", encoding="utf8") as file: processed = Processed(p, [], p.seed, "") @@ -745,7 +753,11 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: images.save_image(grid, p.outpath_grids, "grid", p.all_seeds[0], p.all_prompts[0], opts.grid_format, info=infotext(), short_filename=not opts.grid_extended_filename, p=p, grid=True) if not p.disable_extra_networks: - extra_networks.deactivate(p, extra_network_data) + if type(p) == StableDiffusionProcessingTxt2Img: + if p.enable_hr and p.hr_prompt != '': + extra_networks.deactivate(p, extra_network_data + hr_extra_network_data) + else: + extra_networks.deactivate(p, extra_network_data) devices.torch_gc() -- cgit v1.2.3 From 6127d2ff1bc5c3bc81d876e6dbc9a60f79aec898 Mon Sep 17 00:00:00 2001 From: invincibledude <> Date: Sun, 29 Jan 2023 19:13:27 +0300 Subject: Extra networks loading fix --- modules/processing.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'modules/processing.py') diff --git a/modules/processing.py b/modules/processing.py index da890fb3..a56915c5 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -600,7 +600,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: if not p.disable_extra_networks: if type(p) == StableDiffusionProcessingTxt2Img: if p.enable_hr and p.hr_prompt != '': - extra_networks.activate(p, extra_network_data + hr_extra_network_data) + extra_networks.activate(p, extra_network_data | hr_extra_network_data) else: extra_networks.activate(p, extra_network_data) @@ -755,7 +755,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: if not p.disable_extra_networks: if type(p) == StableDiffusionProcessingTxt2Img: if p.enable_hr and p.hr_prompt != '': - extra_networks.deactivate(p, extra_network_data + hr_extra_network_data) + extra_networks.deactivate(p, extra_network_data | hr_extra_network_data) else: extra_networks.deactivate(p, extra_network_data) -- cgit v1.2.3 From 9beeef6267ecbcb16f8b24e0092194f0f00142a6 Mon Sep 17 00:00:00 2001 From: invincibledude <> Date: Sun, 29 Jan 2023 19:16:17 +0300 Subject: Extra networks loading fix --- modules/processing.py | 13 +++---------- 1 file changed, 3 insertions(+), 10 deletions(-) (limited to 'modules/processing.py') diff --git a/modules/processing.py b/modules/processing.py index a56915c5..98e83c69 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -558,6 +558,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: if type(p) == StableDiffusionProcessingTxt2Img: if p.enable_hr and p.hr_prompt != '': _, hr_extra_network_data = extra_networks.parse_prompts(p.all_hr_prompts[0:1]) + extra_network_data.update(hr_extra_network_data) if p.scripts is not None: @@ -598,11 +599,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: sd_vae_approx.model() if not p.disable_extra_networks: - if type(p) == StableDiffusionProcessingTxt2Img: - if p.enable_hr and p.hr_prompt != '': - extra_networks.activate(p, extra_network_data | hr_extra_network_data) - else: - extra_networks.activate(p, extra_network_data) + extra_networks.activate(p, extra_network_data) with open(os.path.join(paths.data_path, "params.txt"), "w", encoding="utf8") as file: processed = Processed(p, [], p.seed, "") @@ -753,11 +750,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: images.save_image(grid, p.outpath_grids, "grid", p.all_seeds[0], p.all_prompts[0], opts.grid_format, info=infotext(), short_filename=not opts.grid_extended_filename, p=p, grid=True) if not p.disable_extra_networks: - if type(p) == StableDiffusionProcessingTxt2Img: - if p.enable_hr and p.hr_prompt != '': - extra_networks.deactivate(p, extra_network_data | hr_extra_network_data) - else: - extra_networks.deactivate(p, extra_network_data) + extra_networks.deactivate(p, extra_network_data) devices.torch_gc() -- cgit v1.2.3 From 425eab34641e8e378db610d6a2b23f3ababe1058 Mon Sep 17 00:00:00 2001 From: invincibledude <> Date: Sun, 29 Jan 2023 19:26:31 +0300 Subject: Extra network in hr abomination fix --- modules/processing.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'modules/processing.py') diff --git a/modules/processing.py b/modules/processing.py index 98e83c69..a2a91a5b 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -558,7 +558,8 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: if type(p) == StableDiffusionProcessingTxt2Img: if p.enable_hr and p.hr_prompt != '': _, hr_extra_network_data = extra_networks.parse_prompts(p.all_hr_prompts[0:1]) - extra_network_data.update(hr_extra_network_data) + if p.all_hr_prompts != p.all_prompts: + extra_network_data.update(hr_extra_network_data) if p.scripts is not None: -- cgit v1.2.3 From c3bd113a0b969732a324aff415c49ea9ad434707 Mon Sep 17 00:00:00 2001 From: InvincibleDude <81354513+InvincibleDude@users.noreply.github.com> Date: Sun, 5 Feb 2023 15:24:41 +0000 Subject: Image info fix --- modules/processing.py | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'modules/processing.py') diff --git a/modules/processing.py b/modules/processing.py index 61e6dfcd..43fac21c 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -808,6 +808,13 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): def init(self, all_prompts, all_seeds, all_subseeds): if self.enable_hr: + if self.hr_sampler != '---': + self.extra_generation_params["Hires sampler"] = self.hr_sampler + + if self.hr_prompt != '': + self.extra_generation_params["Hires prompt"] = f'({self.hr_prompt.replace(",", ";")})' + self.extra_generation_params["Hires negative prompt"] = f'({self.hr_negative_prompt.replace(",", ";")})' + if opts.use_old_hires_fix_width_height and self.applied_old_hires_behavior_to != (self.width, self.height): self.hr_resize_x = self.width self.hr_resize_y = self.height @@ -819,9 +826,6 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): if self.hr_resize_x == 0 and self.hr_resize_y == 0: self.extra_generation_params["Hires upscale"] = self.hr_scale - self.extra_generation_params["Hires sampler"] = self.hr_sampler - self.extra_generation_params["Hires prompt"] = f'({self.hr_prompt.replace(",", ";")})' - self.extra_generation_params["Hires negative prompt"] = f'({self.hr_negative_prompt.replace(",", ";")})' self.hr_upscale_to_x = int(self.width * self.hr_scale) self.hr_upscale_to_y = int(self.height * self.hr_scale) else: -- cgit v1.2.3 From 51f81efb02876d24c9e6d844e8c0cbd2384f6514 Mon Sep 17 00:00:00 2001 From: InvincibleDude <81354513+InvincibleDude@users.noreply.github.com> Date: Wed, 1 Mar 2023 21:30:20 +0300 Subject: Image processing changes Image processing changes --- modules/processing.py | 76 +++++++++++++++++++++++++-------------------------- 1 file changed, 38 insertions(+), 38 deletions(-) (limited to 'modules/processing.py') diff --git a/modules/processing.py b/modules/processing.py index 43fac21c..72dd3f6f 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -528,7 +528,9 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: p.all_negative_prompts = p.batch_size * p.n_iter * [shared.prompt_styles.apply_negative_styles_to_prompt(p.negative_prompt, p.styles)] if type(p) == StableDiffusionProcessingTxt2Img: - if p.enable_hr and p.hr_prompt != '': + if p.enable_hr and p.hr_prompt == '': + p.all_hr_prompts, p.all_hr_negative_prompts = p.all_prompts, p.all_negative_prompts + elif p.enable_hr and p.hr_prompt != '': if type(p.prompt) == list: p.all_hr_prompts = [shared.prompt_styles.apply_styles_to_prompt(x, p.styles) for x in p.hr_prompt] else: @@ -555,14 +557,6 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: if os.path.exists(cmd_opts.embeddings_dir) and not p.do_not_reload_embeddings: model_hijack.embedding_db.load_textual_inversion_embeddings() - _, extra_network_data = extra_networks.parse_prompts(p.all_prompts[0:1]) - if type(p) == StableDiffusionProcessingTxt2Img: - if p.enable_hr and p.hr_prompt != '': - _, hr_extra_network_data = extra_networks.parse_prompts(p.all_hr_prompts[0:1]) - if p.all_hr_prompts != p.all_prompts: - extra_network_data.update(hr_extra_network_data) - - if p.scripts is not None: p.scripts.process(p) @@ -600,13 +594,6 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: if shared.opts.live_previews_enable and opts.show_progress_type == "Approx NN": sd_vae_approx.model() - if not p.disable_extra_networks: - extra_networks.activate(p, extra_network_data) - - with open(os.path.join(paths.data_path, "params.txt"), "w", encoding="utf8") as file: - processed = Processed(p, [], p.seed, "") - file.write(processed.infotext(p, 0)) - if state.job_count == -1: state.job_count = p.n_iter @@ -623,9 +610,12 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: negative_prompts = p.all_negative_prompts[n * p.batch_size:(n + 1) * p.batch_size] if type(p) == StableDiffusionProcessingTxt2Img: - if p.enable_hr and p.hr_prompt != '': - hr_prompts = p.all_hr_prompts[n * p.batch_size:(n + 1) * p.batch_size] - hr_negative_prompts = p.all_negative_prompts[n * p.batch_size:(n + 1) * p.batch_size] + if p.enable_hr: + if p.hr_prompt == '': + hr_prompts, hr_negative_prompts = prompts, negative_prompts + else: + hr_prompts = p.all_hr_prompts[n * p.batch_size:(n + 1) * p.batch_size] + hr_negative_prompts = p.all_negative_prompts[n * p.batch_size:(n + 1) * p.batch_size] seeds = p.all_seeds[n * p.batch_size:(n + 1) * p.batch_size] subseeds = p.all_subseeds[n * p.batch_size:(n + 1) * p.batch_size] @@ -633,19 +623,40 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: if len(prompts) == 0: break - prompts, _ = extra_networks.parse_prompts(prompts) + prompts, extra_network_data = extra_networks.parse_prompts(prompts) + if type(p) == StableDiffusionProcessingTxt2Img: + if p.enable_hr and hr_prompts != prompts: + _, hr_extra_network_data = extra_networks.parse_prompts(hr_prompts) + extra_network_data.update(hr_extra_network_data) + + + + if not p.disable_extra_networks: + with devices.autocast(): + extra_networks.activate(p, extra_network_data) if p.scripts is not None: p.scripts.process_batch(p, batch_number=n, prompts=prompts, seeds=seeds, subseeds=subseeds) + # params.txt should be saved after scripts.process_batch, since the + # infotext could be modified by that callback + # Example: a wildcard processed by process_batch sets an extra model + # strength, which is saved as "Model Strength: 1.0" in the infotext + if n == 0: + with open(os.path.join(paths.data_path, "params.txt"), "w", encoding="utf8") as file: + processed = Processed(p, [], p.seed, "") + file.write(processed.infotext(p, 0)) + uc = get_conds_with_caching(prompt_parser.get_learned_conditioning, negative_prompts, p.steps, cached_uc) c = get_conds_with_caching(prompt_parser.get_multicond_learned_conditioning, prompts, p.steps, cached_c) + if type(p) == StableDiffusionProcessingTxt2Img: - if p.enable_hr and p.hr_prompt != '': - hr_uc = get_conds_with_caching(prompt_parser.get_learned_conditioning, hr_negative_prompts, p.steps, - cached_uc) - hr_c = get_conds_with_caching(prompt_parser.get_multicond_learned_conditioning, hr_prompts, p.steps, - cached_c) + if p.enable_hr: + if prompts != hr_prompts: + hr_uc = get_conds_with_caching(prompt_parser.get_learned_conditioning, hr_negative_prompts, p.steps, cached_uc) + hr_c = get_conds_with_caching(prompt_parser.get_multicond_learned_conditioning, hr_prompts, p.steps, cached_c) + else: + hr_uc, hr_c = uc, c if len(model_hijack.comments) > 0: for comment in model_hijack.comments: @@ -658,20 +669,9 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: with devices.without_autocast() if devices.unet_needs_upcast else devices.autocast(): if type(p) == StableDiffusionProcessingTxt2Img: if p.enable_hr: - if p.hr_prompt != '': - samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, hr_conditioning=hr_c, hr_unconditional_conditioning=hr_uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength, prompts=prompts) - else: - samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, hr_conditioning=c, - hr_unconditional_conditioning=uc, seeds=seeds, subseeds=subseeds, - subseed_strength=p.subseed_strength, prompts=prompts) - else: - samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, subseeds=subseeds, - subseed_strength=p.subseed_strength, prompts=prompts) - + samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, hr_conditioning=hr_c, hr_unconditional_conditioning=hr_uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength, prompts=prompts) else: - samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, - subseeds=subseeds, - subseed_strength=p.subseed_strength, prompts=prompts) + samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength, prompts=prompts) x_samples_ddim = [decode_first_stage(p.sd_model, samples_ddim[i:i+1].to(dtype=devices.dtype_vae))[0].cpu() for i in range(samples_ddim.size(0))] for x in x_samples_ddim: -- cgit v1.2.3 From b9fdb9f701e576ce48458fdf756187c2d1725649 Mon Sep 17 00:00:00 2001 From: InvincibleDude <81354513+InvincibleDude@users.noreply.github.com> Date: Sat, 4 Mar 2023 18:09:05 +0000 Subject: Fix crash when hr is disabled --- modules/processing.py | 2 ++ 1 file changed, 2 insertions(+) (limited to 'modules/processing.py') diff --git a/modules/processing.py b/modules/processing.py index 25479c06..f5cc2433 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -670,6 +670,8 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: if type(p) == StableDiffusionProcessingTxt2Img: if p.enable_hr: samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, hr_conditioning=hr_c, hr_unconditional_conditioning=hr_uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength, prompts=prompts) + else: + samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength, prompts=prompts) else: samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength, prompts=prompts) -- cgit v1.2.3 From f6e27378404631d951656388fc178b784fe1495b Mon Sep 17 00:00:00 2001 From: InvincibleDude <81354513+InvincibleDude@users.noreply.github.com> Date: Fri, 10 Mar 2023 12:13:55 +0000 Subject: Negative prompt fix --- modules/processing.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'modules/processing.py') diff --git a/modules/processing.py b/modules/processing.py index f5cc2433..694e2637 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -615,7 +615,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: hr_prompts, hr_negative_prompts = prompts, negative_prompts else: hr_prompts = p.all_hr_prompts[n * p.batch_size:(n + 1) * p.batch_size] - hr_negative_prompts = p.all_negative_prompts[n * p.batch_size:(n + 1) * p.batch_size] + hr_negative_prompts = p.all_hr_negative_prompts[n * p.batch_size:(n + 1) * p.batch_size] seeds = p.all_seeds[n * p.batch_size:(n + 1) * p.batch_size] subseeds = p.all_subseeds[n * p.batch_size:(n + 1) * p.batch_size] -- cgit v1.2.3 From a609bd56b4206460d1df3c3022025fc78b66718f Mon Sep 17 00:00:00 2001 From: papuSpartan Date: Sat, 1 Apr 2023 22:18:35 -0500 Subject: Transition to using settings through UI instead of cmd line args. Added feature to only apply to hr-fix. Install package using requirements_versions.txt --- launch.py | 3 --- modules/processing.py | 35 +++++++++++++++++++++++++++++++++++ modules/sd_models.py | 7 ------- modules/shared.py | 44 ++++++++++++++++++++++++++++++++++++++++++++ requirements_versions.txt | 1 + 5 files changed, 80 insertions(+), 10 deletions(-) (limited to 'modules/processing.py') diff --git a/launch.py b/launch.py index 846c4c20..68e08114 100644 --- a/launch.py +++ b/launch.py @@ -280,9 +280,6 @@ def prepare_environment(): elif platform.system() == "Linux": run_pip(f"install {xformers_package}", "xformers") - if not is_installed("tomesd") and args.token_merging: - run_pip(f"install tomesd") - if not is_installed("pyngrok") and args.ngrok: run_pip("install pyngrok", "ngrok") diff --git a/modules/processing.py b/modules/processing.py index 6d9c6a8d..e115aadd 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -29,6 +29,7 @@ from ldm.models.diffusion.ddpm import LatentDepth2ImageDiffusion from einops import repeat, rearrange from blendmodes.blend import blendLayers, BlendType +import tomesd # some of those options should not be changed at all because they would break the model, so I removed them from options. opt_C = 4 @@ -500,9 +501,28 @@ def process_images(p: StableDiffusionProcessing) -> Processed: if k == 'sd_vae': sd_vae.reload_vae_weights() + if opts.token_merging: + + if p.hr_second_pass_steps < 1 and not opts.token_merging_hr_only: + tomesd.apply_patch( + p.sd_model, + ratio=opts.token_merging_ratio, + max_downsample=opts.token_merging_maximum_down_sampling, + sx=opts.token_merging_stride_x, + sy=opts.token_merging_stride_y, + use_rand=opts.token_merging_random, + merge_attn=opts.token_merging_merge_attention, + merge_crossattn=opts.token_merging_merge_cross_attention, + merge_mlp=opts.token_merging_merge_mlp + ) + res = process_images_inner(p) finally: + # undo model optimizations made by tomesd + if opts.token_merging: + tomesd.remove_patch(p.sd_model) + # restore opts to original state if p.override_settings_restore_afterwards: for k, v in stored_opts.items(): @@ -938,6 +958,21 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): x = None devices.torch_gc() + # apply token merging optimizations from tomesd for high-res pass + # check if hr_only so we don't redundantly apply patch + if opts.token_merging and opts.token_merging_hr_only: + tomesd.apply_patch( + self.sd_model, + ratio=opts.token_merging_ratio, + max_downsample=opts.token_merging_maximum_down_sampling, + sx=opts.token_merging_stride_x, + sy=opts.token_merging_stride_y, + use_rand=opts.token_merging_random, + merge_attn=opts.token_merging_merge_attention, + merge_crossattn=opts.token_merging_merge_cross_attention, + merge_mlp=opts.token_merging_merge_mlp + ) + samples = self.sampler.sample_img2img(self, samples, noise, conditioning, unconditional_conditioning, steps=self.hr_second_pass_steps or self.steps, image_conditioning=image_conditioning) return samples diff --git a/modules/sd_models.py b/modules/sd_models.py index 2c05ec17..87c49b83 100644 --- a/modules/sd_models.py +++ b/modules/sd_models.py @@ -431,13 +431,6 @@ def load_model(checkpoint_info=None, already_loaded_state_dict=None, time_taken_ with sd_disable_initialization.DisableInitialization(disable_clip=clip_is_included_into_sd): sd_model = instantiate_from_config(sd_config.model) - if shared.cmd_opts.token_merging: - import tomesd - ratio = shared.cmd_opts.token_merging_ratio - - tomesd.apply_patch(sd_model, ratio=ratio) - print(f"Model accelerated using {(ratio * 100)}% token merging via tomesd.") - timer.record("token merging") except Exception as e: pass diff --git a/modules/shared.py b/modules/shared.py index 5fd0eecb..d7379e24 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -427,6 +427,50 @@ options_templates.update(options_section((None, "Hidden options"), { "sd_checkpoint_hash": OptionInfo("", "SHA256 hash of the current checkpoint"), })) +options_templates.update(options_section(('token_merging', 'Token Merging'), { + "token_merging": OptionInfo( + False, "Enable redundant token merging via tomesd. (currently incompatible with controlnet extension)", + gr.Checkbox + ), + "token_merging_ratio": OptionInfo( + 0.5, "Merging Ratio", + gr.Slider, {"minimum": 0, "maximum": 0.9, "step": 0.1} + ), + "token_merging_hr_only": OptionInfo( + True, "Apply only to high-res fix pass. Disabling can yield a ~20-35% speedup on contemporary resolutions.", + gr.Checkbox + ), + # More advanced/niche settings: + "token_merging_random": OptionInfo( + True, "Use random perturbations - Disabling might help with certain samplers", + gr.Checkbox + ), + "token_merging_merge_attention": OptionInfo( + True, "Merge attention", + gr.Checkbox + ), + "token_merging_merge_cross_attention": OptionInfo( + False, "Merge cross attention", + gr.Checkbox + ), + "token_merging_merge_mlp": OptionInfo( + False, "Merge mlp", + gr.Checkbox + ), + "token_merging_maximum_down_sampling": OptionInfo( + 1, "Maximum down sampling", + gr.Dropdown, lambda: {"choices": ["1", "2", "4", "8"]} + ), + "token_merging_stride_x": OptionInfo( + 2, "Stride - X", + gr.Slider, {"minimum": 2, "maximum": 8, "step": 2} + ), + "token_merging_stride_y": OptionInfo( + 2, "Stride - Y", + gr.Slider, {"minimum": 2, "maximum": 8, "step": 2} + ) +})) + options_templates.update() diff --git a/requirements_versions.txt b/requirements_versions.txt index df65431a..045230ab 100644 --- a/requirements_versions.txt +++ b/requirements_versions.txt @@ -28,3 +28,4 @@ torchsde==0.2.5 safetensors==0.3.0 httpcore<=0.15 fastapi==0.94.0 +tomesd>=0.1 \ No newline at end of file -- cgit v1.2.3 From c707b7df95a61b66a05be94e805e1be9a432e294 Mon Sep 17 00:00:00 2001 From: papuSpartan Date: Sat, 1 Apr 2023 23:47:10 -0500 Subject: remove excess condition --- modules/processing.py | 29 +++++++++++++++-------------- 1 file changed, 15 insertions(+), 14 deletions(-) (limited to 'modules/processing.py') diff --git a/modules/processing.py b/modules/processing.py index e115aadd..55735572 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -501,26 +501,26 @@ def process_images(p: StableDiffusionProcessing) -> Processed: if k == 'sd_vae': sd_vae.reload_vae_weights() - if opts.token_merging: - - if p.hr_second_pass_steps < 1 and not opts.token_merging_hr_only: - tomesd.apply_patch( - p.sd_model, - ratio=opts.token_merging_ratio, - max_downsample=opts.token_merging_maximum_down_sampling, - sx=opts.token_merging_stride_x, - sy=opts.token_merging_stride_y, - use_rand=opts.token_merging_random, - merge_attn=opts.token_merging_merge_attention, - merge_crossattn=opts.token_merging_merge_cross_attention, - merge_mlp=opts.token_merging_merge_mlp - ) + if opts.token_merging and not opts.token_merging_hr_only: + print("applying token merging to all passes") + tomesd.apply_patch( + p.sd_model, + ratio=opts.token_merging_ratio, + max_downsample=opts.token_merging_maximum_down_sampling, + sx=opts.token_merging_stride_x, + sy=opts.token_merging_stride_y, + use_rand=opts.token_merging_random, + merge_attn=opts.token_merging_merge_attention, + merge_crossattn=opts.token_merging_merge_cross_attention, + merge_mlp=opts.token_merging_merge_mlp + ) res = process_images_inner(p) finally: # undo model optimizations made by tomesd if opts.token_merging: + print('removing token merging model optimizations') tomesd.remove_patch(p.sd_model) # restore opts to original state @@ -961,6 +961,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): # apply token merging optimizations from tomesd for high-res pass # check if hr_only so we don't redundantly apply patch if opts.token_merging and opts.token_merging_hr_only: + print("applying token merging for high-res pass") tomesd.apply_patch( self.sd_model, ratio=opts.token_merging_ratio, -- cgit v1.2.3 From 5c8e53d5e98da0eabf384318955c57842d612c07 Mon Sep 17 00:00:00 2001 From: papuSpartan Date: Tue, 4 Apr 2023 02:26:44 -0500 Subject: Allow different merge ratios to be used for each pass. Make toggle cmd flag work again. Remove ratio flag. Remove warning about controlnet being incompatible --- modules/cmd_args.py | 3 +-- modules/processing.py | 44 +++++++++++++++----------------------------- modules/sd_models.py | 29 ++++++++++++++++++++++++++++- modules/shared.py | 6 +++++- 4 files changed, 49 insertions(+), 33 deletions(-) (limited to 'modules/processing.py') diff --git a/modules/cmd_args.py b/modules/cmd_args.py index 4314f97b..8e5a7fab 100644 --- a/modules/cmd_args.py +++ b/modules/cmd_args.py @@ -103,5 +103,4 @@ parser.add_argument("--no-hashing", action='store_true', help="disable sha256 ha parser.add_argument("--no-download-sd-model", action='store_true', help="don't download SD1.5 model even if no model is found in --ckpt-dir", default=False) # token merging / tomesd -parser.add_argument("--token-merging", action='store_true', help="Provides generation speedup by merging redundant tokens. (compatible with --xformers)", default=False) -parser.add_argument("--token-merging-ratio", type=float, help="Adjusts ratio of merged to untouched tokens. Range: (0.0-1.0], Defaults to 0.5", default=0.5) +parser.add_argument("--token-merging", action='store_true', help="Provides speed and memory improvements by merging redundant tokens. This has a more pronounced effect on higher resolutions.", default=False) diff --git a/modules/processing.py b/modules/processing.py index 55735572..670a7a28 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -501,26 +501,16 @@ def process_images(p: StableDiffusionProcessing) -> Processed: if k == 'sd_vae': sd_vae.reload_vae_weights() - if opts.token_merging and not opts.token_merging_hr_only: - print("applying token merging to all passes") - tomesd.apply_patch( - p.sd_model, - ratio=opts.token_merging_ratio, - max_downsample=opts.token_merging_maximum_down_sampling, - sx=opts.token_merging_stride_x, - sy=opts.token_merging_stride_y, - use_rand=opts.token_merging_random, - merge_attn=opts.token_merging_merge_attention, - merge_crossattn=opts.token_merging_merge_cross_attention, - merge_mlp=opts.token_merging_merge_mlp - ) + if (opts.token_merging or cmd_opts.token_merging) and not opts.token_merging_hr_only: + print("\nApplying token merging\n") + sd_models.apply_token_merging(sd_model=p.sd_model, hr=False) res = process_images_inner(p) finally: # undo model optimizations made by tomesd - if opts.token_merging: - print('removing token merging model optimizations') + if opts.token_merging or cmd_opts.token_merging: + print('\nRemoving token merging model optimizations\n') tomesd.remove_patch(p.sd_model) # restore opts to original state @@ -959,20 +949,16 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): devices.torch_gc() # apply token merging optimizations from tomesd for high-res pass - # check if hr_only so we don't redundantly apply patch - if opts.token_merging and opts.token_merging_hr_only: - print("applying token merging for high-res pass") - tomesd.apply_patch( - self.sd_model, - ratio=opts.token_merging_ratio, - max_downsample=opts.token_merging_maximum_down_sampling, - sx=opts.token_merging_stride_x, - sy=opts.token_merging_stride_y, - use_rand=opts.token_merging_random, - merge_attn=opts.token_merging_merge_attention, - merge_crossattn=opts.token_merging_merge_cross_attention, - merge_mlp=opts.token_merging_merge_mlp - ) + # check if hr_only so we are not redundantly patching + if (cmd_opts.token_merging or opts.token_merging) and (opts.token_merging_hr_only or opts.token_merging_ratio_hr != opts.token_merging_ratio): + # case where user wants to use separate merge ratios + if not opts.token_merging_hr_only: + # clean patch done by first pass. (clobbering the first patch might be fine? this might be excessive) + print('Temporarily reverting token merging optimizations in preparation for next pass') + tomesd.remove_patch(self.sd_model) + + print("\nApplying token merging for high-res pass\n") + sd_models.apply_token_merging(sd_model=self.sd_model, hr=True) samples = self.sampler.sample_img2img(self, samples, noise, conditioning, unconditional_conditioning, steps=self.hr_second_pass_steps or self.steps, image_conditioning=image_conditioning) diff --git a/modules/sd_models.py b/modules/sd_models.py index 87c49b83..696a2333 100644 --- a/modules/sd_models.py +++ b/modules/sd_models.py @@ -16,6 +16,7 @@ from modules import paths, shared, modelloader, devices, script_callbacks, sd_va from modules.paths import models_path from modules.sd_hijack_inpainting import do_inpainting_hijack from modules.timer import Timer +import tomesd model_dir = "Stable-diffusion" model_path = os.path.abspath(os.path.join(paths.models_path, model_dir)) @@ -545,4 +546,30 @@ def unload_model_weights(sd_model=None, info=None): print(f"Unloaded weights {timer.summary()}.") - return sd_model \ No newline at end of file + return sd_model + + +def apply_token_merging(sd_model, hr: bool): + """ + Applies speed and memory optimizations from tomesd. + + Args: + hr (bool): True if called in the context of a high-res pass + """ + + ratio = shared.opts.token_merging_ratio + if hr: + ratio = shared.opts.token_merging_ratio_hr + print("effective hr pass merge ratio is "+str(ratio)) + + tomesd.apply_patch( + sd_model, + ratio=ratio, + max_downsample=shared.opts.token_merging_maximum_down_sampling, + sx=shared.opts.token_merging_stride_x, + sy=shared.opts.token_merging_stride_y, + use_rand=shared.opts.token_merging_random, + merge_attn=shared.opts.token_merging_merge_attention, + merge_crossattn=shared.opts.token_merging_merge_cross_attention, + merge_mlp=shared.opts.token_merging_merge_mlp + ) diff --git a/modules/shared.py b/modules/shared.py index d7379e24..c7572e98 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -429,7 +429,7 @@ options_templates.update(options_section((None, "Hidden options"), { options_templates.update(options_section(('token_merging', 'Token Merging'), { "token_merging": OptionInfo( - False, "Enable redundant token merging via tomesd. (currently incompatible with controlnet extension)", + 0.5, "Enable redundant token merging via tomesd. This can provide significant speed and memory improvements.", gr.Checkbox ), "token_merging_ratio": OptionInfo( @@ -440,6 +440,10 @@ options_templates.update(options_section(('token_merging', 'Token Merging'), { True, "Apply only to high-res fix pass. Disabling can yield a ~20-35% speedup on contemporary resolutions.", gr.Checkbox ), + "token_merging_ratio_hr": OptionInfo( + 0.5, "Merging Ratio (high-res pass) - If 'Apply only to high-res' is enabled, this will always be the ratio used.", + gr.Slider, {"minimum": 0, "maximum": 0.9, "step": 0.1} + ), # More advanced/niche settings: "token_merging_random": OptionInfo( True, "Use random perturbations - Disabling might help with certain samplers", -- cgit v1.2.3 From 1c1106260300ca3956d9619875e28278b148adab Mon Sep 17 00:00:00 2001 From: papuSpartan Date: Mon, 10 Apr 2023 03:37:15 -0500 Subject: add token merging options to infotext when necessary. Bump tomesd version --- modules/generation_parameters_copypaste.py | 37 ++++++++++++++++++++++++++++++ modules/processing.py | 22 ++++++++++++++---- modules/shared.py | 2 +- requirements_versions.txt | 2 +- 4 files changed, 57 insertions(+), 6 deletions(-) (limited to 'modules/processing.py') diff --git a/modules/generation_parameters_copypaste.py b/modules/generation_parameters_copypaste.py index 6df76858..a7ede534 100644 --- a/modules/generation_parameters_copypaste.py +++ b/modules/generation_parameters_copypaste.py @@ -282,6 +282,32 @@ Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 965400086, Size: 512x512, Model res["Hires resize-1"] = 0 res["Hires resize-2"] = 0 + # Infer additional override settings for token merging + print("inferring settings for tomesd") + token_merging_ratio = res.get("Token merging ratio", None) + token_merging_ratio_hr = res.get("Token merging ratio hr", None) + + if token_merging_ratio is not None or token_merging_ratio_hr is not None: + res["Token merging"] = 'True' + + if token_merging_ratio is None: + res["Token merging hr only"] = 'True' + else: + res["Token merging hr only"] = 'False' + + if res.get("Token merging random", None) is None: + res["Token merging random"] = 'False' + if res.get("Token merging merge attention", None) is None: + res["Token merging merge attention"] = 'True' + if res.get("Token merging merge cross attention", None) is None: + res["Token merging merge cross attention"] = 'False' + if res.get("Token merging merge mlp", None) is None: + res["Token merging merge mlp"] = 'False' + if res.get("Token merging stride x", None) is None: + res["Token merging stride x"] = '2' + if res.get("Token merging stride y", None) is None: + res["Token merging stride y"] = '2' + restore_old_hires_fix_params(res) return res @@ -304,6 +330,17 @@ infotext_to_setting_name_mapping = [ ('UniPC skip type', 'uni_pc_skip_type'), ('UniPC order', 'uni_pc_order'), ('UniPC lower order final', 'uni_pc_lower_order_final'), + ('Token merging', 'token_merging'), + ('Token merging ratio', 'token_merging_ratio'), + ('Token merging hr only', 'token_merging_hr_only'), + ('Token merging ratio hr', 'token_merging_ratio_hr'), + ('Token merging random', 'token_merging_random'), + ('Token merging merge attention', 'token_merging_merge_attention'), + ('Token merging merge cross attention', 'token_merging_merge_cross_attention'), + ('Token merging merge mlp', 'token_merging_merge_mlp'), + ('Token merging maximum downsampling', 'token_merging_maximum_downsampling'), + ('Token merging stride x', 'token_merging_stride_x'), + ('Token merging stride y', 'token_merging_stride_y') ] diff --git a/modules/processing.py b/modules/processing.py index 670a7a28..95058d0b 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -31,6 +31,12 @@ from einops import repeat, rearrange from blendmodes.blend import blendLayers, BlendType import tomesd +# add a logger for the processing module +logger = logging.getLogger(__name__) +# manually set output level here since there is no option to do so yet through launch options +# logging.basicConfig(level=logging.DEBUG, format='%(asctime)s %(levelname)s %(name)s %(message)s') + + # some of those options should not be changed at all because they would break the model, so I removed them from options. opt_C = 4 opt_f = 8 @@ -477,6 +483,14 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments=None, iter "Conditional mask weight": getattr(p, "inpainting_mask_weight", shared.opts.inpainting_mask_weight) if p.is_using_inpainting_conditioning else None, "Clip skip": None if clip_skip <= 1 else clip_skip, "ENSD": None if opts.eta_noise_seed_delta == 0 else opts.eta_noise_seed_delta, + "Token merging ratio": None if not (opts.token_merging or cmd_opts.token_merging) or opts.token_merging_hr_only else opts.token_merging_ratio, + "Token merging ratio hr": None if not (opts.token_merging or cmd_opts.token_merging) else opts.token_merging_ratio_hr, + "Token merging random": None if opts.token_merging_random is False else opts.token_merging_random, + "Token merging merge attention": None if opts.token_merging_merge_attention is True else opts.token_merging_merge_attention, + "Token merging merge cross attention": None if opts.token_merging_merge_cross_attention is False else opts.token_merging_merge_cross_attention, + "Token merging merge mlp": None if opts.token_merging_merge_mlp is False else opts.token_merging_merge_mlp, + "Token merging stride x": None if opts.token_merging_stride_x == 2 else opts.token_merging_stride_x, + "Token merging stride y": None if opts.token_merging_stride_y == 2 else opts.token_merging_stride_y } generation_params.update(p.extra_generation_params) @@ -502,16 +516,16 @@ def process_images(p: StableDiffusionProcessing) -> Processed: sd_vae.reload_vae_weights() if (opts.token_merging or cmd_opts.token_merging) and not opts.token_merging_hr_only: - print("\nApplying token merging\n") sd_models.apply_token_merging(sd_model=p.sd_model, hr=False) + logger.debug('Token merging applied') res = process_images_inner(p) finally: # undo model optimizations made by tomesd if opts.token_merging or cmd_opts.token_merging: - print('\nRemoving token merging model optimizations\n') tomesd.remove_patch(p.sd_model) + logger.debug('Token merging model optimizations removed') # restore opts to original state if p.override_settings_restore_afterwards: @@ -954,11 +968,11 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): # case where user wants to use separate merge ratios if not opts.token_merging_hr_only: # clean patch done by first pass. (clobbering the first patch might be fine? this might be excessive) - print('Temporarily reverting token merging optimizations in preparation for next pass') tomesd.remove_patch(self.sd_model) + logger.debug('Temporarily removed token merging optimizations in preparation for next pass') - print("\nApplying token merging for high-res pass\n") sd_models.apply_token_merging(sd_model=self.sd_model, hr=True) + logger.debug('Applied token merging for high-res pass') samples = self.sampler.sample_img2img(self, samples, noise, conditioning, unconditional_conditioning, steps=self.hr_second_pass_steps or self.steps, image_conditioning=image_conditioning) diff --git a/modules/shared.py b/modules/shared.py index 568acdc4..d9db7317 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -446,7 +446,7 @@ options_templates.update(options_section(('token_merging', 'Token Merging'), { ), # More advanced/niche settings: "token_merging_random": OptionInfo( - True, "Use random perturbations - Disabling might help with certain samplers", + False, "Use random perturbations - Can improve outputs for certain samplers. For others, it may cause visaul artifacting.", gr.Checkbox ), "token_merging_merge_attention": OptionInfo( diff --git a/requirements_versions.txt b/requirements_versions.txt index 03522715..f972f975 100644 --- a/requirements_versions.txt +++ b/requirements_versions.txt @@ -28,4 +28,4 @@ torchsde==0.2.5 safetensors==0.3.0 httpcore<=0.15 fastapi==0.94.0 -tomesd>=0.1.1 \ No newline at end of file +tomesd>=0.1.2 \ No newline at end of file -- cgit v1.2.3 From e960781511eb175943be09b314ac2be46b6fc684 Mon Sep 17 00:00:00 2001 From: papuSpartan <30642826+papuSpartan@users.noreply.github.com> Date: Wed, 3 May 2023 13:12:43 -0500 Subject: fix maximum downsampling option --- modules/generation_parameters_copypaste.py | 4 +++- modules/processing.py | 1 + modules/shared.py | 5 +---- 3 files changed, 5 insertions(+), 5 deletions(-) (limited to 'modules/processing.py') diff --git a/modules/generation_parameters_copypaste.py b/modules/generation_parameters_copypaste.py index 34c1b860..83382e93 100644 --- a/modules/generation_parameters_copypaste.py +++ b/modules/generation_parameters_copypaste.py @@ -306,6 +306,8 @@ Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 965400086, Size: 512x512, Model res["Token merging stride x"] = '2' if res.get("Token merging stride y", None) is None: res["Token merging stride y"] = '2' + if res.get("Token merging maximum down sampling", None) is None: + res["Token merging maximum down sampling"] = '1' restore_old_hires_fix_params(res) @@ -341,7 +343,7 @@ infotext_to_setting_name_mapping = [ ('Token merging merge attention', 'token_merging_merge_attention'), ('Token merging merge cross attention', 'token_merging_merge_cross_attention'), ('Token merging merge mlp', 'token_merging_merge_mlp'), - ('Token merging maximum downsampling', 'token_merging_maximum_downsampling'), + ('Token merging maximum down sampling', 'token_merging_maximum_down_sampling'), ('Token merging stride x', 'token_merging_stride_x'), ('Token merging stride y', 'token_merging_stride_y'), ('RNG', 'randn_source'), diff --git a/modules/processing.py b/modules/processing.py index d5d1da5a..6807a301 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -495,6 +495,7 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments=None, iter "Token merging merge mlp": None if opts.token_merging_merge_mlp is False else opts.token_merging_merge_mlp, "Token merging stride x": None if opts.token_merging_stride_x == 2 else opts.token_merging_stride_x, "Token merging stride y": None if opts.token_merging_stride_y == 2 else opts.token_merging_stride_y, + "Token merging maximum down sampling": None if opts.token_merging_maximum_down_sampling == 1 else opts.token_merging_maximum_down_sampling, "Init image hash": getattr(p, 'init_img_hash', None), "RNG": opts.randn_source if opts.randn_source != "GPU" else None, "NGMS": None if p.s_min_uncond == 0 else p.s_min_uncond, diff --git a/modules/shared.py b/modules/shared.py index 7b81ffc9..a7a72dd5 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -488,10 +488,7 @@ options_templates.update(options_section(('token_merging', 'Token Merging'), { False, "Merge mlp", gr.Checkbox ), - "token_merging_maximum_down_sampling": OptionInfo( - 1, "Maximum down sampling", - gr.Dropdown, lambda: {"choices": ["1", "2", "4", "8"]} - ), + "token_merging_maximum_down_sampling": OptionInfo(1, "Maximum down sampling", gr.Radio, lambda: {"choices": ['1', '2', '4', '8']}), "token_merging_stride_x": OptionInfo( 2, "Stride - X", gr.Slider, {"minimum": 2, "maximum": 8, "step": 2} -- cgit v1.2.3 From 96d6ca4199e7c5eee8d451618de5161cea317c40 Mon Sep 17 00:00:00 2001 From: AUTOMATIC <16777216c@gmail.com> Date: Wed, 10 May 2023 08:25:25 +0300 Subject: manual fixes for ruff --- extensions-builtin/LDSR/ldsr_model_arch.py | 2 +- extensions-builtin/LDSR/scripts/ldsr_model.py | 3 +- extensions-builtin/LDSR/sd_hijack_autoencoder.py | 10 +- extensions-builtin/LDSR/sd_hijack_ddpm_v1.py | 26 ++--- extensions-builtin/ScuNET/scunet_model_arch.py | 9 +- extensions-builtin/SwinIR/scripts/swinir_model.py | 2 +- modules/api/api.py | 129 +++++++++++----------- modules/api/models.py | 5 +- modules/codeformer/codeformer_arch.py | 2 +- modules/esrgan_model_arch.py | 2 + modules/extra_networks_hypernet.py | 2 +- modules/images.py | 4 +- modules/img2img.py | 1 - modules/interrogate.py | 1 - modules/modelloader.py | 6 +- modules/models/diffusion/ddpm_edit.py | 26 ++--- modules/models/diffusion/uni_pc/sampler.py | 3 +- modules/processing.py | 2 +- modules/prompt_parser.py | 11 +- modules/textual_inversion/autocrop.py | 2 +- modules/ui.py | 8 +- modules/upscaler.py | 2 +- 22 files changed, 129 insertions(+), 129 deletions(-) (limited to 'modules/processing.py') diff --git a/extensions-builtin/LDSR/ldsr_model_arch.py b/extensions-builtin/LDSR/ldsr_model_arch.py index 2339de7f..a5fb8907 100644 --- a/extensions-builtin/LDSR/ldsr_model_arch.py +++ b/extensions-builtin/LDSR/ldsr_model_arch.py @@ -243,7 +243,7 @@ def make_convolutional_sample(batch, model, custom_steps=None, eta=1.0, quantize x_sample_noquant = model.decode_first_stage(sample, force_not_quantize=True) log["sample_noquant"] = x_sample_noquant log["sample_diff"] = torch.abs(x_sample_noquant - x_sample) - except: + except Exception: pass log["sample"] = x_sample diff --git a/extensions-builtin/LDSR/scripts/ldsr_model.py b/extensions-builtin/LDSR/scripts/ldsr_model.py index da19cff1..e8dc083c 100644 --- a/extensions-builtin/LDSR/scripts/ldsr_model.py +++ b/extensions-builtin/LDSR/scripts/ldsr_model.py @@ -7,7 +7,8 @@ from basicsr.utils.download_util import load_file_from_url from modules.upscaler import Upscaler, UpscalerData from ldsr_model_arch import LDSR from modules import shared, script_callbacks -import sd_hijack_autoencoder, sd_hijack_ddpm_v1 +import sd_hijack_autoencoder +import sd_hijack_ddpm_v1 class UpscalerLDSR(Upscaler): diff --git a/extensions-builtin/LDSR/sd_hijack_autoencoder.py b/extensions-builtin/LDSR/sd_hijack_autoencoder.py index db2231dd..6303fed5 100644 --- a/extensions-builtin/LDSR/sd_hijack_autoencoder.py +++ b/extensions-builtin/LDSR/sd_hijack_autoencoder.py @@ -1,16 +1,21 @@ # The content of this file comes from the ldm/models/autoencoder.py file of the compvis/stable-diffusion repo # The VQModel & VQModelInterface were subsequently removed from ldm/models/autoencoder.py when we moved to the stability-ai/stablediffusion repo # As the LDSR upscaler relies on VQModel & VQModelInterface, the hijack aims to put them back into the ldm.models.autoencoder - +import numpy as np import torch import pytorch_lightning as pl import torch.nn.functional as F from contextlib import contextmanager + +from torch.optim.lr_scheduler import LambdaLR + +from ldm.modules.ema import LitEma from taming.modules.vqvae.quantize import VectorQuantizer2 as VectorQuantizer from ldm.modules.diffusionmodules.model import Encoder, Decoder from ldm.util import instantiate_from_config import ldm.models.autoencoder +from packaging import version class VQModel(pl.LightningModule): def __init__(self, @@ -249,7 +254,8 @@ class VQModel(pl.LightningModule): if plot_ema: with self.ema_scope(): xrec_ema, _ = self(x) - if x.shape[1] > 3: xrec_ema = self.to_rgb(xrec_ema) + if x.shape[1] > 3: + xrec_ema = self.to_rgb(xrec_ema) log["reconstructions_ema"] = xrec_ema return log diff --git a/extensions-builtin/LDSR/sd_hijack_ddpm_v1.py b/extensions-builtin/LDSR/sd_hijack_ddpm_v1.py index 5c0488e5..4d3f6c56 100644 --- a/extensions-builtin/LDSR/sd_hijack_ddpm_v1.py +++ b/extensions-builtin/LDSR/sd_hijack_ddpm_v1.py @@ -450,7 +450,7 @@ class LatentDiffusionV1(DDPMV1): self.cond_stage_key = cond_stage_key try: self.num_downs = len(first_stage_config.params.ddconfig.ch_mult) - 1 - except: + except Exception: self.num_downs = 0 if not scale_by_std: self.scale_factor = scale_factor @@ -877,16 +877,6 @@ class LatentDiffusionV1(DDPMV1): c = self.q_sample(x_start=c, t=tc, noise=torch.randn_like(c.float())) return self.p_losses(x, c, t, *args, **kwargs) - def _rescale_annotations(self, bboxes, crop_coordinates): # TODO: move to dataset - def rescale_bbox(bbox): - x0 = clamp((bbox[0] - crop_coordinates[0]) / crop_coordinates[2]) - y0 = clamp((bbox[1] - crop_coordinates[1]) / crop_coordinates[3]) - w = min(bbox[2] / crop_coordinates[2], 1 - x0) - h = min(bbox[3] / crop_coordinates[3], 1 - y0) - return x0, y0, w, h - - return [rescale_bbox(b) for b in bboxes] - def apply_model(self, x_noisy, t, cond, return_ids=False): if isinstance(cond, dict): @@ -1157,8 +1147,10 @@ class LatentDiffusionV1(DDPMV1): if i % log_every_t == 0 or i == timesteps - 1: intermediates.append(x0_partial) - if callback: callback(i) - if img_callback: img_callback(img, i) + if callback: + callback(i) + if img_callback: + img_callback(img, i) return img, intermediates @torch.no_grad() @@ -1205,8 +1197,10 @@ class LatentDiffusionV1(DDPMV1): if i % log_every_t == 0 or i == timesteps - 1: intermediates.append(img) - if callback: callback(i) - if img_callback: img_callback(img, i) + if callback: + callback(i) + if img_callback: + img_callback(img, i) if return_intermediates: return img, intermediates @@ -1322,7 +1316,7 @@ class LatentDiffusionV1(DDPMV1): if inpaint: # make a simple center square - b, h, w = z.shape[0], z.shape[2], z.shape[3] + h, w = z.shape[2], z.shape[3] mask = torch.ones(N, h, w).to(self.device) # zeros will be filled in mask[:, h // 4:3 * h // 4, w // 4:3 * w // 4] = 0. diff --git a/extensions-builtin/ScuNET/scunet_model_arch.py b/extensions-builtin/ScuNET/scunet_model_arch.py index 43ca8d36..8028918a 100644 --- a/extensions-builtin/ScuNET/scunet_model_arch.py +++ b/extensions-builtin/ScuNET/scunet_model_arch.py @@ -61,7 +61,9 @@ class WMSA(nn.Module): Returns: output: tensor shape [b h w c] """ - if self.type != 'W': x = torch.roll(x, shifts=(-(self.window_size // 2), -(self.window_size // 2)), dims=(1, 2)) + if self.type != 'W': + x = torch.roll(x, shifts=(-(self.window_size // 2), -(self.window_size // 2)), dims=(1, 2)) + x = rearrange(x, 'b (w1 p1) (w2 p2) c -> b w1 w2 p1 p2 c', p1=self.window_size, p2=self.window_size) h_windows = x.size(1) w_windows = x.size(2) @@ -85,8 +87,9 @@ class WMSA(nn.Module): output = self.linear(output) output = rearrange(output, 'b (w1 w2) (p1 p2) c -> b (w1 p1) (w2 p2) c', w1=h_windows, p1=self.window_size) - if self.type != 'W': output = torch.roll(output, shifts=(self.window_size // 2, self.window_size // 2), - dims=(1, 2)) + if self.type != 'W': + output = torch.roll(output, shifts=(self.window_size // 2, self.window_size // 2), dims=(1, 2)) + return output def relative_embedding(self): diff --git a/extensions-builtin/SwinIR/scripts/swinir_model.py b/extensions-builtin/SwinIR/scripts/swinir_model.py index e8783bca..d77c3a92 100644 --- a/extensions-builtin/SwinIR/scripts/swinir_model.py +++ b/extensions-builtin/SwinIR/scripts/swinir_model.py @@ -45,7 +45,7 @@ class UpscalerSwinIR(Upscaler): img = upscale(img, model) try: torch.cuda.empty_cache() - except: + except Exception: pass return img diff --git a/modules/api/api.py b/modules/api/api.py index d47c39fc..f52d371b 100644 --- a/modules/api/api.py +++ b/modules/api/api.py @@ -15,7 +15,8 @@ from secrets import compare_digest import modules.shared as shared from modules import sd_samplers, deepbooru, sd_hijack, images, scripts, ui, postprocessing -from modules.api.models import * +from modules.api import models +from modules.shared import opts from modules.processing import StableDiffusionProcessingTxt2Img, StableDiffusionProcessingImg2Img, process_images from modules.textual_inversion.textual_inversion import create_embedding, train_embedding from modules.textual_inversion.preprocess import preprocess @@ -25,20 +26,21 @@ from modules.sd_models import checkpoints_list, unload_model_weights, reload_mod from modules.sd_models_config import find_checkpoint_config_near_filename from modules.realesrgan_model import get_realesrgan_models from modules import devices -from typing import List +from typing import Dict, List, Any import piexif import piexif.helper + def upscaler_to_index(name: str): try: return [x.name.lower() for x in shared.sd_upscalers].index(name.lower()) - except: - raise HTTPException(status_code=400, detail=f"Invalid upscaler, needs to be one of these: {' , '.join([x.name for x in sd_upscalers])}") + except Exception: + raise HTTPException(status_code=400, detail=f"Invalid upscaler, needs to be one of these: {' , '.join([x.name for x in shared.sd_upscalers])}") def script_name_to_index(name, scripts): try: return [script.title().lower() for script in scripts].index(name.lower()) - except: + except Exception: raise HTTPException(status_code=422, detail=f"Script '{name}' not found") def validate_sampler_name(name): @@ -99,7 +101,7 @@ def api_middleware(app: FastAPI): import starlette # importing just so it can be placed on silent list from rich.console import Console console = Console() - except: + except Exception: import traceback rich_available = False @@ -166,36 +168,36 @@ class Api: self.app = app self.queue_lock = queue_lock api_middleware(self.app) - self.add_api_route("/sdapi/v1/txt2img", self.text2imgapi, methods=["POST"], response_model=TextToImageResponse) - self.add_api_route("/sdapi/v1/img2img", self.img2imgapi, methods=["POST"], response_model=ImageToImageResponse) - self.add_api_route("/sdapi/v1/extra-single-image", self.extras_single_image_api, methods=["POST"], response_model=ExtrasSingleImageResponse) - self.add_api_route("/sdapi/v1/extra-batch-images", self.extras_batch_images_api, methods=["POST"], response_model=ExtrasBatchImagesResponse) - self.add_api_route("/sdapi/v1/png-info", self.pnginfoapi, methods=["POST"], response_model=PNGInfoResponse) - self.add_api_route("/sdapi/v1/progress", self.progressapi, methods=["GET"], response_model=ProgressResponse) + self.add_api_route("/sdapi/v1/txt2img", self.text2imgapi, methods=["POST"], response_model=models.TextToImageResponse) + self.add_api_route("/sdapi/v1/img2img", self.img2imgapi, methods=["POST"], response_model=models.ImageToImageResponse) + self.add_api_route("/sdapi/v1/extra-single-image", self.extras_single_image_api, methods=["POST"], response_model=models.ExtrasSingleImageResponse) + self.add_api_route("/sdapi/v1/extra-batch-images", self.extras_batch_images_api, methods=["POST"], response_model=models.ExtrasBatchImagesResponse) + self.add_api_route("/sdapi/v1/png-info", self.pnginfoapi, methods=["POST"], response_model=models.PNGInfoResponse) + self.add_api_route("/sdapi/v1/progress", self.progressapi, methods=["GET"], response_model=models.ProgressResponse) self.add_api_route("/sdapi/v1/interrogate", self.interrogateapi, methods=["POST"]) self.add_api_route("/sdapi/v1/interrupt", self.interruptapi, methods=["POST"]) self.add_api_route("/sdapi/v1/skip", self.skip, methods=["POST"]) - self.add_api_route("/sdapi/v1/options", self.get_config, methods=["GET"], response_model=OptionsModel) + self.add_api_route("/sdapi/v1/options", self.get_config, methods=["GET"], response_model=models.OptionsModel) self.add_api_route("/sdapi/v1/options", self.set_config, methods=["POST"]) - self.add_api_route("/sdapi/v1/cmd-flags", self.get_cmd_flags, methods=["GET"], response_model=FlagsModel) - self.add_api_route("/sdapi/v1/samplers", self.get_samplers, methods=["GET"], response_model=List[SamplerItem]) - self.add_api_route("/sdapi/v1/upscalers", self.get_upscalers, methods=["GET"], response_model=List[UpscalerItem]) - self.add_api_route("/sdapi/v1/sd-models", self.get_sd_models, methods=["GET"], response_model=List[SDModelItem]) - self.add_api_route("/sdapi/v1/hypernetworks", self.get_hypernetworks, methods=["GET"], response_model=List[HypernetworkItem]) - self.add_api_route("/sdapi/v1/face-restorers", self.get_face_restorers, methods=["GET"], response_model=List[FaceRestorerItem]) - self.add_api_route("/sdapi/v1/realesrgan-models", self.get_realesrgan_models, methods=["GET"], response_model=List[RealesrganItem]) - self.add_api_route("/sdapi/v1/prompt-styles", self.get_prompt_styles, methods=["GET"], response_model=List[PromptStyleItem]) - self.add_api_route("/sdapi/v1/embeddings", self.get_embeddings, methods=["GET"], response_model=EmbeddingsResponse) + self.add_api_route("/sdapi/v1/cmd-flags", self.get_cmd_flags, methods=["GET"], response_model=models.FlagsModel) + self.add_api_route("/sdapi/v1/samplers", self.get_samplers, methods=["GET"], response_model=List[models.SamplerItem]) + self.add_api_route("/sdapi/v1/upscalers", self.get_upscalers, methods=["GET"], response_model=List[models.UpscalerItem]) + self.add_api_route("/sdapi/v1/sd-models", self.get_sd_models, methods=["GET"], response_model=List[models.SDModelItem]) + self.add_api_route("/sdapi/v1/hypernetworks", self.get_hypernetworks, methods=["GET"], response_model=List[models.HypernetworkItem]) + self.add_api_route("/sdapi/v1/face-restorers", self.get_face_restorers, methods=["GET"], response_model=List[models.FaceRestorerItem]) + self.add_api_route("/sdapi/v1/realesrgan-models", self.get_realesrgan_models, methods=["GET"], response_model=List[models.RealesrganItem]) + self.add_api_route("/sdapi/v1/prompt-styles", self.get_prompt_styles, methods=["GET"], response_model=List[models.PromptStyleItem]) + self.add_api_route("/sdapi/v1/embeddings", self.get_embeddings, methods=["GET"], response_model=models.EmbeddingsResponse) self.add_api_route("/sdapi/v1/refresh-checkpoints", self.refresh_checkpoints, methods=["POST"]) - self.add_api_route("/sdapi/v1/create/embedding", self.create_embedding, methods=["POST"], response_model=CreateResponse) - self.add_api_route("/sdapi/v1/create/hypernetwork", self.create_hypernetwork, methods=["POST"], response_model=CreateResponse) - self.add_api_route("/sdapi/v1/preprocess", self.preprocess, methods=["POST"], response_model=PreprocessResponse) - self.add_api_route("/sdapi/v1/train/embedding", self.train_embedding, methods=["POST"], response_model=TrainResponse) - self.add_api_route("/sdapi/v1/train/hypernetwork", self.train_hypernetwork, methods=["POST"], response_model=TrainResponse) - self.add_api_route("/sdapi/v1/memory", self.get_memory, methods=["GET"], response_model=MemoryResponse) + self.add_api_route("/sdapi/v1/create/embedding", self.create_embedding, methods=["POST"], response_model=models.CreateResponse) + self.add_api_route("/sdapi/v1/create/hypernetwork", self.create_hypernetwork, methods=["POST"], response_model=models.CreateResponse) + self.add_api_route("/sdapi/v1/preprocess", self.preprocess, methods=["POST"], response_model=models.PreprocessResponse) + self.add_api_route("/sdapi/v1/train/embedding", self.train_embedding, methods=["POST"], response_model=models.TrainResponse) + self.add_api_route("/sdapi/v1/train/hypernetwork", self.train_hypernetwork, methods=["POST"], response_model=models.TrainResponse) + self.add_api_route("/sdapi/v1/memory", self.get_memory, methods=["GET"], response_model=models.MemoryResponse) self.add_api_route("/sdapi/v1/unload-checkpoint", self.unloadapi, methods=["POST"]) self.add_api_route("/sdapi/v1/reload-checkpoint", self.reloadapi, methods=["POST"]) - self.add_api_route("/sdapi/v1/scripts", self.get_scripts_list, methods=["GET"], response_model=ScriptsList) + self.add_api_route("/sdapi/v1/scripts", self.get_scripts_list, methods=["GET"], response_model=models.ScriptsList) self.default_script_arg_txt2img = [] self.default_script_arg_img2img = [] @@ -224,7 +226,7 @@ class Api: t2ilist = [str(title.lower()) for title in scripts.scripts_txt2img.titles] i2ilist = [str(title.lower()) for title in scripts.scripts_img2img.titles] - return ScriptsList(txt2img = t2ilist, img2img = i2ilist) + return models.ScriptsList(txt2img=t2ilist, img2img=i2ilist) def get_script(self, script_name, script_runner): if script_name is None or script_name == "": @@ -276,7 +278,7 @@ class Api: script_args[alwayson_script.args_from + idx] = request.alwayson_scripts[alwayson_script_name]["args"][idx] return script_args - def text2imgapi(self, txt2imgreq: StableDiffusionTxt2ImgProcessingAPI): + def text2imgapi(self, txt2imgreq: models.StableDiffusionTxt2ImgProcessingAPI): script_runner = scripts.scripts_txt2img if not script_runner.scripts: script_runner.initialize_scripts(False) @@ -320,9 +322,9 @@ class Api: b64images = list(map(encode_pil_to_base64, processed.images)) if send_images else [] - return TextToImageResponse(images=b64images, parameters=vars(txt2imgreq), info=processed.js()) + return models.TextToImageResponse(images=b64images, parameters=vars(txt2imgreq), info=processed.js()) - def img2imgapi(self, img2imgreq: StableDiffusionImg2ImgProcessingAPI): + def img2imgapi(self, img2imgreq: models.StableDiffusionImg2ImgProcessingAPI): init_images = img2imgreq.init_images if init_images is None: raise HTTPException(status_code=404, detail="Init image not found") @@ -381,9 +383,9 @@ class Api: img2imgreq.init_images = None img2imgreq.mask = None - return ImageToImageResponse(images=b64images, parameters=vars(img2imgreq), info=processed.js()) + return models.ImageToImageResponse(images=b64images, parameters=vars(img2imgreq), info=processed.js()) - def extras_single_image_api(self, req: ExtrasSingleImageRequest): + def extras_single_image_api(self, req: models.ExtrasSingleImageRequest): reqDict = setUpscalers(req) reqDict['image'] = decode_base64_to_image(reqDict['image']) @@ -391,9 +393,9 @@ class Api: with self.queue_lock: result = postprocessing.run_extras(extras_mode=0, image_folder="", input_dir="", output_dir="", save_output=False, **reqDict) - return ExtrasSingleImageResponse(image=encode_pil_to_base64(result[0][0]), html_info=result[1]) + return models.ExtrasSingleImageResponse(image=encode_pil_to_base64(result[0][0]), html_info=result[1]) - def extras_batch_images_api(self, req: ExtrasBatchImagesRequest): + def extras_batch_images_api(self, req: models.ExtrasBatchImagesRequest): reqDict = setUpscalers(req) image_list = reqDict.pop('imageList', []) @@ -402,15 +404,15 @@ class Api: with self.queue_lock: result = postprocessing.run_extras(extras_mode=1, image_folder=image_folder, image="", input_dir="", output_dir="", save_output=False, **reqDict) - return ExtrasBatchImagesResponse(images=list(map(encode_pil_to_base64, result[0])), html_info=result[1]) + return models.ExtrasBatchImagesResponse(images=list(map(encode_pil_to_base64, result[0])), html_info=result[1]) - def pnginfoapi(self, req: PNGInfoRequest): + def pnginfoapi(self, req: models.PNGInfoRequest): if(not req.image.strip()): - return PNGInfoResponse(info="") + return models.PNGInfoResponse(info="") image = decode_base64_to_image(req.image.strip()) if image is None: - return PNGInfoResponse(info="") + return models.PNGInfoResponse(info="") geninfo, items = images.read_info_from_image(image) if geninfo is None: @@ -418,13 +420,13 @@ class Api: items = {**{'parameters': geninfo}, **items} - return PNGInfoResponse(info=geninfo, items=items) + return models.PNGInfoResponse(info=geninfo, items=items) - def progressapi(self, req: ProgressRequest = Depends()): + def progressapi(self, req: models.ProgressRequest = Depends()): # copy from check_progress_call of ui.py if shared.state.job_count == 0: - return ProgressResponse(progress=0, eta_relative=0, state=shared.state.dict(), textinfo=shared.state.textinfo) + return models.ProgressResponse(progress=0, eta_relative=0, state=shared.state.dict(), textinfo=shared.state.textinfo) # avoid dividing zero progress = 0.01 @@ -446,9 +448,9 @@ class Api: if shared.state.current_image and not req.skip_current_image: current_image = encode_pil_to_base64(shared.state.current_image) - return ProgressResponse(progress=progress, eta_relative=eta_relative, state=shared.state.dict(), current_image=current_image, textinfo=shared.state.textinfo) + return models.ProgressResponse(progress=progress, eta_relative=eta_relative, state=shared.state.dict(), current_image=current_image, textinfo=shared.state.textinfo) - def interrogateapi(self, interrogatereq: InterrogateRequest): + def interrogateapi(self, interrogatereq: models.InterrogateRequest): image_b64 = interrogatereq.image if image_b64 is None: raise HTTPException(status_code=404, detail="Image not found") @@ -465,7 +467,7 @@ class Api: else: raise HTTPException(status_code=404, detail="Model not found") - return InterrogateResponse(caption=processed) + return models.InterrogateResponse(caption=processed) def interruptapi(self): shared.state.interrupt() @@ -570,36 +572,36 @@ class Api: filename = create_embedding(**args) # create empty embedding sd_hijack.model_hijack.embedding_db.load_textual_inversion_embeddings() # reload embeddings so new one can be immediately used shared.state.end() - return CreateResponse(info=f"create embedding filename: {filename}") + return models.CreateResponse(info=f"create embedding filename: {filename}") except AssertionError as e: shared.state.end() - return TrainResponse(info=f"create embedding error: {e}") + return models.TrainResponse(info=f"create embedding error: {e}") def create_hypernetwork(self, args: dict): try: shared.state.begin() filename = create_hypernetwork(**args) # create empty embedding shared.state.end() - return CreateResponse(info=f"create hypernetwork filename: {filename}") + return models.CreateResponse(info=f"create hypernetwork filename: {filename}") except AssertionError as e: shared.state.end() - return TrainResponse(info=f"create hypernetwork error: {e}") + return models.TrainResponse(info=f"create hypernetwork error: {e}") def preprocess(self, args: dict): try: shared.state.begin() preprocess(**args) # quick operation unless blip/booru interrogation is enabled shared.state.end() - return PreprocessResponse(info = 'preprocess complete') + return models.PreprocessResponse(info = 'preprocess complete') except KeyError as e: shared.state.end() - return PreprocessResponse(info=f"preprocess error: invalid token: {e}") + return models.PreprocessResponse(info=f"preprocess error: invalid token: {e}") except AssertionError as e: shared.state.end() - return PreprocessResponse(info=f"preprocess error: {e}") + return models.PreprocessResponse(info=f"preprocess error: {e}") except FileNotFoundError as e: shared.state.end() - return PreprocessResponse(info=f'preprocess error: {e}') + return models.PreprocessResponse(info=f'preprocess error: {e}') def train_embedding(self, args: dict): try: @@ -617,10 +619,10 @@ class Api: if not apply_optimizations: sd_hijack.apply_optimizations() shared.state.end() - return TrainResponse(info=f"train embedding complete: filename: {filename} error: {error}") + return models.TrainResponse(info=f"train embedding complete: filename: {filename} error: {error}") except AssertionError as msg: shared.state.end() - return TrainResponse(info=f"train embedding error: {msg}") + return models.TrainResponse(info=f"train embedding error: {msg}") def train_hypernetwork(self, args: dict): try: @@ -641,14 +643,15 @@ class Api: if not apply_optimizations: sd_hijack.apply_optimizations() shared.state.end() - return TrainResponse(info=f"train embedding complete: filename: {filename} error: {error}") + return models.TrainResponse(info=f"train embedding complete: filename: {filename} error: {error}") except AssertionError: shared.state.end() - return TrainResponse(info=f"train embedding error: {error}") + return models.TrainResponse(info=f"train embedding error: {error}") def get_memory(self): try: - import os, psutil + import os + import psutil process = psutil.Process(os.getpid()) res = process.memory_info() # only rss is cross-platform guaranteed so we dont rely on other values ram_total = 100 * res.rss / process.memory_percent() # and total memory is calculated as actual value is not cross-platform safe @@ -675,10 +678,10 @@ class Api: 'events': warnings, } else: - cuda = { 'error': 'unavailable' } + cuda = {'error': 'unavailable'} except Exception as err: - cuda = { 'error': f'{err}' } - return MemoryResponse(ram = ram, cuda = cuda) + cuda = {'error': f'{err}'} + return models.MemoryResponse(ram=ram, cuda=cuda) def launch(self, server_name, port): self.app.include_router(self.router) diff --git a/modules/api/models.py b/modules/api/models.py index 4a70f440..4d291076 100644 --- a/modules/api/models.py +++ b/modules/api/models.py @@ -223,8 +223,9 @@ for key in _options: if(_options[key].dest != 'help'): flag = _options[key] _type = str - if _options[key].default is not None: _type = type(_options[key].default) - flags.update({flag.dest: (_type,Field(default=flag.default, description=flag.help))}) + if _options[key].default is not None: + _type = type(_options[key].default) + flags.update({flag.dest: (_type, Field(default=flag.default, description=flag.help))}) FlagsModel = create_model("Flags", **flags) diff --git a/modules/codeformer/codeformer_arch.py b/modules/codeformer/codeformer_arch.py index 11dcc3ee..f1a7cf09 100644 --- a/modules/codeformer/codeformer_arch.py +++ b/modules/codeformer/codeformer_arch.py @@ -7,7 +7,7 @@ from torch import nn, Tensor import torch.nn.functional as F from typing import Optional, List -from modules.codeformer.vqgan_arch import * +from modules.codeformer.vqgan_arch import VQAutoEncoder, ResBlock from basicsr.utils import get_root_logger from basicsr.utils.registry import ARCH_REGISTRY diff --git a/modules/esrgan_model_arch.py b/modules/esrgan_model_arch.py index 6071fea7..7f8bc7c0 100644 --- a/modules/esrgan_model_arch.py +++ b/modules/esrgan_model_arch.py @@ -438,9 +438,11 @@ def conv_block(in_nc, out_nc, kernel_size, stride=1, dilation=1, groups=1, bias= padding = padding if pad_type == 'zero' else 0 if convtype=='PartialConv2D': + from torchvision.ops import PartialConv2d # this is definitely not going to work, but PartialConv2d doesn't work anyway and this shuts up static analyzer c = PartialConv2d(in_nc, out_nc, kernel_size=kernel_size, stride=stride, padding=padding, dilation=dilation, bias=bias, groups=groups) elif convtype=='DeformConv2D': + from torchvision.ops import DeformConv2d # not tested c = DeformConv2d(in_nc, out_nc, kernel_size=kernel_size, stride=stride, padding=padding, dilation=dilation, bias=bias, groups=groups) elif convtype=='Conv3D': diff --git a/modules/extra_networks_hypernet.py b/modules/extra_networks_hypernet.py index 04f27c9f..aa2a14ef 100644 --- a/modules/extra_networks_hypernet.py +++ b/modules/extra_networks_hypernet.py @@ -1,4 +1,4 @@ -from modules import extra_networks, shared, extra_networks +from modules import extra_networks, shared from modules.hypernetworks import hypernetwork diff --git a/modules/images.py b/modules/images.py index 3d5d76cc..5eb6d855 100644 --- a/modules/images.py +++ b/modules/images.py @@ -472,9 +472,9 @@ def get_next_sequence_number(path, basename): prefix_length = len(basename) for p in os.listdir(path): if p.startswith(basename): - l = os.path.splitext(p[prefix_length:])[0].split('-') # splits the filename (removing the basename first if one is defined, so the sequence number is always the first element) + parts = os.path.splitext(p[prefix_length:])[0].split('-') # splits the filename (removing the basename first if one is defined, so the sequence number is always the first element) try: - result = max(int(l[0]), result) + result = max(int(parts[0]), result) except ValueError: pass diff --git a/modules/img2img.py b/modules/img2img.py index cdae301a..32b1ecd6 100644 --- a/modules/img2img.py +++ b/modules/img2img.py @@ -13,7 +13,6 @@ from modules.shared import opts, state import modules.shared as shared import modules.processing as processing from modules.ui import plaintext_to_html -import modules.images as images import modules.scripts diff --git a/modules/interrogate.py b/modules/interrogate.py index 9f7d657f..22df9216 100644 --- a/modules/interrogate.py +++ b/modules/interrogate.py @@ -11,7 +11,6 @@ import torch.hub from torchvision import transforms from torchvision.transforms.functional import InterpolationMode -import modules.shared as shared from modules import devices, paths, shared, lowvram, modelloader, errors blip_image_eval_size = 384 diff --git a/modules/modelloader.py b/modules/modelloader.py index cb85ac4f..cf685000 100644 --- a/modules/modelloader.py +++ b/modules/modelloader.py @@ -108,12 +108,12 @@ def move_files(src_path: str, dest_path: str, ext_filter: str = None): print(f"Moving {file} from {src_path} to {dest_path}.") try: shutil.move(fullpath, dest_path) - except: + except Exception: pass if len(os.listdir(src_path)) == 0: print(f"Removing empty folder: {src_path}") shutil.rmtree(src_path, True) - except: + except Exception: pass @@ -141,7 +141,7 @@ def load_upscalers(): full_model = f"modules.{model_name}_model" try: importlib.import_module(full_model) - except: + except Exception: pass datas = [] diff --git a/modules/models/diffusion/ddpm_edit.py b/modules/models/diffusion/ddpm_edit.py index f880bc3c..611c2b69 100644 --- a/modules/models/diffusion/ddpm_edit.py +++ b/modules/models/diffusion/ddpm_edit.py @@ -479,7 +479,7 @@ class LatentDiffusion(DDPM): self.cond_stage_key = cond_stage_key try: self.num_downs = len(first_stage_config.params.ddconfig.ch_mult) - 1 - except: + except Exception: self.num_downs = 0 if not scale_by_std: self.scale_factor = scale_factor @@ -891,16 +891,6 @@ class LatentDiffusion(DDPM): c = self.q_sample(x_start=c, t=tc, noise=torch.randn_like(c.float())) return self.p_losses(x, c, t, *args, **kwargs) - def _rescale_annotations(self, bboxes, crop_coordinates): # TODO: move to dataset - def rescale_bbox(bbox): - x0 = clamp((bbox[0] - crop_coordinates[0]) / crop_coordinates[2]) - y0 = clamp((bbox[1] - crop_coordinates[1]) / crop_coordinates[3]) - w = min(bbox[2] / crop_coordinates[2], 1 - x0) - h = min(bbox[3] / crop_coordinates[3], 1 - y0) - return x0, y0, w, h - - return [rescale_bbox(b) for b in bboxes] - def apply_model(self, x_noisy, t, cond, return_ids=False): if isinstance(cond, dict): @@ -1171,8 +1161,10 @@ class LatentDiffusion(DDPM): if i % log_every_t == 0 or i == timesteps - 1: intermediates.append(x0_partial) - if callback: callback(i) - if img_callback: img_callback(img, i) + if callback: + callback(i) + if img_callback: + img_callback(img, i) return img, intermediates @torch.no_grad() @@ -1219,8 +1211,10 @@ class LatentDiffusion(DDPM): if i % log_every_t == 0 or i == timesteps - 1: intermediates.append(img) - if callback: callback(i) - if img_callback: img_callback(img, i) + if callback: + callback(i) + if img_callback: + img_callback(img, i) if return_intermediates: return img, intermediates @@ -1337,7 +1331,7 @@ class LatentDiffusion(DDPM): if inpaint: # make a simple center square - b, h, w = z.shape[0], z.shape[2], z.shape[3] + h, w = z.shape[2], z.shape[3] mask = torch.ones(N, h, w).to(self.device) # zeros will be filled in mask[:, h // 4:3 * h // 4, w // 4:3 * w // 4] = 0. diff --git a/modules/models/diffusion/uni_pc/sampler.py b/modules/models/diffusion/uni_pc/sampler.py index a241c8a7..0a9defa1 100644 --- a/modules/models/diffusion/uni_pc/sampler.py +++ b/modules/models/diffusion/uni_pc/sampler.py @@ -54,7 +54,8 @@ class UniPCSampler(object): if conditioning is not None: if isinstance(conditioning, dict): ctmp = conditioning[list(conditioning.keys())[0]] - while isinstance(ctmp, list): ctmp = ctmp[0] + while isinstance(ctmp, list): + ctmp = ctmp[0] cbs = ctmp.shape[0] if cbs != batch_size: print(f"Warning: Got {cbs} conditionings but batch-size is {batch_size}") diff --git a/modules/processing.py b/modules/processing.py index 1a76e552..6f5233c1 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -664,7 +664,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: if not shared.opts.dont_fix_second_order_samplers_schedule: try: step_multiplier = 2 if sd_samplers.all_samplers_map.get(p.sampler_name).aliases[0] in ['k_dpmpp_2s_a', 'k_dpmpp_2s_a_ka', 'k_dpmpp_sde', 'k_dpmpp_sde_ka', 'k_dpm_2', 'k_dpm_2_a', 'k_heun'] else 1 - except: + except Exception: pass uc = get_conds_with_caching(prompt_parser.get_learned_conditioning, negative_prompts, p.steps * step_multiplier, cached_uc) c = get_conds_with_caching(prompt_parser.get_multicond_learned_conditioning, prompts, p.steps * step_multiplier, cached_c) diff --git a/modules/prompt_parser.py b/modules/prompt_parser.py index e084e948..3a720721 100644 --- a/modules/prompt_parser.py +++ b/modules/prompt_parser.py @@ -54,18 +54,21 @@ def get_learned_conditioning_prompt_schedules(prompts, steps): """ def collect_steps(steps, tree): - l = [steps] + res = [steps] + class CollectSteps(lark.Visitor): def scheduled(self, tree): tree.children[-1] = float(tree.children[-1]) if tree.children[-1] < 1: tree.children[-1] *= steps tree.children[-1] = min(steps, int(tree.children[-1])) - l.append(tree.children[-1]) + res.append(tree.children[-1]) + def alternate(self, tree): - l.extend(range(1, steps+1)) + res.extend(range(1, steps+1)) + CollectSteps().visit(tree) - return sorted(set(l)) + return sorted(set(res)) def at_step(step, tree): class AtStep(lark.Transformer): diff --git a/modules/textual_inversion/autocrop.py b/modules/textual_inversion/autocrop.py index ba1bdcd4..d7d8d2e3 100644 --- a/modules/textual_inversion/autocrop.py +++ b/modules/textual_inversion/autocrop.py @@ -185,7 +185,7 @@ def image_face_points(im, settings): try: faces = classifier.detectMultiScale(gray, scaleFactor=1.1, minNeighbors=7, minSize=(minsize, minsize), flags=cv2.CASCADE_SCALE_IMAGE) - except: + except Exception: continue if len(faces) > 0: diff --git a/modules/ui.py b/modules/ui.py index 2171f3aa..6beda76f 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -1,15 +1,9 @@ -import html import json -import math import mimetypes import os -import platform -import random import sys -import tempfile -import time import traceback -from functools import partial, reduce +from functools import reduce import warnings import gradio as gr diff --git a/modules/upscaler.py b/modules/upscaler.py index e2eaa730..0ad4fe99 100644 --- a/modules/upscaler.py +++ b/modules/upscaler.py @@ -45,7 +45,7 @@ class Upscaler: try: import cv2 self.can_tile = True - except: + except Exception: pass @abstractmethod -- cgit v1.2.3 From f741a98baccae100fcfb40c017b5c35c5cba1b0c Mon Sep 17 00:00:00 2001 From: AUTOMATIC <16777216c@gmail.com> Date: Wed, 10 May 2023 08:43:42 +0300 Subject: imports cleanup for ruff --- extensions-builtin/Lora/lora.py | 1 - extensions-builtin/ScuNET/scripts/scunet_model.py | 1 - extensions-builtin/SwinIR/scripts/swinir_model.py | 3 +-- modules/codeformer/codeformer_arch.py | 4 +--- modules/codeformer/vqgan_arch.py | 2 -- modules/codeformer_model.py | 4 +--- modules/config_states.py | 2 +- modules/esrgan_model.py | 2 +- modules/esrgan_model_arch.py | 1 - modules/extensions.py | 1 - modules/generation_parameters_copypaste.py | 4 ---- modules/hypernetworks/hypernetwork.py | 3 +-- modules/hypernetworks/ui.py | 2 -- modules/images.py | 2 +- modules/img2img.py | 5 +---- modules/mac_specific.py | 1 - modules/modelloader.py | 1 - modules/models/diffusion/uni_pc/uni_pc.py | 1 - modules/processing.py | 5 ++--- modules/sd_hijack.py | 2 +- modules/sd_hijack_inpainting.py | 6 ------ modules/sd_hijack_ip2p.py | 5 +---- modules/sd_hijack_xlmr.py | 2 -- modules/sd_models.py | 2 +- modules/sd_models_config.py | 1 - modules/sd_samplers_kdiffusion.py | 1 - modules/sd_vae.py | 3 --- modules/shared.py | 3 --- modules/styles.py | 9 --------- modules/textual_inversion/autocrop.py | 4 +--- modules/textual_inversion/image_embedding.py | 2 +- modules/textual_inversion/preprocess.py | 4 ---- modules/textual_inversion/textual_inversion.py | 1 - modules/txt2img.py | 9 +++------ modules/ui.py | 5 ++--- modules/ui_extra_networks.py | 1 - modules/ui_postprocessing.py | 2 +- modules/upscaler.py | 2 -- modules/xlmr.py | 2 +- pyproject.toml | 11 +++++++---- scripts/custom_code.py | 2 +- scripts/outpainting_mk_2.py | 4 ++-- scripts/poor_mans_outpainting.py | 4 ++-- scripts/prompt_matrix.py | 7 ++----- scripts/prompts_from_file.py | 5 +---- scripts/sd_upscale.py | 4 ++-- scripts/xyz_grid.py | 6 ++---- webui.py | 2 +- 48 files changed, 42 insertions(+), 114 deletions(-) (limited to 'modules/processing.py') diff --git a/extensions-builtin/Lora/lora.py b/extensions-builtin/Lora/lora.py index ba1293df..0ab43229 100644 --- a/extensions-builtin/Lora/lora.py +++ b/extensions-builtin/Lora/lora.py @@ -1,4 +1,3 @@ -import glob import os import re import torch diff --git a/extensions-builtin/ScuNET/scripts/scunet_model.py b/extensions-builtin/ScuNET/scripts/scunet_model.py index c7fd5739..aa2fdb3a 100644 --- a/extensions-builtin/ScuNET/scripts/scunet_model.py +++ b/extensions-builtin/ScuNET/scripts/scunet_model.py @@ -13,7 +13,6 @@ import modules.upscaler from modules import devices, modelloader from scunet_model_arch import SCUNet as net from modules.shared import opts -from modules import images class UpscalerScuNET(modules.upscaler.Upscaler): diff --git a/extensions-builtin/SwinIR/scripts/swinir_model.py b/extensions-builtin/SwinIR/scripts/swinir_model.py index d77c3a92..55dd94ab 100644 --- a/extensions-builtin/SwinIR/scripts/swinir_model.py +++ b/extensions-builtin/SwinIR/scripts/swinir_model.py @@ -1,4 +1,3 @@ -import contextlib import os import numpy as np @@ -8,7 +7,7 @@ from basicsr.utils.download_util import load_file_from_url from tqdm import tqdm from modules import modelloader, devices, script_callbacks, shared -from modules.shared import cmd_opts, opts, state +from modules.shared import opts, state from swinir_model_arch import SwinIR as net from swinir_model_arch_v2 import Swin2SR as net2 from modules.upscaler import Upscaler, UpscalerData diff --git a/modules/codeformer/codeformer_arch.py b/modules/codeformer/codeformer_arch.py index f1a7cf09..00c407de 100644 --- a/modules/codeformer/codeformer_arch.py +++ b/modules/codeformer/codeformer_arch.py @@ -1,14 +1,12 @@ # this file is copied from CodeFormer repository. Please see comment in modules/codeformer_model.py import math -import numpy as np import torch from torch import nn, Tensor import torch.nn.functional as F -from typing import Optional, List +from typing import Optional from modules.codeformer.vqgan_arch import VQAutoEncoder, ResBlock -from basicsr.utils import get_root_logger from basicsr.utils.registry import ARCH_REGISTRY def calc_mean_std(feat, eps=1e-5): diff --git a/modules/codeformer/vqgan_arch.py b/modules/codeformer/vqgan_arch.py index e7293683..820e6b12 100644 --- a/modules/codeformer/vqgan_arch.py +++ b/modules/codeformer/vqgan_arch.py @@ -5,11 +5,9 @@ VQGAN code, adapted from the original created by the Unleashing Transformers aut https://github.com/samb-t/unleashing-transformers/blob/master/models/vqgan.py ''' -import numpy as np import torch import torch.nn as nn import torch.nn.functional as F -import copy from basicsr.utils import get_root_logger from basicsr.utils.registry import ARCH_REGISTRY diff --git a/modules/codeformer_model.py b/modules/codeformer_model.py index 8d84bbc9..8e56cb89 100644 --- a/modules/codeformer_model.py +++ b/modules/codeformer_model.py @@ -33,11 +33,9 @@ def setup_model(dirname): try: from torchvision.transforms.functional import normalize from modules.codeformer.codeformer_arch import CodeFormer - from basicsr.utils.download_util import load_file_from_url - from basicsr.utils import imwrite, img2tensor, tensor2img + from basicsr.utils import img2tensor, tensor2img from facelib.utils.face_restoration_helper import FaceRestoreHelper from facelib.detection.retinaface import retinaface - from modules.shared import cmd_opts net_class = CodeFormer diff --git a/modules/config_states.py b/modules/config_states.py index 2ea00929..8f1ff428 100644 --- a/modules/config_states.py +++ b/modules/config_states.py @@ -14,7 +14,7 @@ from collections import OrderedDict import git from modules import shared, extensions -from modules.paths_internal import extensions_dir, extensions_builtin_dir, script_path, config_states_dir +from modules.paths_internal import script_path, config_states_dir all_config_states = OrderedDict() diff --git a/modules/esrgan_model.py b/modules/esrgan_model.py index f4369257..85aa6934 100644 --- a/modules/esrgan_model.py +++ b/modules/esrgan_model.py @@ -6,7 +6,7 @@ from PIL import Image from basicsr.utils.download_util import load_file_from_url import modules.esrgan_model_arch as arch -from modules import shared, modelloader, images, devices +from modules import modelloader, images, devices from modules.upscaler import Upscaler, UpscalerData from modules.shared import opts diff --git a/modules/esrgan_model_arch.py b/modules/esrgan_model_arch.py index 7f8bc7c0..4de9dd8d 100644 --- a/modules/esrgan_model_arch.py +++ b/modules/esrgan_model_arch.py @@ -2,7 +2,6 @@ from collections import OrderedDict import math -import functools import torch import torch.nn as nn import torch.nn.functional as F diff --git a/modules/extensions.py b/modules/extensions.py index 34d9d654..829f8cd9 100644 --- a/modules/extensions.py +++ b/modules/extensions.py @@ -3,7 +3,6 @@ import sys import traceback import time -from datetime import datetime import git from modules import shared diff --git a/modules/generation_parameters_copypaste.py b/modules/generation_parameters_copypaste.py index fe8b18b2..f1c59c46 100644 --- a/modules/generation_parameters_copypaste.py +++ b/modules/generation_parameters_copypaste.py @@ -1,15 +1,11 @@ import base64 -import html import io -import math import os import re -from pathlib import Path import gradio as gr from modules.paths import data_path from modules import shared, ui_tempdir, script_callbacks -import tempfile from PIL import Image re_param_code = r'\s*([\w ]+):\s*("(?:\\"[^,]|\\"|\\|[^\"])+"|[^,]*)(?:,|$)' diff --git a/modules/hypernetworks/hypernetwork.py b/modules/hypernetworks/hypernetwork.py index 1fc49537..9fe749b7 100644 --- a/modules/hypernetworks/hypernetwork.py +++ b/modules/hypernetworks/hypernetwork.py @@ -1,4 +1,3 @@ -import csv import datetime import glob import html @@ -18,7 +17,7 @@ from modules.textual_inversion.learn_schedule import LearnRateScheduler from torch import einsum from torch.nn.init import normal_, xavier_normal_, xavier_uniform_, kaiming_normal_, kaiming_uniform_, zeros_ -from collections import defaultdict, deque +from collections import deque from statistics import stdev, mean diff --git a/modules/hypernetworks/ui.py b/modules/hypernetworks/ui.py index 76599f5a..be168736 100644 --- a/modules/hypernetworks/ui.py +++ b/modules/hypernetworks/ui.py @@ -1,6 +1,4 @@ import html -import os -import re import gradio as gr import modules.hypernetworks.hypernetwork diff --git a/modules/images.py b/modules/images.py index 5eb6d855..7392cb8b 100644 --- a/modules/images.py +++ b/modules/images.py @@ -19,7 +19,7 @@ import json import hashlib from modules import sd_samplers, shared, script_callbacks, errors -from modules.shared import opts, cmd_opts +from modules.shared import opts LANCZOS = (Image.Resampling.LANCZOS if hasattr(Image, 'Resampling') else Image.LANCZOS) diff --git a/modules/img2img.py b/modules/img2img.py index 32b1ecd6..d704bf90 100644 --- a/modules/img2img.py +++ b/modules/img2img.py @@ -1,12 +1,9 @@ -import math import os -import sys -import traceback import numpy as np from PIL import Image, ImageOps, ImageFilter, ImageEnhance, ImageChops, UnidentifiedImageError -from modules import devices, sd_samplers +from modules import sd_samplers from modules.generation_parameters_copypaste import create_override_settings_dict from modules.processing import Processed, StableDiffusionProcessingImg2Img, process_images from modules.shared import opts, state diff --git a/modules/mac_specific.py b/modules/mac_specific.py index 40ce2101..5c2f92a1 100644 --- a/modules/mac_specific.py +++ b/modules/mac_specific.py @@ -1,6 +1,5 @@ import torch import platform -from modules import paths from modules.sd_hijack_utils import CondFunc from packaging import version diff --git a/modules/modelloader.py b/modules/modelloader.py index cf685000..92ada694 100644 --- a/modules/modelloader.py +++ b/modules/modelloader.py @@ -1,4 +1,3 @@ -import glob import os import shutil import importlib diff --git a/modules/models/diffusion/uni_pc/uni_pc.py b/modules/models/diffusion/uni_pc/uni_pc.py index 11b330bc..a4c4ef4e 100644 --- a/modules/models/diffusion/uni_pc/uni_pc.py +++ b/modules/models/diffusion/uni_pc/uni_pc.py @@ -1,5 +1,4 @@ import torch -import torch.nn.functional as F import math from tqdm.auto import trange diff --git a/modules/processing.py b/modules/processing.py index 6f5233c1..c3932d6b 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -2,7 +2,6 @@ import json import math import os import sys -import warnings import hashlib import torch @@ -11,10 +10,10 @@ from PIL import Image, ImageFilter, ImageOps import random import cv2 from skimage import exposure -from typing import Any, Dict, List, Optional +from typing import Any, Dict, List import modules.sd_hijack -from modules import devices, prompt_parser, masking, sd_samplers, lowvram, generation_parameters_copypaste, script_callbacks, extra_networks, sd_vae_approx, scripts +from modules import devices, prompt_parser, masking, sd_samplers, lowvram, generation_parameters_copypaste, extra_networks, sd_vae_approx, scripts from modules.sd_hijack import model_hijack from modules.shared import opts, cmd_opts, state import modules.shared as shared diff --git a/modules/sd_hijack.py b/modules/sd_hijack.py index d8135211..81573b78 100644 --- a/modules/sd_hijack.py +++ b/modules/sd_hijack.py @@ -3,7 +3,7 @@ from torch.nn.functional import silu from types import MethodType import modules.textual_inversion.textual_inversion -from modules import devices, sd_hijack_optimizations, shared, sd_hijack_checkpoint +from modules import devices, sd_hijack_optimizations, shared from modules.hypernetworks import hypernetwork from modules.shared import cmd_opts from modules import sd_hijack_clip, sd_hijack_open_clip, sd_hijack_unet, sd_hijack_xlmr, xlmr diff --git a/modules/sd_hijack_inpainting.py b/modules/sd_hijack_inpainting.py index 55a2ce4d..344d75c8 100644 --- a/modules/sd_hijack_inpainting.py +++ b/modules/sd_hijack_inpainting.py @@ -1,15 +1,9 @@ -import os import torch -from einops import repeat -from omegaconf import ListConfig - import ldm.models.diffusion.ddpm import ldm.models.diffusion.ddim import ldm.models.diffusion.plms -from ldm.models.diffusion.ddpm import LatentDiffusion -from ldm.models.diffusion.plms import PLMSSampler from ldm.models.diffusion.ddim import DDIMSampler, noise_like from ldm.models.diffusion.sampling_util import norm_thresholding diff --git a/modules/sd_hijack_ip2p.py b/modules/sd_hijack_ip2p.py index 41ed54a2..6fe6b6ff 100644 --- a/modules/sd_hijack_ip2p.py +++ b/modules/sd_hijack_ip2p.py @@ -1,8 +1,5 @@ -import collections import os.path -import sys -import gc -import time + def should_hijack_ip2p(checkpoint_info): from modules import sd_models_config diff --git a/modules/sd_hijack_xlmr.py b/modules/sd_hijack_xlmr.py index 4ac51c38..28528329 100644 --- a/modules/sd_hijack_xlmr.py +++ b/modules/sd_hijack_xlmr.py @@ -1,8 +1,6 @@ -import open_clip.tokenizer import torch from modules import sd_hijack_clip, devices -from modules.shared import opts class FrozenXLMREmbedderWithCustomWords(sd_hijack_clip.FrozenCLIPEmbedderWithCustomWords): diff --git a/modules/sd_models.py b/modules/sd_models.py index 11c1a344..1c09c709 100644 --- a/modules/sd_models.py +++ b/modules/sd_models.py @@ -565,7 +565,7 @@ def reload_model_weights(sd_model=None, info=None): def unload_model_weights(sd_model=None, info=None): - from modules import lowvram, devices, sd_hijack + from modules import devices, sd_hijack timer = Timer() if model_data.sd_model: diff --git a/modules/sd_models_config.py b/modules/sd_models_config.py index 7a79925a..9bfe1237 100644 --- a/modules/sd_models_config.py +++ b/modules/sd_models_config.py @@ -1,4 +1,3 @@ -import re import os import torch diff --git a/modules/sd_samplers_kdiffusion.py b/modules/sd_samplers_kdiffusion.py index 0fc9f456..3b8e9622 100644 --- a/modules/sd_samplers_kdiffusion.py +++ b/modules/sd_samplers_kdiffusion.py @@ -1,7 +1,6 @@ from collections import deque import torch import inspect -import einops import k_diffusion.sampling from modules import prompt_parser, devices, sd_samplers_common diff --git a/modules/sd_vae.py b/modules/sd_vae.py index 521e485a..b7176125 100644 --- a/modules/sd_vae.py +++ b/modules/sd_vae.py @@ -1,8 +1,5 @@ -import torch -import safetensors.torch import os import collections -from collections import namedtuple from modules import paths, shared, devices, script_callbacks, sd_models import glob from copy import deepcopy diff --git a/modules/shared.py b/modules/shared.py index 4631965b..44cd2c0c 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -1,12 +1,9 @@ -import argparse import datetime import json import os import sys import time -import requests -from PIL import Image import gradio as gr import tqdm diff --git a/modules/styles.py b/modules/styles.py index 11642075..c22769cf 100644 --- a/modules/styles.py +++ b/modules/styles.py @@ -1,18 +1,9 @@ -# We need this so Python doesn't complain about the unknown StableDiffusionProcessing-typehint at runtime -from __future__ import annotations - import csv import os import os.path import typing -import collections.abc as abc -import tempfile import shutil -if typing.TYPE_CHECKING: - # Only import this when code is being type-checked, it doesn't have any effect at runtime - from .processing import StableDiffusionProcessing - class PromptStyle(typing.NamedTuple): name: str diff --git a/modules/textual_inversion/autocrop.py b/modules/textual_inversion/autocrop.py index d7d8d2e3..7770d22f 100644 --- a/modules/textual_inversion/autocrop.py +++ b/modules/textual_inversion/autocrop.py @@ -1,10 +1,8 @@ import cv2 import requests import os -from collections import defaultdict -from math import log, sqrt import numpy as np -from PIL import Image, ImageDraw +from PIL import ImageDraw GREEN = "#0F0" BLUE = "#00F" diff --git a/modules/textual_inversion/image_embedding.py b/modules/textual_inversion/image_embedding.py index 5593f88c..ee0e850a 100644 --- a/modules/textual_inversion/image_embedding.py +++ b/modules/textual_inversion/image_embedding.py @@ -2,7 +2,7 @@ import base64 import json import numpy as np import zlib -from PIL import Image, PngImagePlugin, ImageDraw, ImageFont +from PIL import Image, ImageDraw, ImageFont from fonts.ttf import Roboto import torch from modules.shared import opts diff --git a/modules/textual_inversion/preprocess.py b/modules/textual_inversion/preprocess.py index da0bcb26..d0cad09e 100644 --- a/modules/textual_inversion/preprocess.py +++ b/modules/textual_inversion/preprocess.py @@ -1,13 +1,9 @@ import os from PIL import Image, ImageOps import math -import platform -import sys import tqdm -import time from modules import paths, shared, images, deepbooru -from modules.shared import opts, cmd_opts from modules.textual_inversion import autocrop diff --git a/modules/textual_inversion/textual_inversion.py b/modules/textual_inversion/textual_inversion.py index f753b75f..9ed9ba45 100644 --- a/modules/textual_inversion/textual_inversion.py +++ b/modules/textual_inversion/textual_inversion.py @@ -1,7 +1,6 @@ import os import sys import traceback -import inspect from collections import namedtuple import torch diff --git a/modules/txt2img.py b/modules/txt2img.py index 16841d0f..f022381c 100644 --- a/modules/txt2img.py +++ b/modules/txt2img.py @@ -1,18 +1,15 @@ import modules.scripts -from modules import sd_samplers +from modules import sd_samplers, processing from modules.generation_parameters_copypaste import create_override_settings_dict -from modules.processing import StableDiffusionProcessing, Processed, StableDiffusionProcessingTxt2Img, \ - StableDiffusionProcessingImg2Img, process_images from modules.shared import opts, cmd_opts import modules.shared as shared -import modules.processing as processing from modules.ui import plaintext_to_html def txt2img(id_task: str, prompt: str, negative_prompt: str, prompt_styles, steps: int, sampler_index: int, restore_faces: bool, tiling: bool, n_iter: int, batch_size: int, cfg_scale: float, seed: int, subseed: int, subseed_strength: float, seed_resize_from_h: int, seed_resize_from_w: int, seed_enable_extras: bool, height: int, width: int, enable_hr: bool, denoising_strength: float, hr_scale: float, hr_upscaler: str, hr_second_pass_steps: int, hr_resize_x: int, hr_resize_y: int, override_settings_texts, *args): override_settings = create_override_settings_dict(override_settings_texts) - p = StableDiffusionProcessingTxt2Img( + p = processing.StableDiffusionProcessingTxt2Img( sd_model=shared.sd_model, outpath_samples=opts.outdir_samples or opts.outdir_txt2img_samples, outpath_grids=opts.outdir_grids or opts.outdir_txt2img_grids, @@ -53,7 +50,7 @@ def txt2img(id_task: str, prompt: str, negative_prompt: str, prompt_styles, step processed = modules.scripts.scripts_txt2img.run(p, *args) if processed is None: - processed = process_images(p) + processed = processing.process_images(p) p.close() diff --git a/modules/ui.py b/modules/ui.py index 6beda76f..f7e57593 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -14,10 +14,10 @@ from PIL import Image, PngImagePlugin from modules.call_queue import wrap_gradio_gpu_call, wrap_queued_call, wrap_gradio_call from modules import sd_hijack, sd_models, localization, script_callbacks, ui_extensions, deepbooru, sd_vae, extra_networks, postprocessing, ui_components, ui_common, ui_postprocessing, progress -from modules.ui_components import FormRow, FormColumn, FormGroup, ToolButton, FormHTML +from modules.ui_components import FormRow, FormGroup, ToolButton, FormHTML from modules.paths import script_path, data_path -from modules.shared import opts, cmd_opts, restricted_opts +from modules.shared import opts, cmd_opts import modules.codeformer_model import modules.generation_parameters_copypaste as parameters_copypaste @@ -28,7 +28,6 @@ import modules.shared as shared import modules.styles import modules.textual_inversion.ui from modules import prompt_parser -from modules.images import save_image from modules.sd_hijack import model_hijack from modules.sd_samplers import samplers, samplers_for_img2img from modules.textual_inversion import textual_inversion diff --git a/modules/ui_extra_networks.py b/modules/ui_extra_networks.py index 49e06289..800e467a 100644 --- a/modules/ui_extra_networks.py +++ b/modules/ui_extra_networks.py @@ -1,4 +1,3 @@ -import glob import os.path import urllib.parse from pathlib import Path diff --git a/modules/ui_postprocessing.py b/modules/ui_postprocessing.py index f25639e5..c7dc1154 100644 --- a/modules/ui_postprocessing.py +++ b/modules/ui_postprocessing.py @@ -1,5 +1,5 @@ import gradio as gr -from modules import scripts_postprocessing, scripts, shared, gfpgan_model, codeformer_model, ui_common, postprocessing, call_queue +from modules import scripts, shared, ui_common, postprocessing, call_queue import modules.generation_parameters_copypaste as parameters_copypaste diff --git a/modules/upscaler.py b/modules/upscaler.py index 0ad4fe99..777593b0 100644 --- a/modules/upscaler.py +++ b/modules/upscaler.py @@ -2,8 +2,6 @@ import os from abc import abstractmethod import PIL -import numpy as np -import torch from PIL import Image import modules.shared diff --git a/modules/xlmr.py b/modules/xlmr.py index beab3fdf..e056c3f6 100644 --- a/modules/xlmr.py +++ b/modules/xlmr.py @@ -1,4 +1,4 @@ -from transformers import BertPreTrainedModel,BertModel,BertConfig +from transformers import BertPreTrainedModel, BertConfig import torch.nn as nn import torch from transformers.models.xlm_roberta.configuration_xlm_roberta import XLMRobertaConfig diff --git a/pyproject.toml b/pyproject.toml index 1e164abc..9caa9ba2 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,10 +1,13 @@ [tool.ruff] +exclude = ["extensions"] + ignore = [ "E501", - "E731", - "E402", # Module level import not at top of file - "F401" # Module imported but unused + + "F401", # Module imported but unused ] -exclude = ["extensions"] + +[tool.ruff.per-file-ignores] +"webui.py" = ["E402"] # Module level import not at top of file \ No newline at end of file diff --git a/scripts/custom_code.py b/scripts/custom_code.py index f36a3675..cc6f0d49 100644 --- a/scripts/custom_code.py +++ b/scripts/custom_code.py @@ -4,7 +4,7 @@ import ast import copy from modules.processing import Processed -from modules.shared import opts, cmd_opts, state +from modules.shared import cmd_opts def convertExpr2Expression(expr): diff --git a/scripts/outpainting_mk_2.py b/scripts/outpainting_mk_2.py index b10fed6c..665dbe89 100644 --- a/scripts/outpainting_mk_2.py +++ b/scripts/outpainting_mk_2.py @@ -7,9 +7,9 @@ import modules.scripts as scripts import gradio as gr from PIL import Image, ImageDraw -from modules import images, processing, devices +from modules import images from modules.processing import Processed, process_images -from modules.shared import opts, cmd_opts, state +from modules.shared import opts, state # this function is taken from https://github.com/parlance-zz/g-diffuser-bot diff --git a/scripts/poor_mans_outpainting.py b/scripts/poor_mans_outpainting.py index ddcbd2d3..c0bbecc1 100644 --- a/scripts/poor_mans_outpainting.py +++ b/scripts/poor_mans_outpainting.py @@ -4,9 +4,9 @@ import modules.scripts as scripts import gradio as gr from PIL import Image, ImageDraw -from modules import images, processing, devices +from modules import images, devices from modules.processing import Processed, process_images -from modules.shared import opts, cmd_opts, state +from modules.shared import opts, state class Script(scripts.Script): diff --git a/scripts/prompt_matrix.py b/scripts/prompt_matrix.py index e9b11517..fb06beab 100644 --- a/scripts/prompt_matrix.py +++ b/scripts/prompt_matrix.py @@ -1,14 +1,11 @@ import math -from collections import namedtuple -from copy import copy -import random import modules.scripts as scripts import gradio as gr from modules import images -from modules.processing import process_images, Processed -from modules.shared import opts, cmd_opts, state +from modules.processing import process_images +from modules.shared import opts, state import modules.sd_samplers diff --git a/scripts/prompts_from_file.py b/scripts/prompts_from_file.py index 76dc5778..149bc85f 100644 --- a/scripts/prompts_from_file.py +++ b/scripts/prompts_from_file.py @@ -1,6 +1,4 @@ import copy -import math -import os import random import sys import traceback @@ -11,8 +9,7 @@ import gradio as gr from modules import sd_samplers from modules.processing import Processed, process_images -from PIL import Image -from modules.shared import opts, cmd_opts, state +from modules.shared import state def process_string_tag(tag): diff --git a/scripts/sd_upscale.py b/scripts/sd_upscale.py index 332d76d9..d873a09c 100644 --- a/scripts/sd_upscale.py +++ b/scripts/sd_upscale.py @@ -4,9 +4,9 @@ import modules.scripts as scripts import gradio as gr from PIL import Image -from modules import processing, shared, sd_samplers, images, devices +from modules import processing, shared, images, devices from modules.processing import Processed -from modules.shared import opts, cmd_opts, state +from modules.shared import opts, state class Script(scripts.Script): diff --git a/scripts/xyz_grid.py b/scripts/xyz_grid.py index 2ff42ef8..332e0ecd 100644 --- a/scripts/xyz_grid.py +++ b/scripts/xyz_grid.py @@ -10,15 +10,13 @@ import numpy as np import modules.scripts as scripts import gradio as gr -from modules import images, paths, sd_samplers, processing, sd_models, sd_vae +from modules import images, sd_samplers, processing, sd_models, sd_vae from modules.processing import process_images, Processed, StableDiffusionProcessingTxt2Img -from modules.shared import opts, cmd_opts, state +from modules.shared import opts, state import modules.shared as shared import modules.sd_samplers import modules.sd_models import modules.sd_vae -import glob -import os import re from modules.ui_components import ToolButton diff --git a/webui.py b/webui.py index ec3d2aba..48277075 100644 --- a/webui.py +++ b/webui.py @@ -43,7 +43,7 @@ if ".dev" in torch.__version__ or "+git" in torch.__version__: torch.__long_version__ = torch.__version__ torch.__version__ = re.search(r'[\d.]+[\d]', torch.__version__).group(0) -from modules import shared, devices, sd_samplers, upscaler, extensions, localization, ui_tempdir, ui_extra_networks, config_states +from modules import shared, sd_samplers, upscaler, extensions, localization, ui_tempdir, ui_extra_networks, config_states import modules.codeformer_model as codeformer import modules.face_restoration import modules.gfpgan_model as gfpgan -- cgit v1.2.3 From 49a55b410b66b7dd9be9335d8a2e3a71e4f8b15c Mon Sep 17 00:00:00 2001 From: Aarni Koskela Date: Thu, 11 May 2023 18:28:15 +0300 Subject: Autofix Ruff W (not W605) (mostly whitespace) --- extensions-builtin/LDSR/ldsr_model_arch.py | 4 +- extensions-builtin/LDSR/sd_hijack_ddpm_v1.py | 6 +-- extensions-builtin/ScuNET/scunet_model_arch.py | 2 +- extensions-builtin/SwinIR/scripts/swinir_model.py | 2 +- extensions-builtin/SwinIR/swinir_model_arch.py | 2 +- extensions-builtin/SwinIR/swinir_model_arch_v2.py | 52 +++++++++++------------ launch.py | 2 +- modules/api/api.py | 4 +- modules/api/models.py | 2 +- modules/cmd_args.py | 2 +- modules/codeformer/codeformer_arch.py | 14 +++--- modules/codeformer/vqgan_arch.py | 38 ++++++++--------- modules/esrgan_model_arch.py | 4 +- modules/extras.py | 2 +- modules/hypernetworks/hypernetwork.py | 12 +++--- modules/images.py | 2 +- modules/mac_specific.py | 4 +- modules/masking.py | 2 +- modules/ngrok.py | 4 +- modules/processing.py | 2 +- modules/script_callbacks.py | 14 +++--- modules/sd_hijack.py | 12 +++--- modules/sd_hijack_optimizations.py | 32 +++++++------- modules/sd_models.py | 4 +- modules/sd_samplers_kdiffusion.py | 18 ++++---- modules/sub_quadratic_attention.py | 2 +- modules/textual_inversion/dataset.py | 4 +- modules/textual_inversion/preprocess.py | 2 +- modules/textual_inversion/textual_inversion.py | 16 +++---- modules/ui.py | 18 ++++---- modules/ui_extensions.py | 6 +-- modules/xlmr.py | 6 +-- pyproject.toml | 5 ++- scripts/img2imgalt.py | 14 +++--- scripts/loopback.py | 8 ++-- scripts/poor_mans_outpainting.py | 2 +- scripts/prompt_matrix.py | 2 +- scripts/prompts_from_file.py | 4 +- scripts/sd_upscale.py | 2 +- 39 files changed, 167 insertions(+), 166 deletions(-) (limited to 'modules/processing.py') diff --git a/extensions-builtin/LDSR/ldsr_model_arch.py b/extensions-builtin/LDSR/ldsr_model_arch.py index 2173de79..7f450086 100644 --- a/extensions-builtin/LDSR/ldsr_model_arch.py +++ b/extensions-builtin/LDSR/ldsr_model_arch.py @@ -130,11 +130,11 @@ class LDSR: im_og = im_og.resize((width_downsampled_pre, height_downsampled_pre), Image.LANCZOS) else: print(f"Down sample rate is 1 from {target_scale} / 4 (Not downsampling)") - + # pad width and height to multiples of 64, pads with the edge values of image to avoid artifacts pad_w, pad_h = np.max(((2, 2), np.ceil(np.array(im_og.size) / 64).astype(int)), axis=0) * 64 - im_og.size im_padded = Image.fromarray(np.pad(np.array(im_og), ((0, pad_h), (0, pad_w), (0, 0)), mode='edge')) - + logs = self.run(model["model"], im_padded, diffusion_steps, eta) sample = logs["sample"] diff --git a/extensions-builtin/LDSR/sd_hijack_ddpm_v1.py b/extensions-builtin/LDSR/sd_hijack_ddpm_v1.py index 57c02d12..631a08ef 100644 --- a/extensions-builtin/LDSR/sd_hijack_ddpm_v1.py +++ b/extensions-builtin/LDSR/sd_hijack_ddpm_v1.py @@ -460,7 +460,7 @@ class LatentDiffusionV1(DDPMV1): self.instantiate_cond_stage(cond_stage_config) self.cond_stage_forward = cond_stage_forward self.clip_denoised = False - self.bbox_tokenizer = None + self.bbox_tokenizer = None self.restarted_from_ckpt = False if ckpt_path is not None: @@ -792,7 +792,7 @@ class LatentDiffusionV1(DDPMV1): z = z.view((z.shape[0], -1, ks[0], ks[1], z.shape[-1])) # (bn, nc, ks[0], ks[1], L ) # 2. apply model loop over last dim - if isinstance(self.first_stage_model, VQModelInterface): + if isinstance(self.first_stage_model, VQModelInterface): output_list = [self.first_stage_model.decode(z[:, :, :, :, i], force_not_quantize=predict_cids or force_not_quantize) for i in range(z.shape[-1])] @@ -890,7 +890,7 @@ class LatentDiffusionV1(DDPMV1): if hasattr(self, "split_input_params"): assert len(cond) == 1 # todo can only deal with one conditioning atm - assert not return_ids + assert not return_ids ks = self.split_input_params["ks"] # eg. (128, 128) stride = self.split_input_params["stride"] # eg. (64, 64) diff --git a/extensions-builtin/ScuNET/scunet_model_arch.py b/extensions-builtin/ScuNET/scunet_model_arch.py index 8028918a..b51a8806 100644 --- a/extensions-builtin/ScuNET/scunet_model_arch.py +++ b/extensions-builtin/ScuNET/scunet_model_arch.py @@ -265,4 +265,4 @@ class SCUNet(nn.Module): nn.init.constant_(m.bias, 0) elif isinstance(m, nn.LayerNorm): nn.init.constant_(m.bias, 0) - nn.init.constant_(m.weight, 1.0) \ No newline at end of file + nn.init.constant_(m.weight, 1.0) diff --git a/extensions-builtin/SwinIR/scripts/swinir_model.py b/extensions-builtin/SwinIR/scripts/swinir_model.py index 55dd94ab..0ba50487 100644 --- a/extensions-builtin/SwinIR/scripts/swinir_model.py +++ b/extensions-builtin/SwinIR/scripts/swinir_model.py @@ -150,7 +150,7 @@ def inference(img, model, tile, tile_overlap, window_size, scale): for w_idx in w_idx_list: if state.interrupted or state.skipped: break - + in_patch = img[..., h_idx: h_idx + tile, w_idx: w_idx + tile] out_patch = model(in_patch) out_patch_mask = torch.ones_like(out_patch) diff --git a/extensions-builtin/SwinIR/swinir_model_arch.py b/extensions-builtin/SwinIR/swinir_model_arch.py index 73e37cfa..93b93274 100644 --- a/extensions-builtin/SwinIR/swinir_model_arch.py +++ b/extensions-builtin/SwinIR/swinir_model_arch.py @@ -805,7 +805,7 @@ class SwinIR(nn.Module): def forward(self, x): H, W = x.shape[2:] x = self.check_image_size(x) - + self.mean = self.mean.type_as(x) x = (x - self.mean) * self.img_range diff --git a/extensions-builtin/SwinIR/swinir_model_arch_v2.py b/extensions-builtin/SwinIR/swinir_model_arch_v2.py index 3ca9be78..dad22cca 100644 --- a/extensions-builtin/SwinIR/swinir_model_arch_v2.py +++ b/extensions-builtin/SwinIR/swinir_model_arch_v2.py @@ -241,7 +241,7 @@ class SwinTransformerBlock(nn.Module): attn_mask = None self.register_buffer("attn_mask", attn_mask) - + def calculate_mask(self, x_size): # calculate attention mask for SW-MSA H, W = x_size @@ -263,7 +263,7 @@ class SwinTransformerBlock(nn.Module): attn_mask = mask_windows.unsqueeze(1) - mask_windows.unsqueeze(2) attn_mask = attn_mask.masked_fill(attn_mask != 0, float(-100.0)).masked_fill(attn_mask == 0, float(0.0)) - return attn_mask + return attn_mask def forward(self, x, x_size): H, W = x_size @@ -288,7 +288,7 @@ class SwinTransformerBlock(nn.Module): attn_windows = self.attn(x_windows, mask=self.attn_mask) # nW*B, window_size*window_size, C else: attn_windows = self.attn(x_windows, mask=self.calculate_mask(x_size).to(x.device)) - + # merge windows attn_windows = attn_windows.view(-1, self.window_size, self.window_size, C) shifted_x = window_reverse(attn_windows, self.window_size, H, W) # B H' W' C @@ -369,7 +369,7 @@ class PatchMerging(nn.Module): H, W = self.input_resolution flops = (H // 2) * (W // 2) * 4 * self.dim * 2 * self.dim flops += H * W * self.dim // 2 - return flops + return flops class BasicLayer(nn.Module): """ A basic Swin Transformer layer for one stage. @@ -447,7 +447,7 @@ class BasicLayer(nn.Module): nn.init.constant_(blk.norm1.weight, 0) nn.init.constant_(blk.norm2.bias, 0) nn.init.constant_(blk.norm2.weight, 0) - + class PatchEmbed(nn.Module): r""" Image to Patch Embedding Args: @@ -492,7 +492,7 @@ class PatchEmbed(nn.Module): flops = Ho * Wo * self.embed_dim * self.in_chans * (self.patch_size[0] * self.patch_size[1]) if self.norm is not None: flops += Ho * Wo * self.embed_dim - return flops + return flops class RSTB(nn.Module): """Residual Swin Transformer Block (RSTB). @@ -531,7 +531,7 @@ class RSTB(nn.Module): num_heads=num_heads, window_size=window_size, mlp_ratio=mlp_ratio, - qkv_bias=qkv_bias, + qkv_bias=qkv_bias, drop=drop, attn_drop=attn_drop, drop_path=drop_path, norm_layer=norm_layer, @@ -622,7 +622,7 @@ class Upsample(nn.Sequential): else: raise ValueError(f'scale {scale} is not supported. ' 'Supported scales: 2^n and 3.') super(Upsample, self).__init__(*m) - + class Upsample_hf(nn.Sequential): """Upsample module. @@ -642,7 +642,7 @@ class Upsample_hf(nn.Sequential): m.append(nn.PixelShuffle(3)) else: raise ValueError(f'scale {scale} is not supported. ' 'Supported scales: 2^n and 3.') - super(Upsample_hf, self).__init__(*m) + super(Upsample_hf, self).__init__(*m) class UpsampleOneStep(nn.Sequential): @@ -667,8 +667,8 @@ class UpsampleOneStep(nn.Sequential): H, W = self.input_resolution flops = H * W * self.num_feat * 3 * 9 return flops - - + + class Swin2SR(nn.Module): r""" Swin2SR @@ -699,7 +699,7 @@ class Swin2SR(nn.Module): def __init__(self, img_size=64, patch_size=1, in_chans=3, embed_dim=96, depths=(6, 6, 6, 6), num_heads=(6, 6, 6, 6), - window_size=7, mlp_ratio=4., qkv_bias=True, + window_size=7, mlp_ratio=4., qkv_bias=True, drop_rate=0., attn_drop_rate=0., drop_path_rate=0.1, norm_layer=nn.LayerNorm, ape=False, patch_norm=True, use_checkpoint=False, upscale=2, img_range=1., upsampler='', resi_connection='1conv', @@ -764,7 +764,7 @@ class Swin2SR(nn.Module): num_heads=num_heads[i_layer], window_size=window_size, mlp_ratio=self.mlp_ratio, - qkv_bias=qkv_bias, + qkv_bias=qkv_bias, drop=drop_rate, attn_drop=attn_drop_rate, drop_path=dpr[sum(depths[:i_layer]):sum(depths[:i_layer + 1])], # no impact on SR results norm_layer=norm_layer, @@ -776,7 +776,7 @@ class Swin2SR(nn.Module): ) self.layers.append(layer) - + if self.upsampler == 'pixelshuffle_hf': self.layers_hf = nn.ModuleList() for i_layer in range(self.num_layers): @@ -787,7 +787,7 @@ class Swin2SR(nn.Module): num_heads=num_heads[i_layer], window_size=window_size, mlp_ratio=self.mlp_ratio, - qkv_bias=qkv_bias, + qkv_bias=qkv_bias, drop=drop_rate, attn_drop=attn_drop_rate, drop_path=dpr[sum(depths[:i_layer]):sum(depths[:i_layer + 1])], # no impact on SR results norm_layer=norm_layer, @@ -799,7 +799,7 @@ class Swin2SR(nn.Module): ) self.layers_hf.append(layer) - + self.norm = norm_layer(self.num_features) # build the last conv layer in deep feature extraction @@ -829,10 +829,10 @@ class Swin2SR(nn.Module): self.conv_aux = nn.Conv2d(num_feat, num_out_ch, 3, 1, 1) self.conv_after_aux = nn.Sequential( nn.Conv2d(3, num_feat, 3, 1, 1), - nn.LeakyReLU(inplace=True)) + nn.LeakyReLU(inplace=True)) self.upsample = Upsample(upscale, num_feat) self.conv_last = nn.Conv2d(num_feat, num_out_ch, 3, 1, 1) - + elif self.upsampler == 'pixelshuffle_hf': self.conv_before_upsample = nn.Sequential(nn.Conv2d(embed_dim, num_feat, 3, 1, 1), nn.LeakyReLU(inplace=True)) @@ -846,7 +846,7 @@ class Swin2SR(nn.Module): nn.Conv2d(embed_dim, num_feat, 3, 1, 1), nn.LeakyReLU(inplace=True)) self.conv_last_hf = nn.Conv2d(num_feat, num_out_ch, 3, 1, 1) - + elif self.upsampler == 'pixelshuffledirect': # for lightweight SR (to save parameters) self.upsample = UpsampleOneStep(upscale, embed_dim, num_out_ch, @@ -905,7 +905,7 @@ class Swin2SR(nn.Module): x = self.patch_unembed(x, x_size) return x - + def forward_features_hf(self, x): x_size = (x.shape[2], x.shape[3]) x = self.patch_embed(x) @@ -919,7 +919,7 @@ class Swin2SR(nn.Module): x = self.norm(x) # B L C x = self.patch_unembed(x, x_size) - return x + return x def forward(self, x): H, W = x.shape[2:] @@ -951,7 +951,7 @@ class Swin2SR(nn.Module): x = self.conv_after_body(self.forward_features(x)) + x x_before = self.conv_before_upsample(x) x_out = self.conv_last(self.upsample(x_before)) - + x_hf = self.conv_first_hf(x_before) x_hf = self.conv_after_body_hf(self.forward_features_hf(x_hf)) + x_hf x_hf = self.conv_before_upsample_hf(x_hf) @@ -977,15 +977,15 @@ class Swin2SR(nn.Module): x_first = self.conv_first(x) res = self.conv_after_body(self.forward_features(x_first)) + x_first x = x + self.conv_last(res) - + x = x / self.img_range + self.mean if self.upsampler == "pixelshuffle_aux": return x[:, :, :H*self.upscale, :W*self.upscale], aux - + elif self.upsampler == "pixelshuffle_hf": x_out = x_out / self.img_range + self.mean return x_out[:, :, :H*self.upscale, :W*self.upscale], x[:, :, :H*self.upscale, :W*self.upscale], x_hf[:, :, :H*self.upscale, :W*self.upscale] - + else: return x[:, :, :H*self.upscale, :W*self.upscale] @@ -1014,4 +1014,4 @@ if __name__ == '__main__': x = torch.randn((1, 3, height, width)) x = model(x) - print(x.shape) \ No newline at end of file + print(x.shape) diff --git a/launch.py b/launch.py index 670af87c..62b33f14 100644 --- a/launch.py +++ b/launch.py @@ -327,7 +327,7 @@ def prepare_environment(): if args.update_all_extensions: git_pull_recursive(extensions_dir) - + if "--exit" in sys.argv: print("Exiting because of --exit argument") exit(0) diff --git a/modules/api/api.py b/modules/api/api.py index 594fa655..165985c3 100644 --- a/modules/api/api.py +++ b/modules/api/api.py @@ -227,7 +227,7 @@ class Api: script_idx = script_name_to_index(script_name, script_runner.selectable_scripts) script = script_runner.selectable_scripts[script_idx] return script, script_idx - + def get_scripts_list(self): t2ilist = [str(title.lower()) for title in scripts.scripts_txt2img.titles] i2ilist = [str(title.lower()) for title in scripts.scripts_img2img.titles] @@ -237,7 +237,7 @@ class Api: def get_script(self, script_name, script_runner): if script_name is None or script_name == "": return None, None - + script_idx = script_name_to_index(script_name, script_runner.scripts) return script_runner.scripts[script_idx] diff --git a/modules/api/models.py b/modules/api/models.py index 4d291076..006ccdb7 100644 --- a/modules/api/models.py +++ b/modules/api/models.py @@ -289,4 +289,4 @@ class MemoryResponse(BaseModel): class ScriptsList(BaseModel): txt2img: list = Field(default=None,title="Txt2img", description="Titles of scripts (txt2img)") - img2img: list = Field(default=None,title="Img2img", description="Titles of scripts (img2img)") \ No newline at end of file + img2img: list = Field(default=None,title="Img2img", description="Titles of scripts (img2img)") diff --git a/modules/cmd_args.py b/modules/cmd_args.py index e01ca655..f4a4ab36 100644 --- a/modules/cmd_args.py +++ b/modules/cmd_args.py @@ -102,4 +102,4 @@ parser.add_argument("--no-gradio-queue", action='store_true', help="Disables gra parser.add_argument("--skip-version-check", action='store_true', help="Do not check versions of torch and xformers") parser.add_argument("--no-hashing", action='store_true', help="disable sha256 hashing of checkpoints to help loading performance", default=False) parser.add_argument("--no-download-sd-model", action='store_true', help="don't download SD1.5 model even if no model is found in --ckpt-dir", default=False) -parser.add_argument('--subpath', type=str, help='customize the subpath for gradio, use with reverse proxy') \ No newline at end of file +parser.add_argument('--subpath', type=str, help='customize the subpath for gradio, use with reverse proxy') diff --git a/modules/codeformer/codeformer_arch.py b/modules/codeformer/codeformer_arch.py index 45c70f84..12db6814 100644 --- a/modules/codeformer/codeformer_arch.py +++ b/modules/codeformer/codeformer_arch.py @@ -119,7 +119,7 @@ class TransformerSALayer(nn.Module): tgt_mask: Optional[Tensor] = None, tgt_key_padding_mask: Optional[Tensor] = None, query_pos: Optional[Tensor] = None): - + # self attention tgt2 = self.norm1(tgt) q = k = self.with_pos_embed(tgt2, query_pos) @@ -159,7 +159,7 @@ class Fuse_sft_block(nn.Module): @ARCH_REGISTRY.register() class CodeFormer(VQAutoEncoder): - def __init__(self, dim_embd=512, n_head=8, n_layers=9, + def __init__(self, dim_embd=512, n_head=8, n_layers=9, codebook_size=1024, latent_size=256, connect_list=('32', '64', '128', '256'), fix_modules=('quantize', 'generator')): @@ -179,14 +179,14 @@ class CodeFormer(VQAutoEncoder): self.feat_emb = nn.Linear(256, self.dim_embd) # transformer - self.ft_layers = nn.Sequential(*[TransformerSALayer(embed_dim=dim_embd, nhead=n_head, dim_mlp=self.dim_mlp, dropout=0.0) + self.ft_layers = nn.Sequential(*[TransformerSALayer(embed_dim=dim_embd, nhead=n_head, dim_mlp=self.dim_mlp, dropout=0.0) for _ in range(self.n_layers)]) # logits_predict head self.idx_pred_layer = nn.Sequential( nn.LayerNorm(dim_embd), nn.Linear(dim_embd, codebook_size, bias=False)) - + self.channels = { '16': 512, '32': 256, @@ -221,7 +221,7 @@ class CodeFormer(VQAutoEncoder): enc_feat_dict = {} out_list = [self.fuse_encoder_block[f_size] for f_size in self.connect_list] for i, block in enumerate(self.encoder.blocks): - x = block(x) + x = block(x) if i in out_list: enc_feat_dict[str(x.shape[-1])] = x.clone() @@ -266,11 +266,11 @@ class CodeFormer(VQAutoEncoder): fuse_list = [self.fuse_generator_block[f_size] for f_size in self.connect_list] for i, block in enumerate(self.generator.blocks): - x = block(x) + x = block(x) if i in fuse_list: # fuse after i-th block f_size = str(x.shape[-1]) if w>0: x = self.fuse_convs_dict[f_size](enc_feat_dict[f_size].detach(), x, w) out = x # logits doesn't need softmax before cross_entropy loss - return out, logits, lq_feat \ No newline at end of file + return out, logits, lq_feat diff --git a/modules/codeformer/vqgan_arch.py b/modules/codeformer/vqgan_arch.py index b24a0394..09ee6660 100644 --- a/modules/codeformer/vqgan_arch.py +++ b/modules/codeformer/vqgan_arch.py @@ -13,7 +13,7 @@ from basicsr.utils.registry import ARCH_REGISTRY def normalize(in_channels): return torch.nn.GroupNorm(num_groups=32, num_channels=in_channels, eps=1e-6, affine=True) - + @torch.jit.script def swish(x): @@ -210,15 +210,15 @@ class AttnBlock(nn.Module): # compute attention b, c, h, w = q.shape q = q.reshape(b, c, h*w) - q = q.permute(0, 2, 1) + q = q.permute(0, 2, 1) k = k.reshape(b, c, h*w) - w_ = torch.bmm(q, k) + w_ = torch.bmm(q, k) w_ = w_ * (int(c)**(-0.5)) w_ = F.softmax(w_, dim=2) # attend to values v = v.reshape(b, c, h*w) - w_ = w_.permute(0, 2, 1) + w_ = w_.permute(0, 2, 1) h_ = torch.bmm(v, w_) h_ = h_.reshape(b, c, h, w) @@ -270,18 +270,18 @@ class Encoder(nn.Module): def forward(self, x): for block in self.blocks: x = block(x) - + return x class Generator(nn.Module): def __init__(self, nf, emb_dim, ch_mult, res_blocks, img_size, attn_resolutions): super().__init__() - self.nf = nf - self.ch_mult = ch_mult + self.nf = nf + self.ch_mult = ch_mult self.num_resolutions = len(self.ch_mult) self.num_res_blocks = res_blocks - self.resolution = img_size + self.resolution = img_size self.attn_resolutions = attn_resolutions self.in_channels = emb_dim self.out_channels = 3 @@ -315,24 +315,24 @@ class Generator(nn.Module): blocks.append(nn.Conv2d(block_in_ch, self.out_channels, kernel_size=3, stride=1, padding=1)) self.blocks = nn.ModuleList(blocks) - + def forward(self, x): for block in self.blocks: x = block(x) - + return x - + @ARCH_REGISTRY.register() class VQAutoEncoder(nn.Module): def __init__(self, img_size, nf, ch_mult, quantizer="nearest", res_blocks=2, attn_resolutions=None, codebook_size=1024, emb_dim=256, beta=0.25, gumbel_straight_through=False, gumbel_kl_weight=1e-8, model_path=None): super().__init__() logger = get_root_logger() - self.in_channels = 3 - self.nf = nf - self.n_blocks = res_blocks + self.in_channels = 3 + self.nf = nf + self.n_blocks = res_blocks self.codebook_size = codebook_size self.embed_dim = emb_dim self.ch_mult = ch_mult @@ -363,11 +363,11 @@ class VQAutoEncoder(nn.Module): self.kl_weight ) self.generator = Generator( - self.nf, + self.nf, self.embed_dim, - self.ch_mult, - self.n_blocks, - self.resolution, + self.ch_mult, + self.n_blocks, + self.resolution, self.attn_resolutions ) @@ -432,4 +432,4 @@ class VQGANDiscriminator(nn.Module): raise ValueError('Wrong params!') def forward(self, x): - return self.main(x) \ No newline at end of file + return self.main(x) diff --git a/modules/esrgan_model_arch.py b/modules/esrgan_model_arch.py index 4de9dd8d..2b9888ba 100644 --- a/modules/esrgan_model_arch.py +++ b/modules/esrgan_model_arch.py @@ -105,7 +105,7 @@ class ResidualDenseBlock_5C(nn.Module): Modified options that can be used: - "Partial Convolution based Padding" arXiv:1811.11718 - "Spectral normalization" arXiv:1802.05957 - - "ICASSP 2020 - ESRGAN+ : Further Improving ESRGAN" N. C. + - "ICASSP 2020 - ESRGAN+ : Further Improving ESRGAN" N. C. {Rakotonirina} and A. {Rasoanaivo} """ @@ -170,7 +170,7 @@ class GaussianNoise(nn.Module): scale = self.sigma * x.detach() if self.is_relative_detach else self.sigma * x sampled_noise = self.noise.repeat(*x.size()).normal_() * scale x = x + sampled_noise - return x + return x def conv1x1(in_planes, out_planes, stride=1): return nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=stride, bias=False) diff --git a/modules/extras.py b/modules/extras.py index eb4f0b42..bdf9b3b7 100644 --- a/modules/extras.py +++ b/modules/extras.py @@ -199,7 +199,7 @@ def run_modelmerger(id_task, primary_model_name, secondary_model_name, tertiary_ result_is_inpainting_model = True else: theta_0[key] = theta_func2(a, b, multiplier) - + theta_0[key] = to_half(theta_0[key], save_as_half) shared.state.sampling_step += 1 diff --git a/modules/hypernetworks/hypernetwork.py b/modules/hypernetworks/hypernetwork.py index 38ef074f..570b5603 100644 --- a/modules/hypernetworks/hypernetwork.py +++ b/modules/hypernetworks/hypernetwork.py @@ -540,7 +540,7 @@ def train_hypernetwork(id_task, hypernetwork_name, learn_rate, batch_size, gradi return hypernetwork, filename scheduler = LearnRateScheduler(learn_rate, steps, initial_step) - + clip_grad = torch.nn.utils.clip_grad_value_ if clip_grad_mode == "value" else torch.nn.utils.clip_grad_norm_ if clip_grad_mode == "norm" else None if clip_grad: clip_grad_sched = LearnRateScheduler(clip_grad_value, steps, initial_step, verbose=False) @@ -593,7 +593,7 @@ def train_hypernetwork(id_task, hypernetwork_name, learn_rate, batch_size, gradi print(e) scaler = torch.cuda.amp.GradScaler() - + batch_size = ds.batch_size gradient_step = ds.gradient_step # n steps = batch_size * gradient_step * n image processed @@ -636,7 +636,7 @@ def train_hypernetwork(id_task, hypernetwork_name, learn_rate, batch_size, gradi if clip_grad: clip_grad_sched.step(hypernetwork.step) - + with devices.autocast(): x = batch.latent_sample.to(devices.device, non_blocking=pin_memory) if use_weight: @@ -657,14 +657,14 @@ def train_hypernetwork(id_task, hypernetwork_name, learn_rate, batch_size, gradi _loss_step += loss.item() scaler.scale(loss).backward() - + # go back until we reach gradient accumulation steps if (j + 1) % gradient_step != 0: continue loss_logging.append(_loss_step) if clip_grad: clip_grad(weights, clip_grad_sched.learn_rate) - + scaler.step(optimizer) scaler.update() hypernetwork.step += 1 @@ -674,7 +674,7 @@ def train_hypernetwork(id_task, hypernetwork_name, learn_rate, batch_size, gradi _loss_step = 0 steps_done = hypernetwork.step + 1 - + epoch_num = hypernetwork.step // steps_per_epoch epoch_step = hypernetwork.step % steps_per_epoch diff --git a/modules/images.py b/modules/images.py index 3b8b62d9..b2de3662 100644 --- a/modules/images.py +++ b/modules/images.py @@ -367,7 +367,7 @@ class FilenameGenerator: self.seed = seed self.prompt = prompt self.image = image - + def hasprompt(self, *args): lower = self.prompt.lower() if self.p is None or self.prompt is None: diff --git a/modules/mac_specific.py b/modules/mac_specific.py index 5c2f92a1..d74c6b95 100644 --- a/modules/mac_specific.py +++ b/modules/mac_specific.py @@ -42,7 +42,7 @@ if has_mps: # MPS workaround for https://github.com/pytorch/pytorch/issues/79383 CondFunc('torch.Tensor.to', lambda orig_func, self, *args, **kwargs: orig_func(self.contiguous(), *args, **kwargs), lambda _, self, *args, **kwargs: self.device.type != 'mps' and (args and isinstance(args[0], torch.device) and args[0].type == 'mps' or isinstance(kwargs.get('device'), torch.device) and kwargs['device'].type == 'mps')) - # MPS workaround for https://github.com/pytorch/pytorch/issues/80800 + # MPS workaround for https://github.com/pytorch/pytorch/issues/80800 CondFunc('torch.nn.functional.layer_norm', lambda orig_func, *args, **kwargs: orig_func(*([args[0].contiguous()] + list(args[1:])), **kwargs), lambda _, *args, **kwargs: args and isinstance(args[0], torch.Tensor) and args[0].device.type == 'mps') # MPS workaround for https://github.com/pytorch/pytorch/issues/90532 @@ -60,4 +60,4 @@ if has_mps: # MPS workaround for https://github.com/pytorch/pytorch/issues/92311 if platform.processor() == 'i386': for funcName in ['torch.argmax', 'torch.Tensor.argmax']: - CondFunc(funcName, lambda _, input, *args, **kwargs: torch.max(input.float() if input.dtype == torch.int64 else input, *args, **kwargs)[1], lambda _, input, *args, **kwargs: input.device.type == 'mps') \ No newline at end of file + CondFunc(funcName, lambda _, input, *args, **kwargs: torch.max(input.float() if input.dtype == torch.int64 else input, *args, **kwargs)[1], lambda _, input, *args, **kwargs: input.device.type == 'mps') diff --git a/modules/masking.py b/modules/masking.py index a5c4d2da..be9f84c7 100644 --- a/modules/masking.py +++ b/modules/masking.py @@ -4,7 +4,7 @@ from PIL import Image, ImageFilter, ImageOps def get_crop_region(mask, pad=0): """finds a rectangular region that contains all masked ares in an image. Returns (x1, y1, x2, y2) coordinates of the rectangle. For example, if a user has painted the top-right part of a 512x512 image", the result may be (256, 0, 512, 256)""" - + h, w = mask.shape crop_left = 0 diff --git a/modules/ngrok.py b/modules/ngrok.py index 7a7b4b26..67a74e85 100644 --- a/modules/ngrok.py +++ b/modules/ngrok.py @@ -13,7 +13,7 @@ def connect(token, port, region): config = conf.PyngrokConfig( auth_token=token, region=region ) - + # Guard for existing tunnels existing = ngrok.get_tunnels(pyngrok_config=config) if existing: @@ -24,7 +24,7 @@ def connect(token, port, region): print(f'ngrok has already been connected to localhost:{port}! URL: {public_url}\n' 'You can use this link after the launch is complete.') return - + try: if account is None: public_url = ngrok.connect(port, pyngrok_config=config, bind_tls=True).public_url diff --git a/modules/processing.py b/modules/processing.py index c3932d6b..f902b9df 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -164,7 +164,7 @@ class StableDiffusionProcessing: self.all_subseeds = None self.iteration = 0 self.is_hr_pass = False - + @property def sd_model(self): diff --git a/modules/script_callbacks.py b/modules/script_callbacks.py index 17109732..7d9dd736 100644 --- a/modules/script_callbacks.py +++ b/modules/script_callbacks.py @@ -32,22 +32,22 @@ class CFGDenoiserParams: def __init__(self, x, image_cond, sigma, sampling_step, total_sampling_steps, text_cond, text_uncond): self.x = x """Latent image representation in the process of being denoised""" - + self.image_cond = image_cond """Conditioning image""" - + self.sigma = sigma """Current sigma noise step value""" - + self.sampling_step = sampling_step """Current Sampling step number""" - + self.total_sampling_steps = total_sampling_steps """Total number of sampling steps planned""" - + self.text_cond = text_cond """ Encoder hidden states of text conditioning from prompt""" - + self.text_uncond = text_uncond """ Encoder hidden states of text conditioning from negative prompt""" @@ -240,7 +240,7 @@ def add_callback(callbacks, fun): callbacks.append(ScriptCallback(filename, fun)) - + def remove_current_script_callbacks(): stack = [x for x in inspect.stack() if x.filename != __file__] filename = stack[0].filename if len(stack) > 0 else 'unknown file' diff --git a/modules/sd_hijack.py b/modules/sd_hijack.py index e374aeb8..7e50f1ab 100644 --- a/modules/sd_hijack.py +++ b/modules/sd_hijack.py @@ -34,7 +34,7 @@ def apply_optimizations(): ldm.modules.diffusionmodules.model.nonlinearity = silu ldm.modules.diffusionmodules.openaimodel.th = sd_hijack_unet.th - + optimization_method = None can_use_sdp = hasattr(torch.nn.functional, "scaled_dot_product_attention") and callable(torch.nn.functional.scaled_dot_product_attention) # not everyone has torch 2.x to use sdp @@ -92,12 +92,12 @@ def fix_checkpoint(): def weighted_loss(sd_model, pred, target, mean=True): #Calculate the weight normally, but ignore the mean loss = sd_model._old_get_loss(pred, target, mean=False) - + #Check if we have weights available weight = getattr(sd_model, '_custom_loss_weight', None) if weight is not None: loss *= weight - + #Return the loss, as mean if specified return loss.mean() if mean else loss @@ -105,7 +105,7 @@ def weighted_forward(sd_model, x, c, w, *args, **kwargs): try: #Temporarily append weights to a place accessible during loss calc sd_model._custom_loss_weight = w - + #Replace 'get_loss' with a weight-aware one. Otherwise we need to reimplement 'forward' completely #Keep 'get_loss', but don't overwrite the previous old_get_loss if it's already set if not hasattr(sd_model, '_old_get_loss'): @@ -120,7 +120,7 @@ def weighted_forward(sd_model, x, c, w, *args, **kwargs): del sd_model._custom_loss_weight except AttributeError: pass - + #If we have an old loss function, reset the loss function to the original one if hasattr(sd_model, '_old_get_loss'): sd_model.get_loss = sd_model._old_get_loss @@ -184,7 +184,7 @@ class StableDiffusionModelHijack: def undo_hijack(self, m): if type(m.cond_stage_model) == xlmr.BertSeriesModelWithTransformation: - m.cond_stage_model = m.cond_stage_model.wrapped + m.cond_stage_model = m.cond_stage_model.wrapped elif type(m.cond_stage_model) == sd_hijack_clip.FrozenCLIPEmbedderWithCustomWords: m.cond_stage_model = m.cond_stage_model.wrapped diff --git a/modules/sd_hijack_optimizations.py b/modules/sd_hijack_optimizations.py index a174bbe1..f00fe55c 100644 --- a/modules/sd_hijack_optimizations.py +++ b/modules/sd_hijack_optimizations.py @@ -62,10 +62,10 @@ def split_cross_attention_forward_v1(self, x, context=None, mask=None): end = i + 2 s1 = einsum('b i d, b j d -> b i j', q[i:end], k[i:end]) s1 *= self.scale - + s2 = s1.softmax(dim=-1) del s1 - + r1[i:end] = einsum('b i j, b j d -> b i d', s2, v[i:end]) del s2 del q, k, v @@ -95,43 +95,43 @@ def split_cross_attention_forward(self, x, context=None, mask=None): with devices.without_autocast(disable=not shared.opts.upcast_attn): k_in = k_in * self.scale - + del context, x - + q, k, v = (rearrange(t, 'b n (h d) -> (b h) n d', h=h) for t in (q_in, k_in, v_in)) del q_in, k_in, v_in - + r1 = torch.zeros(q.shape[0], q.shape[1], v.shape[2], device=q.device, dtype=q.dtype) - + mem_free_total = get_available_vram() - + gb = 1024 ** 3 tensor_size = q.shape[0] * q.shape[1] * k.shape[1] * q.element_size() modifier = 3 if q.element_size() == 2 else 2.5 mem_required = tensor_size * modifier steps = 1 - + if mem_required > mem_free_total: steps = 2 ** (math.ceil(math.log(mem_required / mem_free_total, 2))) # print(f"Expected tensor size:{tensor_size/gb:0.1f}GB, cuda free:{mem_free_cuda/gb:0.1f}GB " # f"torch free:{mem_free_torch/gb:0.1f} total:{mem_free_total/gb:0.1f} steps:{steps}") - + if steps > 64: max_res = math.floor(math.sqrt(math.sqrt(mem_free_total / 2.5)) / 8) * 64 raise RuntimeError(f'Not enough memory, use lower resolution (max approx. {max_res}x{max_res}). ' f'Need: {mem_required / 64 / gb:0.1f}GB free, Have:{mem_free_total / gb:0.1f}GB free') - + slice_size = q.shape[1] // steps if (q.shape[1] % steps) == 0 else q.shape[1] for i in range(0, q.shape[1], slice_size): end = i + slice_size s1 = einsum('b i d, b j d -> b i j', q[:, i:end], k) - + s2 = s1.softmax(dim=-1, dtype=q.dtype) del s1 - + r1[:, i:end] = einsum('b i j, b j d -> b i d', s2, v) del s2 - + del q, k, v r1 = r1.to(dtype) @@ -228,7 +228,7 @@ def split_cross_attention_forward_invokeAI(self, x, context=None, mask=None): with devices.without_autocast(disable=not shared.opts.upcast_attn): k = k * self.scale - + q, k, v = (rearrange(t, 'b n (h d) -> (b h) n d', h=h) for t in (q, k, v)) r = einsum_op(q, k, v) r = r.to(dtype) @@ -369,7 +369,7 @@ def scaled_dot_product_attention_forward(self, x, context=None, mask=None): q = q_in.view(batch_size, -1, h, head_dim).transpose(1, 2) k = k_in.view(batch_size, -1, h, head_dim).transpose(1, 2) v = v_in.view(batch_size, -1, h, head_dim).transpose(1, 2) - + del q_in, k_in, v_in dtype = q.dtype @@ -451,7 +451,7 @@ def cross_attention_attnblock_forward(self, x): h3 += x return h3 - + def xformers_attnblock_forward(self, x): try: h_ = x diff --git a/modules/sd_models.py b/modules/sd_models.py index d1e946a5..3316d021 100644 --- a/modules/sd_models.py +++ b/modules/sd_models.py @@ -165,7 +165,7 @@ def model_hash(filename): def select_checkpoint(): model_checkpoint = shared.opts.sd_model_checkpoint - + checkpoint_info = checkpoint_alisases.get(model_checkpoint, None) if checkpoint_info is not None: return checkpoint_info @@ -372,7 +372,7 @@ def enable_midas_autodownload(): if not os.path.exists(path): if not os.path.exists(midas_path): mkdir(midas_path) - + print(f"Downloading midas model weights for {model_type} to {path}") request.urlretrieve(midas_urls[model_type], path) print(f"{model_type} downloaded") diff --git a/modules/sd_samplers_kdiffusion.py b/modules/sd_samplers_kdiffusion.py index 2f733cf5..e9e41818 100644 --- a/modules/sd_samplers_kdiffusion.py +++ b/modules/sd_samplers_kdiffusion.py @@ -93,10 +93,10 @@ class CFGDenoiser(torch.nn.Module): if shared.sd_model.model.conditioning_key == "crossattn-adm": image_uncond = torch.zeros_like(image_cond) - make_condition_dict = lambda c_crossattn, c_adm: {"c_crossattn": c_crossattn, "c_adm": c_adm} + make_condition_dict = lambda c_crossattn, c_adm: {"c_crossattn": c_crossattn, "c_adm": c_adm} else: image_uncond = image_cond - make_condition_dict = lambda c_crossattn, c_concat: {"c_crossattn": c_crossattn, "c_concat": [c_concat]} + make_condition_dict = lambda c_crossattn, c_concat: {"c_crossattn": c_crossattn, "c_concat": [c_concat]} if not is_edit_model: x_in = torch.cat([torch.stack([x[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [x]) @@ -316,7 +316,7 @@ class KDiffusionSampler: sigma_sched = sigmas[steps - t_enc - 1:] xi = x + noise * sigma_sched[0] - + extra_params_kwargs = self.initialize(p) parameters = inspect.signature(self.func).parameters @@ -339,9 +339,9 @@ class KDiffusionSampler: self.model_wrap_cfg.init_latent = x self.last_latent = x extra_args={ - 'cond': conditioning, - 'image_cond': image_conditioning, - 'uncond': unconditional_conditioning, + 'cond': conditioning, + 'image_cond': image_conditioning, + 'uncond': unconditional_conditioning, 'cond_scale': p.cfg_scale, 's_min_uncond': self.s_min_uncond } @@ -374,9 +374,9 @@ class KDiffusionSampler: self.last_latent = x samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args={ - 'cond': conditioning, - 'image_cond': image_conditioning, - 'uncond': unconditional_conditioning, + 'cond': conditioning, + 'image_cond': image_conditioning, + 'uncond': unconditional_conditioning, 'cond_scale': p.cfg_scale, 's_min_uncond': self.s_min_uncond }, disable=False, callback=self.callback_state, **extra_params_kwargs)) diff --git a/modules/sub_quadratic_attention.py b/modules/sub_quadratic_attention.py index cc38debd..497568eb 100644 --- a/modules/sub_quadratic_attention.py +++ b/modules/sub_quadratic_attention.py @@ -179,7 +179,7 @@ def efficient_dot_product_attention( chunk_idx, min(query_chunk_size, q_tokens) ) - + summarize_chunk: SummarizeChunk = partial(_summarize_chunk, scale=scale) summarize_chunk: SummarizeChunk = partial(checkpoint, summarize_chunk) if use_checkpoint else summarize_chunk compute_query_chunk_attn: ComputeQueryChunkAttn = partial( diff --git a/modules/textual_inversion/dataset.py b/modules/textual_inversion/dataset.py index 41610e03..b9621fc9 100644 --- a/modules/textual_inversion/dataset.py +++ b/modules/textual_inversion/dataset.py @@ -118,7 +118,7 @@ class PersonalizedBase(Dataset): weight = torch.ones(latent_sample.shape) else: weight = None - + if latent_sampling_method == "random": entry = DatasetEntry(filename=path, filename_text=filename_text, latent_dist=latent_dist, weight=weight) else: @@ -243,4 +243,4 @@ class BatchLoaderRandom(BatchLoader): return self def collate_wrapper_random(batch): - return BatchLoaderRandom(batch) \ No newline at end of file + return BatchLoaderRandom(batch) diff --git a/modules/textual_inversion/preprocess.py b/modules/textual_inversion/preprocess.py index d0cad09e..a009d8e8 100644 --- a/modules/textual_inversion/preprocess.py +++ b/modules/textual_inversion/preprocess.py @@ -125,7 +125,7 @@ def multicrop_pic(image: Image, mindim, maxdim, minarea, maxarea, objective, thr default=None ) return wh and center_crop(image, *wh) - + def preprocess_work(process_src, process_dst, process_width, process_height, preprocess_txt_action, process_keep_original_size, process_flip, process_split, process_caption, process_caption_deepbooru=False, split_threshold=0.5, overlap_ratio=0.2, process_focal_crop=False, process_focal_crop_face_weight=0.9, process_focal_crop_entropy_weight=0.3, process_focal_crop_edges_weight=0.5, process_focal_crop_debug=False, process_multicrop=None, process_multicrop_mindim=None, process_multicrop_maxdim=None, process_multicrop_minarea=None, process_multicrop_maxarea=None, process_multicrop_objective=None, process_multicrop_threshold=None): width = process_width diff --git a/modules/textual_inversion/textual_inversion.py b/modules/textual_inversion/textual_inversion.py index 9e1b2b9a..d489ed1e 100644 --- a/modules/textual_inversion/textual_inversion.py +++ b/modules/textual_inversion/textual_inversion.py @@ -323,16 +323,16 @@ def tensorboard_add(tensorboard_writer, loss, global_step, step, learn_rate, epo tensorboard_add_scaler(tensorboard_writer, f"Learn rate/train/epoch-{epoch_num}", learn_rate, step) def tensorboard_add_scaler(tensorboard_writer, tag, value, step): - tensorboard_writer.add_scalar(tag=tag, + tensorboard_writer.add_scalar(tag=tag, scalar_value=value, global_step=step) def tensorboard_add_image(tensorboard_writer, tag, pil_image, step): # Convert a pil image to a torch tensor img_tensor = torch.as_tensor(np.array(pil_image, copy=True)) - img_tensor = img_tensor.view(pil_image.size[1], pil_image.size[0], + img_tensor = img_tensor.view(pil_image.size[1], pil_image.size[0], len(pil_image.getbands())) img_tensor = img_tensor.permute((2, 0, 1)) - + tensorboard_writer.add_image(tag, img_tensor, global_step=step) def validate_train_inputs(model_name, learn_rate, batch_size, gradient_step, data_root, template_file, template_filename, steps, save_model_every, create_image_every, log_directory, name="embedding"): @@ -402,7 +402,7 @@ def train_embedding(id_task, embedding_name, learn_rate, batch_size, gradient_st if initial_step >= steps: shared.state.textinfo = "Model has already been trained beyond specified max steps" return embedding, filename - + scheduler = LearnRateScheduler(learn_rate, steps, initial_step) clip_grad = torch.nn.utils.clip_grad_value_ if clip_grad_mode == "value" else \ torch.nn.utils.clip_grad_norm_ if clip_grad_mode == "norm" else \ @@ -412,7 +412,7 @@ def train_embedding(id_task, embedding_name, learn_rate, batch_size, gradient_st # dataset loading may take a while, so input validations and early returns should be done before this shared.state.textinfo = f"Preparing dataset from {html.escape(data_root)}..." old_parallel_processing_allowed = shared.parallel_processing_allowed - + if shared.opts.training_enable_tensorboard: tensorboard_writer = tensorboard_setup(log_directory) @@ -439,7 +439,7 @@ def train_embedding(id_task, embedding_name, learn_rate, batch_size, gradient_st optimizer_saved_dict = torch.load(f"{filename}.optim", map_location='cpu') if embedding.checksum() == optimizer_saved_dict.get('hash', None): optimizer_state_dict = optimizer_saved_dict.get('optimizer_state_dict', None) - + if optimizer_state_dict is not None: optimizer.load_state_dict(optimizer_state_dict) print("Loaded existing optimizer from checkpoint") @@ -485,7 +485,7 @@ def train_embedding(id_task, embedding_name, learn_rate, batch_size, gradient_st if clip_grad: clip_grad_sched.step(embedding.step) - + with devices.autocast(): x = batch.latent_sample.to(devices.device, non_blocking=pin_memory) if use_weight: @@ -513,7 +513,7 @@ def train_embedding(id_task, embedding_name, learn_rate, batch_size, gradient_st # go back until we reach gradient accumulation steps if (j + 1) % gradient_step != 0: continue - + if clip_grad: clip_grad(embedding.vec, clip_grad_sched.learn_rate) diff --git a/modules/ui.py b/modules/ui.py index 1efb656a..ff82fff6 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -1171,7 +1171,7 @@ def create_ui(): process_focal_crop_entropy_weight = gr.Slider(label='Focal point entropy weight', value=0.15, minimum=0.0, maximum=1.0, step=0.05, elem_id="train_process_focal_crop_entropy_weight") process_focal_crop_edges_weight = gr.Slider(label='Focal point edges weight', value=0.5, minimum=0.0, maximum=1.0, step=0.05, elem_id="train_process_focal_crop_edges_weight") process_focal_crop_debug = gr.Checkbox(label='Create debug image', elem_id="train_process_focal_crop_debug") - + with gr.Column(visible=False) as process_multicrop_col: gr.Markdown('Each image is center-cropped with an automatically chosen width and height.') with gr.Row(): @@ -1183,7 +1183,7 @@ def create_ui(): with gr.Row(): process_multicrop_objective = gr.Radio(["Maximize area", "Minimize error"], value="Maximize area", label="Resizing objective", elem_id="train_process_multicrop_objective") process_multicrop_threshold = gr.Slider(minimum=0, maximum=1, step=0.01, label="Error threshold", value=0.1, elem_id="train_process_multicrop_threshold") - + with gr.Row(): with gr.Column(scale=3): gr.HTML(value="") @@ -1226,7 +1226,7 @@ def create_ui(): with FormRow(): embedding_learn_rate = gr.Textbox(label='Embedding Learning rate', placeholder="Embedding Learning rate", value="0.005", elem_id="train_embedding_learn_rate") hypernetwork_learn_rate = gr.Textbox(label='Hypernetwork Learning rate', placeholder="Hypernetwork Learning rate", value="0.00001", elem_id="train_hypernetwork_learn_rate") - + with FormRow(): clip_grad_mode = gr.Dropdown(value="disabled", label="Gradient Clipping", choices=["disabled", "value", "norm"]) clip_grad_value = gr.Textbox(placeholder="Gradient clip value", value="0.1", show_label=False) @@ -1565,7 +1565,7 @@ def create_ui(): gr.HTML(shared.html("licenses.html"), elem_id="licenses") gr.Button(value="Show all pages", elem_id="settings_show_all_pages") - + def unload_sd_weights(): modules.sd_models.unload_model_weights() @@ -1841,15 +1841,15 @@ def versions_html(): return f""" version: {tag} - •  + • python: {python_version} - •  + • torch: {getattr(torch, '__long_version__',torch.__version__)} - •  + • xformers: {xformers_version} - •  + • gradio: {gr.__version__} - •  + • checkpoint: N/A """ diff --git a/modules/ui_extensions.py b/modules/ui_extensions.py index ed70abe5..af497733 100644 --- a/modules/ui_extensions.py +++ b/modules/ui_extensions.py @@ -467,7 +467,7 @@ def refresh_available_extensions_from_data(hide_tags, sort_column, filter_text=" {html.escape(description)}

Added: {html.escape(added)}

{install_code} - + """ for tag in [x for x in extension_tags if x not in tags]: @@ -535,9 +535,9 @@ def create_ui(): hide_tags = gr.CheckboxGroup(value=["ads", "localization", "installed"], label="Hide extensions with tags", choices=["script", "ads", "localization", "installed"]) sort_column = gr.Radio(value="newest first", label="Order", choices=["newest first", "oldest first", "a-z", "z-a", "internal order", ], type="index") - with gr.Row(): + with gr.Row(): search_extensions_text = gr.Text(label="Search").style(container=False) - + install_result = gr.HTML() available_extensions_table = gr.HTML() diff --git a/modules/xlmr.py b/modules/xlmr.py index e056c3f6..a407a3ca 100644 --- a/modules/xlmr.py +++ b/modules/xlmr.py @@ -28,7 +28,7 @@ class BertSeriesModelWithTransformation(BertPreTrainedModel): config_class = BertSeriesConfig def __init__(self, config=None, **kargs): - # modify initialization for autoloading + # modify initialization for autoloading if config is None: config = XLMRobertaConfig() config.attention_probs_dropout_prob= 0.1 @@ -74,7 +74,7 @@ class BertSeriesModelWithTransformation(BertPreTrainedModel): text["attention_mask"] = torch.tensor( text['attention_mask']).to(device) features = self(**text) - return features['projection_state'] + return features['projection_state'] def forward( self, @@ -134,4 +134,4 @@ class BertSeriesModelWithTransformation(BertPreTrainedModel): class RobertaSeriesModelWithTransformation(BertSeriesModelWithTransformation): base_model_prefix = 'roberta' - config_class= RobertaSeriesConfig \ No newline at end of file + config_class= RobertaSeriesConfig diff --git a/pyproject.toml b/pyproject.toml index c88907be..d4a1bbf4 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -6,6 +6,7 @@ extend-select = [ "B", "C", "I", + "W", ] exclude = [ @@ -20,7 +21,7 @@ ignore = [ "I001", # Import block is un-sorted or un-formatted "C901", # Function is too complex "C408", # Rewrite as a literal - + "W605", # invalid escape sequence, messes with some docstrings ] [tool.ruff.per-file-ignores] @@ -28,4 +29,4 @@ ignore = [ [tool.ruff.flake8-bugbear] # Allow default arguments like, e.g., `data: List[str] = fastapi.Query(None)`. -extend-immutable-calls = ["fastapi.Depends", "fastapi.security.HTTPBasic"] \ No newline at end of file +extend-immutable-calls = ["fastapi.Depends", "fastapi.security.HTTPBasic"] diff --git a/scripts/img2imgalt.py b/scripts/img2imgalt.py index bb00fb3f..1e833fa8 100644 --- a/scripts/img2imgalt.py +++ b/scripts/img2imgalt.py @@ -149,9 +149,9 @@ class Script(scripts.Script): sigma_adjustment = gr.Checkbox(label="Sigma adjustment for finding noise for image", value=False, elem_id=self.elem_id("sigma_adjustment")) return [ - info, + info, override_sampler, - override_prompt, original_prompt, original_negative_prompt, + override_prompt, original_prompt, original_negative_prompt, override_steps, st, override_strength, cfg, randomness, sigma_adjustment, @@ -191,17 +191,17 @@ class Script(scripts.Script): self.cache = Cached(rec_noise, cfg, st, lat, original_prompt, original_negative_prompt, sigma_adjustment) rand_noise = processing.create_random_tensors(p.init_latent.shape[1:], seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength, seed_resize_from_h=p.seed_resize_from_h, seed_resize_from_w=p.seed_resize_from_w, p=p) - + combined_noise = ((1 - randomness) * rec_noise + randomness * rand_noise) / ((randomness**2 + (1-randomness)**2) ** 0.5) - + sampler = sd_samplers.create_sampler(p.sampler_name, p.sd_model) sigmas = sampler.model_wrap.get_sigmas(p.steps) - + noise_dt = combined_noise - (p.init_latent / sigmas[0]) - + p.seed = p.seed + 1 - + return sampler.sample_img2img(p, p.init_latent, noise_dt, conditioning, unconditional_conditioning, image_conditioning=p.image_conditioning) p.sample = sample_extra diff --git a/scripts/loopback.py b/scripts/loopback.py index ad6609be..2d5feaf9 100644 --- a/scripts/loopback.py +++ b/scripts/loopback.py @@ -14,7 +14,7 @@ class Script(scripts.Script): def show(self, is_img2img): return is_img2img - def ui(self, is_img2img): + def ui(self, is_img2img): loops = gr.Slider(minimum=1, maximum=32, step=1, label='Loops', value=4, elem_id=self.elem_id("loops")) final_denoising_strength = gr.Slider(minimum=0, maximum=1, step=0.01, label='Final denoising strength', value=0.5, elem_id=self.elem_id("final_denoising_strength")) denoising_curve = gr.Dropdown(label="Denoising strength curve", choices=["Aggressive", "Linear", "Lazy"], value="Linear") @@ -104,7 +104,7 @@ class Script(scripts.Script): p.seed = processed.seed + 1 p.denoising_strength = calculate_denoising_strength(i + 1) - + if state.skipped: break @@ -121,7 +121,7 @@ class Script(scripts.Script): all_images.append(last_image) p.inpainting_fill = original_inpainting_fill - + if state.interrupted: break @@ -132,7 +132,7 @@ class Script(scripts.Script): if opts.return_grid: grids.append(grid) - + all_images = grids + all_images processed = Processed(p, all_images, initial_seed, initial_info) diff --git a/scripts/poor_mans_outpainting.py b/scripts/poor_mans_outpainting.py index c0bbecc1..ea0632b6 100644 --- a/scripts/poor_mans_outpainting.py +++ b/scripts/poor_mans_outpainting.py @@ -19,7 +19,7 @@ class Script(scripts.Script): def ui(self, is_img2img): if not is_img2img: return None - + pixels = gr.Slider(label="Pixels to expand", minimum=8, maximum=256, step=8, value=128, elem_id=self.elem_id("pixels")) mask_blur = gr.Slider(label='Mask blur', minimum=0, maximum=64, step=1, value=4, elem_id=self.elem_id("mask_blur")) inpainting_fill = gr.Radio(label='Masked content', choices=['fill', 'original', 'latent noise', 'latent nothing'], value='fill', type="index", elem_id=self.elem_id("inpainting_fill")) diff --git a/scripts/prompt_matrix.py b/scripts/prompt_matrix.py index fb06beab..88324fe6 100644 --- a/scripts/prompt_matrix.py +++ b/scripts/prompt_matrix.py @@ -96,7 +96,7 @@ class Script(scripts.Script): p.prompt_for_display = positive_prompt processed = process_images(p) - grid = images.image_grid(processed.images, p.batch_size, rows=1 << ((len(prompt_matrix_parts) - 1) // 2)) + grid = images.image_grid(processed.images, p.batch_size, rows=1 << ((len(prompt_matrix_parts) - 1) // 2)) grid = images.draw_prompt_matrix(grid, processed.images[0].width, processed.images[0].height, prompt_matrix_parts, margin_size) processed.images.insert(0, grid) processed.index_of_first_image = 1 diff --git a/scripts/prompts_from_file.py b/scripts/prompts_from_file.py index 9607077a..2378816f 100644 --- a/scripts/prompts_from_file.py +++ b/scripts/prompts_from_file.py @@ -109,7 +109,7 @@ class Script(scripts.Script): def title(self): return "Prompts from file or textbox" - def ui(self, is_img2img): + def ui(self, is_img2img): checkbox_iterate = gr.Checkbox(label="Iterate seed every line", value=False, elem_id=self.elem_id("checkbox_iterate")) checkbox_iterate_batch = gr.Checkbox(label="Use same random seed for all lines", value=False, elem_id=self.elem_id("checkbox_iterate_batch")) @@ -166,7 +166,7 @@ class Script(scripts.Script): proc = process_images(copy_p) images += proc.images - + if checkbox_iterate: p.seed = p.seed + (p.batch_size * p.n_iter) all_prompts += proc.all_prompts diff --git a/scripts/sd_upscale.py b/scripts/sd_upscale.py index 0b1d3096..e614c23b 100644 --- a/scripts/sd_upscale.py +++ b/scripts/sd_upscale.py @@ -16,7 +16,7 @@ class Script(scripts.Script): def show(self, is_img2img): return is_img2img - def ui(self, is_img2img): + def ui(self, is_img2img): info = gr.HTML("

Will upscale the image by the selected scale factor; use width and height sliders to set tile size

") overlap = gr.Slider(minimum=0, maximum=256, step=16, label='Tile overlap', value=64, elem_id=self.elem_id("overlap")) scale_factor = gr.Slider(minimum=1.0, maximum=4.0, step=0.05, label='Scale Factor', value=2.0, elem_id=self.elem_id("scale_factor")) -- cgit v1.2.3 From 55e52c878ab669d5b11b001a4152ee1a3b8d4880 Mon Sep 17 00:00:00 2001 From: papuSpartan <30642826+papuSpartan@users.noreply.github.com> Date: Sat, 13 May 2023 09:24:56 -0500 Subject: remove command line option --- modules/cmd_args.py | 1 - modules/processing.py | 10 +++++----- 2 files changed, 5 insertions(+), 6 deletions(-) (limited to 'modules/processing.py') diff --git a/modules/cmd_args.py b/modules/cmd_args.py index 46043e33..f4a4ab36 100644 --- a/modules/cmd_args.py +++ b/modules/cmd_args.py @@ -102,5 +102,4 @@ parser.add_argument("--no-gradio-queue", action='store_true', help="Disables gra parser.add_argument("--skip-version-check", action='store_true', help="Do not check versions of torch and xformers") parser.add_argument("--no-hashing", action='store_true', help="disable sha256 hashing of checkpoints to help loading performance", default=False) parser.add_argument("--no-download-sd-model", action='store_true', help="don't download SD1.5 model even if no model is found in --ckpt-dir", default=False) -parser.add_argument("--token-merging", action='store_true', help="Provides speed and memory improvements by merging redundant tokens. This has a more pronounced effect on higher resolutions.", default=False) parser.add_argument('--subpath', type=str, help='customize the subpath for gradio, use with reverse proxy') diff --git a/modules/processing.py b/modules/processing.py index 8ba3a96b..6828e898 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -496,8 +496,8 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments=None, iter "Conditional mask weight": getattr(p, "inpainting_mask_weight", shared.opts.inpainting_mask_weight) if p.is_using_inpainting_conditioning else None, "Clip skip": None if clip_skip <= 1 else clip_skip, "ENSD": None if opts.eta_noise_seed_delta == 0 else opts.eta_noise_seed_delta, - "Token merging ratio": None if not (opts.token_merging or cmd_opts.token_merging) or opts.token_merging_hr_only else opts.token_merging_ratio, - "Token merging ratio hr": None if not (opts.token_merging or cmd_opts.token_merging) else opts.token_merging_ratio_hr, + "Token merging ratio": None if not opts.token_merging or opts.token_merging_hr_only else opts.token_merging_ratio, + "Token merging ratio hr": None if not opts.token_merging else opts.token_merging_ratio_hr, "Token merging random": None if opts.token_merging_random is False else opts.token_merging_random, "Token merging merge attention": None if opts.token_merging_merge_attention is True else opts.token_merging_merge_attention, "Token merging merge cross attention": None if opts.token_merging_merge_cross_attention is False else opts.token_merging_merge_cross_attention, @@ -538,7 +538,7 @@ def process_images(p: StableDiffusionProcessing) -> Processed: if k == 'sd_vae': sd_vae.reload_vae_weights() - if (opts.token_merging or cmd_opts.token_merging) and not opts.token_merging_hr_only: + if opts.token_merging and not opts.token_merging_hr_only: sd_models.apply_token_merging(sd_model=p.sd_model, hr=False) logger.debug('Token merging applied') @@ -546,7 +546,7 @@ def process_images(p: StableDiffusionProcessing) -> Processed: finally: # undo model optimizations made by tomesd - if opts.token_merging or cmd_opts.token_merging: + if opts.token_merging: tomesd.remove_patch(p.sd_model) logger.debug('Token merging model optimizations removed') @@ -1004,7 +1004,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): # apply token merging optimizations from tomesd for high-res pass # check if hr_only so we are not redundantly patching - if (cmd_opts.token_merging or opts.token_merging) and (opts.token_merging_hr_only or opts.token_merging_ratio_hr != opts.token_merging_ratio): + if opts.token_merging and (opts.token_merging_hr_only or opts.token_merging_ratio_hr != opts.token_merging_ratio): # case where user wants to use separate merge ratios if not opts.token_merging_hr_only: # clean patch done by first pass. (clobbering the first patch might be fine? this might be excessive) -- cgit v1.2.3 From ac83627a31daac06f4d48b0e7db223ef807fe8e5 Mon Sep 17 00:00:00 2001 From: papuSpartan <30642826+papuSpartan@users.noreply.github.com> Date: Sat, 13 May 2023 10:23:42 -0500 Subject: heavily simplify --- modules/generation_parameters_copypaste.py | 36 ------------------------- modules/processing.py | 35 +++++++++++-------------- modules/sd_models.py | 11 +++----- modules/shared.py | 42 +++--------------------------- 4 files changed, 23 insertions(+), 101 deletions(-) (limited to 'modules/processing.py') diff --git a/modules/generation_parameters_copypaste.py b/modules/generation_parameters_copypaste.py index fb56254f..a0a98bbc 100644 --- a/modules/generation_parameters_copypaste.py +++ b/modules/generation_parameters_copypaste.py @@ -282,33 +282,6 @@ Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 965400086, Size: 512x512, Model res["Hires resize-1"] = 0 res["Hires resize-2"] = 0 - # Infer additional override settings for token merging - token_merging_ratio = res.get("Token merging ratio", None) - token_merging_ratio_hr = res.get("Token merging ratio hr", None) - - if token_merging_ratio is not None or token_merging_ratio_hr is not None: - res["Token merging"] = 'True' - - if token_merging_ratio is None: - res["Token merging hr only"] = 'True' - else: - res["Token merging hr only"] = 'False' - - if res.get("Token merging random", None) is None: - res["Token merging random"] = 'False' - if res.get("Token merging merge attention", None) is None: - res["Token merging merge attention"] = 'True' - if res.get("Token merging merge cross attention", None) is None: - res["Token merging merge cross attention"] = 'False' - if res.get("Token merging merge mlp", None) is None: - res["Token merging merge mlp"] = 'False' - if res.get("Token merging stride x", None) is None: - res["Token merging stride x"] = '2' - if res.get("Token merging stride y", None) is None: - res["Token merging stride y"] = '2' - if res.get("Token merging maximum down sampling", None) is None: - res["Token merging maximum down sampling"] = '1' - restore_old_hires_fix_params(res) # Missing RNG means the default was set, which is GPU RNG @@ -335,17 +308,8 @@ infotext_to_setting_name_mapping = [ ('UniPC skip type', 'uni_pc_skip_type'), ('UniPC order', 'uni_pc_order'), ('UniPC lower order final', 'uni_pc_lower_order_final'), - ('Token merging', 'token_merging'), ('Token merging ratio', 'token_merging_ratio'), - ('Token merging hr only', 'token_merging_hr_only'), ('Token merging ratio hr', 'token_merging_ratio_hr'), - ('Token merging random', 'token_merging_random'), - ('Token merging merge attention', 'token_merging_merge_attention'), - ('Token merging merge cross attention', 'token_merging_merge_cross_attention'), - ('Token merging merge mlp', 'token_merging_merge_mlp'), - ('Token merging maximum down sampling', 'token_merging_maximum_down_sampling'), - ('Token merging stride x', 'token_merging_stride_x'), - ('Token merging stride y', 'token_merging_stride_y'), ('RNG', 'randn_source'), ('NGMS', 's_min_uncond') ] diff --git a/modules/processing.py b/modules/processing.py index 6828e898..32ff61e9 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -34,7 +34,7 @@ import tomesd # add a logger for the processing module logger = logging.getLogger(__name__) # manually set output level here since there is no option to do so yet through launch options -# logging.basicConfig(level=logging.DEBUG, format='%(asctime)s %(levelname)s %(name)s %(message)s') +logging.basicConfig(level=logging.DEBUG, format='%(asctime)s %(levelname)s %(name)s %(message)s') # some of those options should not be changed at all because they would break the model, so I removed them from options. @@ -496,15 +496,8 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments=None, iter "Conditional mask weight": getattr(p, "inpainting_mask_weight", shared.opts.inpainting_mask_weight) if p.is_using_inpainting_conditioning else None, "Clip skip": None if clip_skip <= 1 else clip_skip, "ENSD": None if opts.eta_noise_seed_delta == 0 else opts.eta_noise_seed_delta, - "Token merging ratio": None if not opts.token_merging or opts.token_merging_hr_only else opts.token_merging_ratio, - "Token merging ratio hr": None if not opts.token_merging else opts.token_merging_ratio_hr, - "Token merging random": None if opts.token_merging_random is False else opts.token_merging_random, - "Token merging merge attention": None if opts.token_merging_merge_attention is True else opts.token_merging_merge_attention, - "Token merging merge cross attention": None if opts.token_merging_merge_cross_attention is False else opts.token_merging_merge_cross_attention, - "Token merging merge mlp": None if opts.token_merging_merge_mlp is False else opts.token_merging_merge_mlp, - "Token merging stride x": None if opts.token_merging_stride_x == 2 else opts.token_merging_stride_x, - "Token merging stride y": None if opts.token_merging_stride_y == 2 else opts.token_merging_stride_y, - "Token merging maximum down sampling": None if opts.token_merging_maximum_down_sampling == 1 else opts.token_merging_maximum_down_sampling, + "Token merging ratio": None if opts.token_merging_ratio == 0 else opts.token_merging_ratio, + "Token merging ratio hr": None if not p.enable_hr or opts.token_merging_ratio_hr == 0 else opts.token_merging_ratio_hr, "Init image hash": getattr(p, 'init_img_hash', None), "RNG": opts.randn_source if opts.randn_source != "GPU" else None, "NGMS": None if p.s_min_uncond == 0 else p.s_min_uncond, @@ -538,15 +531,15 @@ def process_images(p: StableDiffusionProcessing) -> Processed: if k == 'sd_vae': sd_vae.reload_vae_weights() - if opts.token_merging and not opts.token_merging_hr_only: + if opts.token_merging_ratio > 0: sd_models.apply_token_merging(sd_model=p.sd_model, hr=False) - logger.debug('Token merging applied') + logger.debug(f"Token merging applied to first pass. Ratio: '{opts.token_merging_ratio}'") res = process_images_inner(p) finally: # undo model optimizations made by tomesd - if opts.token_merging: + if opts.token_merging_ratio > 0: tomesd.remove_patch(p.sd_model) logger.debug('Token merging model optimizations removed') @@ -1003,19 +996,21 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): devices.torch_gc() # apply token merging optimizations from tomesd for high-res pass - # check if hr_only so we are not redundantly patching - if opts.token_merging and (opts.token_merging_hr_only or opts.token_merging_ratio_hr != opts.token_merging_ratio): - # case where user wants to use separate merge ratios - if not opts.token_merging_hr_only: - # clean patch done by first pass. (clobbering the first patch might be fine? this might be excessive) + if opts.token_merging_ratio_hr > 0: + # in case the user has used separate merge ratios + if opts.token_merging_ratio > 0: tomesd.remove_patch(self.sd_model) - logger.debug('Temporarily removed token merging optimizations in preparation for next pass') + logger.debug('Adjusting token merging ratio for high-res pass') sd_models.apply_token_merging(sd_model=self.sd_model, hr=True) - logger.debug('Applied token merging for high-res pass') + logger.debug(f"Applied token merging for high-res pass. Ratio: '{opts.token_merging_ratio_hr}'") samples = self.sampler.sample_img2img(self, samples, noise, conditioning, unconditional_conditioning, steps=self.hr_second_pass_steps or self.steps, image_conditioning=image_conditioning) + if opts.token_merging_ratio_hr > 0 or opts.token_merging_ratio > 0: + tomesd.remove_patch(self.sd_model) + logger.debug('Removed token merging optimizations from model') + self.is_hr_pass = False return samples diff --git a/modules/sd_models.py b/modules/sd_models.py index 4787193c..4c9a0a1f 100644 --- a/modules/sd_models.py +++ b/modules/sd_models.py @@ -596,11 +596,8 @@ def apply_token_merging(sd_model, hr: bool): tomesd.apply_patch( sd_model, ratio=ratio, - max_downsample=shared.opts.token_merging_maximum_down_sampling, - sx=shared.opts.token_merging_stride_x, - sy=shared.opts.token_merging_stride_y, - use_rand=shared.opts.token_merging_random, - merge_attn=shared.opts.token_merging_merge_attention, - merge_crossattn=shared.opts.token_merging_merge_cross_attention, - merge_mlp=shared.opts.token_merging_merge_mlp + use_rand=False, # can cause issues with some samplers + merge_attn=True, + merge_crossattn=False, + merge_mlp=False ) diff --git a/modules/shared.py b/modules/shared.py index 4b346585..0d96c14c 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -459,47 +459,13 @@ options_templates.update(options_section((None, "Hidden options"), { })) options_templates.update(options_section(('token_merging', 'Token Merging'), { - "token_merging": OptionInfo( - False, "Enable redundant token merging via tomesd. This can provide significant speed and memory improvements.", - gr.Checkbox - ), - "token_merging_ratio": OptionInfo( - 0.5, "Merging Ratio", - gr.Slider, {"minimum": 0, "maximum": 0.9, "step": 0.1} - ), - "token_merging_hr_only": OptionInfo( - True, "Apply only to high-res fix pass. Disabling can yield a ~20-35% speedup on contemporary resolutions.", - gr.Checkbox - ), "token_merging_ratio_hr": OptionInfo( - 0.5, "Merging Ratio (high-res pass) - If 'Apply only to high-res' is enabled, this will always be the ratio used.", + 0, "Merging Ratio (high-res pass)", gr.Slider, {"minimum": 0, "maximum": 0.9, "step": 0.1} ), - # More advanced/niche settings: - "token_merging_random": OptionInfo( - False, "Use random perturbations - Can improve outputs for certain samplers. For others, it may cause visual artifacting.", - gr.Checkbox - ), - "token_merging_merge_attention": OptionInfo( - True, "Merge attention", - gr.Checkbox - ), - "token_merging_merge_cross_attention": OptionInfo( - False, "Merge cross attention", - gr.Checkbox - ), - "token_merging_merge_mlp": OptionInfo( - False, "Merge mlp", - gr.Checkbox - ), - "token_merging_maximum_down_sampling": OptionInfo(1, "Maximum down sampling", gr.Radio, lambda: {"choices": [1, 2, 4, 8]}), - "token_merging_stride_x": OptionInfo( - 2, "Stride - X", - gr.Slider, {"minimum": 2, "maximum": 8, "step": 2} - ), - "token_merging_stride_y": OptionInfo( - 2, "Stride - Y", - gr.Slider, {"minimum": 2, "maximum": 8, "step": 2} + "token_merging_ratio": OptionInfo( + 0, "Merging Ratio", + gr.Slider, {"minimum": 0, "maximum": 0.9, "step": 0.1} ) })) -- cgit v1.2.3 From c2fdb44880e07f43aee2f7edc1dc36a9516501e8 Mon Sep 17 00:00:00 2001 From: papuSpartan <30642826+papuSpartan@users.noreply.github.com> Date: Sat, 13 May 2023 11:11:02 -0500 Subject: fix for img2img --- modules/processing.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'modules/processing.py') diff --git a/modules/processing.py b/modules/processing.py index 32ff61e9..94fe2625 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -34,7 +34,7 @@ import tomesd # add a logger for the processing module logger = logging.getLogger(__name__) # manually set output level here since there is no option to do so yet through launch options -logging.basicConfig(level=logging.DEBUG, format='%(asctime)s %(levelname)s %(name)s %(message)s') +# logging.basicConfig(level=logging.DEBUG, format='%(asctime)s %(levelname)s %(name)s %(message)s') # some of those options should not be changed at all because they would break the model, so I removed them from options. @@ -478,6 +478,7 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments=None, iter index = position_in_batch + iteration * p.batch_size clip_skip = getattr(p, 'clip_skip', opts.CLIP_stop_at_last_layers) + enable_hr = getattr(p, 'enable_hr', False) generation_params = { "Steps": p.steps, @@ -497,7 +498,7 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments=None, iter "Clip skip": None if clip_skip <= 1 else clip_skip, "ENSD": None if opts.eta_noise_seed_delta == 0 else opts.eta_noise_seed_delta, "Token merging ratio": None if opts.token_merging_ratio == 0 else opts.token_merging_ratio, - "Token merging ratio hr": None if not p.enable_hr or opts.token_merging_ratio_hr == 0 else opts.token_merging_ratio_hr, + "Token merging ratio hr": None if not enable_hr or opts.token_merging_ratio_hr == 0 else opts.token_merging_ratio_hr, "Init image hash": getattr(p, 'init_img_hash', None), "RNG": opts.randn_source if opts.randn_source != "GPU" else None, "NGMS": None if p.s_min_uncond == 0 else p.s_min_uncond, -- cgit v1.2.3 From cdac5ace1456ba779d5a0171ff8757f31955bfee Mon Sep 17 00:00:00 2001 From: AUTOMATIC <16777216c@gmail.com> Date: Tue, 16 May 2023 11:54:02 +0300 Subject: suppress ENSD infotext for samplers that don't use it --- modules/processing.py | 11 +++++++---- modules/sd_samplers.py | 8 +++++++- modules/sd_samplers_common.py | 21 ++++++++++++++++++++- modules/sd_samplers_compvis.py | 8 ++++++-- modules/sd_samplers_kdiffusion.py | 16 ++++++++-------- 5 files changed, 48 insertions(+), 16 deletions(-) (limited to 'modules/processing.py') diff --git a/modules/processing.py b/modules/processing.py index 94fe2625..15806f78 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -13,7 +13,7 @@ from skimage import exposure from typing import Any, Dict, List import modules.sd_hijack -from modules import devices, prompt_parser, masking, sd_samplers, lowvram, generation_parameters_copypaste, extra_networks, sd_vae_approx, scripts +from modules import devices, prompt_parser, masking, sd_samplers, lowvram, generation_parameters_copypaste, extra_networks, sd_vae_approx, scripts, sd_samplers_common from modules.sd_hijack import model_hijack from modules.shared import opts, cmd_opts, state import modules.shared as shared @@ -480,6 +480,10 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments=None, iter clip_skip = getattr(p, 'clip_skip', opts.CLIP_stop_at_last_layers) enable_hr = getattr(p, 'enable_hr', False) + uses_ensd = opts.eta_noise_seed_delta != 0 + if uses_ensd: + uses_ensd = sd_samplers_common.is_sampler_using_eta_noise_seed_delta(p) + generation_params = { "Steps": p.steps, "Sampler": p.sampler_name, @@ -496,17 +500,16 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments=None, iter "Denoising strength": getattr(p, 'denoising_strength', None), "Conditional mask weight": getattr(p, "inpainting_mask_weight", shared.opts.inpainting_mask_weight) if p.is_using_inpainting_conditioning else None, "Clip skip": None if clip_skip <= 1 else clip_skip, - "ENSD": None if opts.eta_noise_seed_delta == 0 else opts.eta_noise_seed_delta, + "ENSD": opts.eta_noise_seed_delta if uses_ensd else None, "Token merging ratio": None if opts.token_merging_ratio == 0 else opts.token_merging_ratio, "Token merging ratio hr": None if not enable_hr or opts.token_merging_ratio_hr == 0 else opts.token_merging_ratio_hr, "Init image hash": getattr(p, 'init_img_hash', None), "RNG": opts.randn_source if opts.randn_source != "GPU" else None, "NGMS": None if p.s_min_uncond == 0 else p.s_min_uncond, + **p.extra_generation_params, "Version": program_version() if opts.add_version_to_infotext else None, } - generation_params.update(p.extra_generation_params) - generation_params_text = ", ".join([k if k == v else f'{k}: {generation_parameters_copypaste.quote(v)}' for k, v in generation_params.items() if v is not None]) negative_prompt_text = f"\nNegative prompt: {p.all_negative_prompts[index]}" if p.all_negative_prompts[index] else "" diff --git a/modules/sd_samplers.py b/modules/sd_samplers.py index 4f1bf21d..f22aad8f 100644 --- a/modules/sd_samplers.py +++ b/modules/sd_samplers.py @@ -14,12 +14,18 @@ samplers_for_img2img = [] samplers_map = {} -def create_sampler(name, model): +def find_sampler_config(name): if name is not None: config = all_samplers_map.get(name, None) else: config = all_samplers[0] + return config + + +def create_sampler(name, model): + config = find_sampler_config(name) + assert config is not None, f'bad sampler name: {name}' sampler = config.constructor(model) diff --git a/modules/sd_samplers_common.py b/modules/sd_samplers_common.py index bc074238..92880caf 100644 --- a/modules/sd_samplers_common.py +++ b/modules/sd_samplers_common.py @@ -2,7 +2,7 @@ from collections import namedtuple import numpy as np import torch from PIL import Image -from modules import devices, processing, images, sd_vae_approx +from modules import devices, processing, images, sd_vae_approx, sd_samplers from modules.shared import opts, state import modules.shared as shared @@ -58,6 +58,25 @@ def store_latent(decoded): shared.state.assign_current_image(sample_to_image(decoded)) +def is_sampler_using_eta_noise_seed_delta(p): + """returns whether sampler from config will use eta noise seed delta for image creation""" + + sampler_config = sd_samplers.find_sampler_config(p.sampler_name) + + eta = p.eta + + if eta is None and p.sampler is not None: + eta = p.sampler.eta + + if eta is None and sampler_config is not None: + eta = 0 if sampler_config.options.get("default_eta_is_0", False) else 1.0 + + if eta == 0: + return False + + return sampler_config.options.get("uses_ensd", False) + + class InterruptedException(BaseException): pass diff --git a/modules/sd_samplers_compvis.py b/modules/sd_samplers_compvis.py index b1ee3be7..bdae8b40 100644 --- a/modules/sd_samplers_compvis.py +++ b/modules/sd_samplers_compvis.py @@ -11,7 +11,7 @@ import modules.models.diffusion.uni_pc samplers_data_compvis = [ - sd_samplers_common.SamplerData('DDIM', lambda model: VanillaStableDiffusionSampler(ldm.models.diffusion.ddim.DDIMSampler, model), [], {}), + sd_samplers_common.SamplerData('DDIM', lambda model: VanillaStableDiffusionSampler(ldm.models.diffusion.ddim.DDIMSampler, model), [], {"default_eta_is_0": True, "uses_ensd": True}), sd_samplers_common.SamplerData('PLMS', lambda model: VanillaStableDiffusionSampler(ldm.models.diffusion.plms.PLMSSampler, model), [], {}), sd_samplers_common.SamplerData('UniPC', lambda model: VanillaStableDiffusionSampler(modules.models.diffusion.uni_pc.UniPCSampler, model), [], {}), ] @@ -134,7 +134,11 @@ class VanillaStableDiffusionSampler: self.update_step(x) def initialize(self, p): - self.eta = p.eta if p.eta is not None else shared.opts.eta_ddim + if self.is_ddim: + self.eta = p.eta if p.eta is not None else shared.opts.eta_ddim + else: + self.eta = 0.0 + if self.eta != 0.0: p.extra_generation_params["Eta DDIM"] = self.eta diff --git a/modules/sd_samplers_kdiffusion.py b/modules/sd_samplers_kdiffusion.py index 61f23ad7..5455561a 100644 --- a/modules/sd_samplers_kdiffusion.py +++ b/modules/sd_samplers_kdiffusion.py @@ -11,21 +11,21 @@ from modules.script_callbacks import CFGDenoisedParams, cfg_denoised_callback from modules.script_callbacks import AfterCFGCallbackParams, cfg_after_cfg_callback samplers_k_diffusion = [ - ('Euler a', 'sample_euler_ancestral', ['k_euler_a', 'k_euler_ancestral'], {}), + ('Euler a', 'sample_euler_ancestral', ['k_euler_a', 'k_euler_ancestral'], {"uses_ensd": True}), ('Euler', 'sample_euler', ['k_euler'], {}), ('LMS', 'sample_lms', ['k_lms'], {}), ('Heun', 'sample_heun', ['k_heun'], {}), ('DPM2', 'sample_dpm_2', ['k_dpm_2'], {'discard_next_to_last_sigma': True}), - ('DPM2 a', 'sample_dpm_2_ancestral', ['k_dpm_2_a'], {'discard_next_to_last_sigma': True}), - ('DPM++ 2S a', 'sample_dpmpp_2s_ancestral', ['k_dpmpp_2s_a'], {}), + ('DPM2 a', 'sample_dpm_2_ancestral', ['k_dpm_2_a'], {'discard_next_to_last_sigma': True, "uses_ensd": True}), + ('DPM++ 2S a', 'sample_dpmpp_2s_ancestral', ['k_dpmpp_2s_a'], {"uses_ensd": True}), ('DPM++ 2M', 'sample_dpmpp_2m', ['k_dpmpp_2m'], {}), ('DPM++ SDE', 'sample_dpmpp_sde', ['k_dpmpp_sde'], {}), - ('DPM fast', 'sample_dpm_fast', ['k_dpm_fast'], {}), - ('DPM adaptive', 'sample_dpm_adaptive', ['k_dpm_ad'], {}), + ('DPM fast', 'sample_dpm_fast', ['k_dpm_fast'], {"uses_ensd": True}), + ('DPM adaptive', 'sample_dpm_adaptive', ['k_dpm_ad'], {"uses_ensd": True}), ('LMS Karras', 'sample_lms', ['k_lms_ka'], {'scheduler': 'karras'}), - ('DPM2 Karras', 'sample_dpm_2', ['k_dpm_2_ka'], {'scheduler': 'karras', 'discard_next_to_last_sigma': True}), - ('DPM2 a Karras', 'sample_dpm_2_ancestral', ['k_dpm_2_a_ka'], {'scheduler': 'karras', 'discard_next_to_last_sigma': True}), - ('DPM++ 2S a Karras', 'sample_dpmpp_2s_ancestral', ['k_dpmpp_2s_a_ka'], {'scheduler': 'karras'}), + ('DPM2 Karras', 'sample_dpm_2', ['k_dpm_2_ka'], {'scheduler': 'karras', 'discard_next_to_last_sigma': True, "uses_ensd": True}), + ('DPM2 a Karras', 'sample_dpm_2_ancestral', ['k_dpm_2_a_ka'], {'scheduler': 'karras', 'discard_next_to_last_sigma': True, "uses_ensd": True}), + ('DPM++ 2S a Karras', 'sample_dpmpp_2s_ancestral', ['k_dpmpp_2s_a_ka'], {'scheduler': 'karras', "uses_ensd": True}), ('DPM++ 2M Karras', 'sample_dpmpp_2m', ['k_dpmpp_2m_ka'], {'scheduler': 'karras'}), ('DPM++ SDE Karras', 'sample_dpmpp_sde', ['k_dpmpp_sde_ka'], {'scheduler': 'karras'}), ] -- cgit v1.2.3 From a61cbef02c7652f96d333b28e01f5230e225224e Mon Sep 17 00:00:00 2001 From: AUTOMATIC <16777216c@gmail.com> Date: Tue, 16 May 2023 12:36:15 +0300 Subject: add second_order field to sampler config --- modules/processing.py | 8 ++------ modules/sd_samplers_kdiffusion.py | 14 +++++++------- 2 files changed, 9 insertions(+), 13 deletions(-) (limited to 'modules/processing.py') diff --git a/modules/processing.py b/modules/processing.py index 15806f78..678c4468 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -681,12 +681,8 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: processed = Processed(p, [], p.seed, "") file.write(processed.infotext(p, 0)) - step_multiplier = 1 - if not shared.opts.dont_fix_second_order_samplers_schedule: - try: - step_multiplier = 2 if sd_samplers.all_samplers_map.get(p.sampler_name).aliases[0] in ['k_dpmpp_2s_a', 'k_dpmpp_2s_a_ka', 'k_dpmpp_sde', 'k_dpmpp_sde_ka', 'k_dpm_2', 'k_dpm_2_a', 'k_heun'] else 1 - except Exception: - pass + sampler_config = sd_samplers.find_sampler_config(p.sampler_name) + step_multiplier = 2 if sampler_config and sampler_config.options.get("second_order", False) else 1 uc = get_conds_with_caching(prompt_parser.get_learned_conditioning, negative_prompts, p.steps * step_multiplier, cached_uc) c = get_conds_with_caching(prompt_parser.get_multicond_learned_conditioning, prompts, p.steps * step_multiplier, cached_c) diff --git a/modules/sd_samplers_kdiffusion.py b/modules/sd_samplers_kdiffusion.py index 5455561a..552c6c64 100644 --- a/modules/sd_samplers_kdiffusion.py +++ b/modules/sd_samplers_kdiffusion.py @@ -14,20 +14,20 @@ samplers_k_diffusion = [ ('Euler a', 'sample_euler_ancestral', ['k_euler_a', 'k_euler_ancestral'], {"uses_ensd": True}), ('Euler', 'sample_euler', ['k_euler'], {}), ('LMS', 'sample_lms', ['k_lms'], {}), - ('Heun', 'sample_heun', ['k_heun'], {}), + ('Heun', 'sample_heun', ['k_heun'], {"second_order": True}), ('DPM2', 'sample_dpm_2', ['k_dpm_2'], {'discard_next_to_last_sigma': True}), ('DPM2 a', 'sample_dpm_2_ancestral', ['k_dpm_2_a'], {'discard_next_to_last_sigma': True, "uses_ensd": True}), - ('DPM++ 2S a', 'sample_dpmpp_2s_ancestral', ['k_dpmpp_2s_a'], {"uses_ensd": True}), + ('DPM++ 2S a', 'sample_dpmpp_2s_ancestral', ['k_dpmpp_2s_a'], {"uses_ensd": True, "second_order": True}), ('DPM++ 2M', 'sample_dpmpp_2m', ['k_dpmpp_2m'], {}), - ('DPM++ SDE', 'sample_dpmpp_sde', ['k_dpmpp_sde'], {}), + ('DPM++ SDE', 'sample_dpmpp_sde', ['k_dpmpp_sde'], {"second_order": True}), ('DPM fast', 'sample_dpm_fast', ['k_dpm_fast'], {"uses_ensd": True}), ('DPM adaptive', 'sample_dpm_adaptive', ['k_dpm_ad'], {"uses_ensd": True}), ('LMS Karras', 'sample_lms', ['k_lms_ka'], {'scheduler': 'karras'}), - ('DPM2 Karras', 'sample_dpm_2', ['k_dpm_2_ka'], {'scheduler': 'karras', 'discard_next_to_last_sigma': True, "uses_ensd": True}), - ('DPM2 a Karras', 'sample_dpm_2_ancestral', ['k_dpm_2_a_ka'], {'scheduler': 'karras', 'discard_next_to_last_sigma': True, "uses_ensd": True}), - ('DPM++ 2S a Karras', 'sample_dpmpp_2s_ancestral', ['k_dpmpp_2s_a_ka'], {'scheduler': 'karras', "uses_ensd": True}), + ('DPM2 Karras', 'sample_dpm_2', ['k_dpm_2_ka'], {'scheduler': 'karras', 'discard_next_to_last_sigma': True, "uses_ensd": True, "second_order": True}), + ('DPM2 a Karras', 'sample_dpm_2_ancestral', ['k_dpm_2_a_ka'], {'scheduler': 'karras', 'discard_next_to_last_sigma': True, "uses_ensd": True, "second_order": True}), + ('DPM++ 2S a Karras', 'sample_dpmpp_2s_ancestral', ['k_dpmpp_2s_a_ka'], {'scheduler': 'karras', "uses_ensd": True, "second_order": True}), ('DPM++ 2M Karras', 'sample_dpmpp_2m', ['k_dpmpp_2m_ka'], {'scheduler': 'karras'}), - ('DPM++ SDE Karras', 'sample_dpmpp_sde', ['k_dpmpp_sde_ka'], {'scheduler': 'karras'}), + ('DPM++ SDE Karras', 'sample_dpmpp_sde', ['k_dpmpp_sde_ka'], {'scheduler': 'karras', "second_order": True}), ] samplers_data_k_diffusion = [ -- cgit v1.2.3 From 315f109427a5dbbf48b0da560640523800fe3c1d Mon Sep 17 00:00:00 2001 From: Aarni Koskela Date: Wed, 17 May 2023 10:26:32 +0300 Subject: Copy s_min_uncond to Processed Should fix #10416 --- modules/processing.py | 1 + 1 file changed, 1 insertion(+) (limited to 'modules/processing.py') diff --git a/modules/processing.py b/modules/processing.py index 678c4468..cd63b9a6 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -316,6 +316,7 @@ class Processed: self.s_tmin = p.s_tmin self.s_tmax = p.s_tmax self.s_noise = p.s_noise + self.s_min_uncond = p.s_min_uncond self.sampler_noise_scheduler_override = p.sampler_noise_scheduler_override self.prompt = self.prompt if type(self.prompt) != list else self.prompt[0] self.negative_prompt = self.negative_prompt if type(self.negative_prompt) != list else self.negative_prompt[0] -- cgit v1.2.3 From 9fd6c1e3430f5947add23e2e94ac816c2546481c Mon Sep 17 00:00:00 2001 From: AUTOMATIC <16777216c@gmail.com> Date: Wed, 17 May 2023 20:22:38 +0300 Subject: move some settings to the new Optimization page add slider for token merging for img2img rework StableDiffusionProcessing to have the token_merging_ratio field fix a bug with applying png optimizations for live previews when they shouldn't be applied --- modules/processing.py | 52 +++++++++++++++++++++++++-------------------------- modules/progress.py | 6 +++++- modules/sd_models.py | 36 +++++++++++++++++++---------------- modules/shared.py | 8 ++++++-- 4 files changed, 56 insertions(+), 46 deletions(-) (limited to 'modules/processing.py') diff --git a/modules/processing.py b/modules/processing.py index cd63b9a6..2b8dd361 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -29,12 +29,6 @@ from ldm.models.diffusion.ddpm import LatentDepth2ImageDiffusion from einops import repeat, rearrange from blendmodes.blend import blendLayers, BlendType -import tomesd - -# add a logger for the processing module -logger = logging.getLogger(__name__) -# manually set output level here since there is no option to do so yet through launch options -# logging.basicConfig(level=logging.DEBUG, format='%(asctime)s %(levelname)s %(name)s %(message)s') # some of those options should not be changed at all because they would break the model, so I removed them from options. @@ -156,6 +150,8 @@ class StableDiffusionProcessing: self.override_settings_restore_afterwards = override_settings_restore_afterwards self.is_using_inpainting_conditioning = False self.disable_extra_networks = False + self.token_merging_ratio = 0 + self.token_merging_ratio_hr = 0 if not seed_enable_extras: self.subseed = -1 @@ -171,6 +167,7 @@ class StableDiffusionProcessing: self.all_subseeds = None self.iteration = 0 self.is_hr_pass = False + self.sampler = None @property @@ -280,6 +277,12 @@ class StableDiffusionProcessing: def close(self): self.sampler = None + def get_token_merging_ratio(self, for_hr=False): + if for_hr: + return self.token_merging_ratio_hr or opts.token_merging_ratio_hr or self.token_merging_ratio or opts.token_merging_ratio + + return self.token_merging_ratio or opts.token_merging_ratio + class Processed: def __init__(self, p: StableDiffusionProcessing, images_list, seed=-1, info="", subseed=None, all_prompts=None, all_negative_prompts=None, all_seeds=None, all_subseeds=None, index_of_first_image=0, infotexts=None, comments=""): @@ -309,6 +312,8 @@ class Processed: self.styles = p.styles self.job_timestamp = state.job_timestamp self.clip_skip = opts.CLIP_stop_at_last_layers + self.token_merging_ratio = p.token_merging_ratio + self.token_merging_ratio_hr = p.token_merging_ratio_hr self.eta = p.eta self.ddim_discretize = p.ddim_discretize @@ -367,6 +372,9 @@ class Processed: def infotext(self, p: StableDiffusionProcessing, index): return create_infotext(p, self.all_prompts, self.all_seeds, self.all_subseeds, comments=[], position_in_batch=index % self.batch_size, iteration=index // self.batch_size) + def get_token_merging_ratio(self, for_hr=False): + return self.token_merging_ratio_hr if for_hr else self.token_merging_ratio + # from https://discuss.pytorch.org/t/help-regarding-slerp-function-for-generative-model-sampling/32475/3 def slerp(val, low, high): @@ -480,6 +488,8 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments=None, iter clip_skip = getattr(p, 'clip_skip', opts.CLIP_stop_at_last_layers) enable_hr = getattr(p, 'enable_hr', False) + token_merging_ratio = p.get_token_merging_ratio() + token_merging_ratio_hr = p.get_token_merging_ratio(for_hr=True) uses_ensd = opts.eta_noise_seed_delta != 0 if uses_ensd: @@ -502,8 +512,8 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments=None, iter "Conditional mask weight": getattr(p, "inpainting_mask_weight", shared.opts.inpainting_mask_weight) if p.is_using_inpainting_conditioning else None, "Clip skip": None if clip_skip <= 1 else clip_skip, "ENSD": opts.eta_noise_seed_delta if uses_ensd else None, - "Token merging ratio": None if opts.token_merging_ratio == 0 else opts.token_merging_ratio, - "Token merging ratio hr": None if not enable_hr or opts.token_merging_ratio_hr == 0 else opts.token_merging_ratio_hr, + "Token merging ratio": None if token_merging_ratio == 0 else token_merging_ratio, + "Token merging ratio hr": None if not enable_hr or token_merging_ratio_hr == 0 else token_merging_ratio_hr, "Init image hash": getattr(p, 'init_img_hash', None), "RNG": opts.randn_source if opts.randn_source != "GPU" else None, "NGMS": None if p.s_min_uncond == 0 else p.s_min_uncond, @@ -536,17 +546,12 @@ def process_images(p: StableDiffusionProcessing) -> Processed: if k == 'sd_vae': sd_vae.reload_vae_weights() - if opts.token_merging_ratio > 0: - sd_models.apply_token_merging(sd_model=p.sd_model, hr=False) - logger.debug(f"Token merging applied to first pass. Ratio: '{opts.token_merging_ratio}'") + sd_models.apply_token_merging(p.sd_model, p.get_token_merging_ratio()) res = process_images_inner(p) finally: - # undo model optimizations made by tomesd - if opts.token_merging_ratio > 0: - tomesd.remove_patch(p.sd_model) - logger.debug('Token merging model optimizations removed') + sd_models.apply_token_merging(p.sd_model, 0) # restore opts to original state if p.override_settings_restore_afterwards: @@ -996,21 +1001,11 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): x = None devices.torch_gc() - # apply token merging optimizations from tomesd for high-res pass - if opts.token_merging_ratio_hr > 0: - # in case the user has used separate merge ratios - if opts.token_merging_ratio > 0: - tomesd.remove_patch(self.sd_model) - logger.debug('Adjusting token merging ratio for high-res pass') - - sd_models.apply_token_merging(sd_model=self.sd_model, hr=True) - logger.debug(f"Applied token merging for high-res pass. Ratio: '{opts.token_merging_ratio_hr}'") + sd_models.apply_token_merging(self.sd_model, self.get_token_merging_ratio(for_hr=True)) samples = self.sampler.sample_img2img(self, samples, noise, conditioning, unconditional_conditioning, steps=self.hr_second_pass_steps or self.steps, image_conditioning=image_conditioning) - if opts.token_merging_ratio_hr > 0 or opts.token_merging_ratio > 0: - tomesd.remove_patch(self.sd_model) - logger.debug('Removed token merging optimizations from model') + sd_models.apply_token_merging(self.sd_model, self.get_token_merging_ratio()) self.is_hr_pass = False @@ -1173,3 +1168,6 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing): devices.torch_gc() return samples + + def get_token_merging_ratio(self, for_hr=False): + return self.token_merging_ratio or ("token_merging_ratio" in self.override_settings and opts.token_merging_ratio) or opts.token_merging_ratio_img2img or opts.token_merging_ratio diff --git a/modules/progress.py b/modules/progress.py index 269863c9..f405f07f 100644 --- a/modules/progress.py +++ b/modules/progress.py @@ -98,7 +98,11 @@ def progressapi(req: ProgressRequest): if opts.live_previews_image_format == "png": # using optimize for large images takes an enormous amount of time - save_kwargs = {"optimize": max(*image.size) > 256} + if max(*image.size) <= 256: + save_kwargs = {"optimize": True} + else: + save_kwargs = {"optimize": False, "compress_level": 1} + else: save_kwargs = {} diff --git a/modules/sd_models.py b/modules/sd_models.py index e612be10..4bd8783e 100644 --- a/modules/sd_models.py +++ b/modules/sd_models.py @@ -583,23 +583,27 @@ def unload_model_weights(sd_model=None, info=None): return sd_model -def apply_token_merging(sd_model, hr: bool): +def apply_token_merging(sd_model, token_merging_ratio): """ Applies speed and memory optimizations from tomesd. - - Args: - hr (bool): True if called in the context of a high-res pass """ - ratio = shared.opts.token_merging_ratio - if hr: - ratio = shared.opts.token_merging_ratio_hr - - tomesd.apply_patch( - sd_model, - ratio=ratio, - use_rand=False, # can cause issues with some samplers - merge_attn=True, - merge_crossattn=False, - merge_mlp=False - ) + current_token_merging_ratio = getattr(sd_model, 'applied_token_merged_ratio', 0) + + if current_token_merging_ratio == token_merging_ratio: + return + + if current_token_merging_ratio > 0: + tomesd.remove_patch(sd_model) + + if token_merging_ratio > 0: + tomesd.apply_patch( + sd_model, + ratio=token_merging_ratio, + use_rand=False, # can cause issues with some samplers + merge_attn=True, + merge_crossattn=False, + merge_mlp=False + ) + + sd_model.applied_token_merged_ratio = token_merging_ratio diff --git a/modules/shared.py b/modules/shared.py index 47bc6d0e..76af8b9c 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -413,8 +413,13 @@ options_templates.update(options_section(('sd', "Stable Diffusion"), { "CLIP_stop_at_last_layers": OptionInfo(1, "Clip skip", gr.Slider, {"minimum": 1, "maximum": 12, "step": 1}).link("wiki", "https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#clip-skip").info("ignore last layers of CLIP nrtwork; 1 ignores none, 2 ignores one layer"), "upcast_attn": OptionInfo(False, "Upcast cross attention layer to float32"), "randn_source": OptionInfo("GPU", "Random number generator source.", gr.Radio, {"choices": ["GPU", "CPU"]}).info("changes seeds drastically; use CPU to produce the same picture across different vidocard vendors"), +})) + +options_templates.update(options_section(('optimizations', "Optimizations"), { + "s_min_uncond": OptionInfo(0, "Negative Guidance minimum sigma", gr.Slider, {"minimum": 0.0, "maximum": 4.0, "step": 0.01}).link("PR", "https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/9177").info("skip negative prompt for some steps when the image is almost ready; 0=disable, higher=faster"), "token_merging_ratio": OptionInfo(0.0, "Token merging ratio", gr.Slider, {"minimum": 0.0, "maximum": 0.9, "step": 0.1}).link("PR", "https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/9256").info("0=disable, higher=faster"), - "token_merging_ratio_hr": OptionInfo(0.0, "Togen merging ratio for high-res pass", gr.Slider, {"minimum": 0.0, "maximum": 0.9, "step": 0.1}), + "token_merging_ratio_img2img": OptionInfo(0.0, "Token merging ratio for img2img", gr.Slider, {"minimum": 0.0, "maximum": 0.9, "step": 0.1}).info("only applies if non-zero and overrides above"), + "token_merging_ratio_hr": OptionInfo(0.0, "Token merging ratio for high-res pass", gr.Slider, {"minimum": 0.0, "maximum": 0.9, "step": 0.1}).info("only applies if non-zero and overrides above"), })) options_templates.update(options_section(('compatibility', "Compatibility"), { @@ -498,7 +503,6 @@ options_templates.update(options_section(('sampler-params', "Sampler parameters" "eta_ddim": OptionInfo(0.0, "Eta for DDIM", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}).info("noise multiplier; higher = more unperdictable results"), "eta_ancestral": OptionInfo(1.0, "Eta for ancestral samplers", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}).info("noise multiplier; applies to Euler a and other samplers that have a in them"), "ddim_discretize": OptionInfo('uniform', "img2img DDIM discretize", gr.Radio, {"choices": ['uniform', 'quad']}), - 's_min_uncond': OptionInfo(0, "Negative Guidance minimum sigma", gr.Slider, {"minimum": 0.0, "maximum": 4.0, "step": 0.01}).link("PR", "https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/9177").info("skip negative prompt for some steps when the image is almost ready; 0=disable, higher=faster"), 's_churn': OptionInfo(0.0, "sigma churn", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}), 's_tmin': OptionInfo(0.0, "sigma tmin", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}), 's_noise': OptionInfo(1.0, "sigma noise", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}), -- cgit v1.2.3 From 44c37f94e176667ccdfeb74916e4640fa9dc586d Mon Sep 17 00:00:00 2001 From: AUTOMATIC <16777216c@gmail.com> Date: Thu, 18 May 2023 16:36:30 +0300 Subject: add messages about Loras that failed to load to UI --- extensions-builtin/Lora/lora.py | 8 +++++++- modules/processing.py | 2 +- 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'modules/processing.py') diff --git a/extensions-builtin/Lora/lora.py b/extensions-builtin/Lora/lora.py index 1308c48b..fa57d466 100644 --- a/extensions-builtin/Lora/lora.py +++ b/extensions-builtin/Lora/lora.py @@ -3,7 +3,7 @@ import re import torch from typing import Union -from modules import shared, devices, sd_models, errors, scripts +from modules import shared, devices, sd_models, errors, scripts, sd_hijack metadata_tags_order = {"ss_sd_model_name": 1, "ss_resolution": 2, "ss_clip_skip": 3, "ss_num_train_images": 10, "ss_tag_frequency": 20} @@ -211,6 +211,8 @@ def load_loras(names, multipliers=None): loras_on_disk = [available_lora_aliases.get(name, None) for name in names] + failed_to_load_loras = [] + for i, name in enumerate(names): lora = already_loaded.get(name, None) @@ -224,12 +226,16 @@ def load_loras(names, multipliers=None): continue if lora is None: + failed_to_load_loras.append(name) print(f"Couldn't find Lora with name {name}") continue lora.multiplier = multipliers[i] if multipliers else 1.0 loaded_loras.append(lora) + if len(failed_to_load_loras) > 0: + sd_hijack.model_hijack.comments.append("Failed to find Loras: " + ", ".join(failed_to_load_loras)) + def lora_calc_updown(lora, module, target): with torch.no_grad(): diff --git a/modules/processing.py b/modules/processing.py index 2b8dd361..7ee6da28 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -808,7 +808,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: images_list=output_images, seed=p.all_seeds[0], info=infotext(), - comments="".join(f"\n\n{comment}" for comment in comments), + comments="".join(f"{comment}\n" for comment in comments), subseed=p.all_subseeds[0], index_of_first_image=index_of_first_image, infotexts=infotexts, -- cgit v1.2.3 From ff0e17174f8d93a71fdd5a4a80a4629bbf97f822 Mon Sep 17 00:00:00 2001 From: AUTOMATIC <16777216c@gmail.com> Date: Thu, 18 May 2023 20:16:09 +0300 Subject: rework hires prompts/sampler code to among other things support different extra networks in first/second pass rework quoting for infotext items that have commas in them to use json (should be backwards compatible except for cases where it didn't work previously) add some locals from processing function into the Processing class as fields --- modules/generation_parameters_copypaste.py | 36 ++-- modules/processing.py | 261 ++++++++++++++++------------- modules/shared.py | 6 +- modules/txt2img.py | 4 +- modules/ui.py | 14 +- 5 files changed, 188 insertions(+), 133 deletions(-) (limited to 'modules/processing.py') diff --git a/modules/generation_parameters_copypaste.py b/modules/generation_parameters_copypaste.py index b34046a0..d5f0a49b 100644 --- a/modules/generation_parameters_copypaste.py +++ b/modules/generation_parameters_copypaste.py @@ -1,5 +1,6 @@ import base64 import io +import json import os import re @@ -34,13 +35,20 @@ def reset(): def quote(text): - if ',' not in str(text): + if ',' not in str(text) and '\n' not in str(text): return text - text = str(text) - text = text.replace('\\', '\\\\') - text = text.replace('"', '\\"') - return f'"{text}"' + return json.dumps(text, ensure_ascii=False) + + +def unquote(text): + if len(text) == 0 or text[0] != '"' or text[-1] != '"': + return text + + try: + return json.loads(text) + except Exception: + return text def image_from_url_text(filedata): @@ -261,7 +269,9 @@ Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 965400086, Size: 512x512, Model res["Negative prompt"] = negative_prompt for k, v in re_param.findall(lastline): - v = v[1:-1] if v[0] == '"' and v[-1] == '"' else v + if v[0] == '"' and v[-1] == '"': + v = unquote(v) + m = re_imagesize.match(v) if m is not None: res[f"{k}-1"] = m.group(1) @@ -269,11 +279,6 @@ Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 965400086, Size: 512x512, Model else: res[k] = v - if k.startswith("Hires prompt"): - res["Hires prompt"] = v[1:][:-1].replace(';', ',') - elif k.startswith("Hires negative prompt"): - res["Hires negative prompt"] = v[1:][:-1].replace(';', ',') - # Missing CLIP skip means it was set to 1 (the default) if "Clip skip" not in res: res["Clip skip"] = "1" @@ -286,6 +291,15 @@ Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 965400086, Size: 512x512, Model res["Hires resize-1"] = 0 res["Hires resize-2"] = 0 + if "Hires sampler" not in res: + res["Hires sampler"] = "Use same sampler" + + if "Hires prompt" not in res: + res["Hires prompt"] = "" + + if "Hires negative prompt" not in res: + res["Hires negative prompt"] = "" + restore_old_hires_fix_params(res) # Missing RNG means the default was set, which is GPU RNG diff --git a/modules/processing.py b/modules/processing.py index dd14c486..29a3743f 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -169,6 +169,16 @@ class StableDiffusionProcessing: self.is_hr_pass = False self.sampler = None + self.prompts = None + self.negative_prompts = None + self.seeds = None + self.subseeds = None + + self.step_multiplier = 1 + self.cached_uc = [None, None] + self.cached_c = [None, None] + self.uc = None + self.c = None @property def sd_model(self): @@ -271,11 +281,15 @@ class StableDiffusionProcessing: def init(self, all_prompts, all_seeds, all_subseeds): pass - def sample(self, conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength, prompts, hr_conditioning=None, hr_unconditional_conditioning=None): + def sample(self, conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength, prompts): raise NotImplementedError() def close(self): self.sampler = None + self.c = None + self.uc = None + self.cached_c = [None, None] + self.cached_uc = [None, None] def get_token_merging_ratio(self, for_hr=False): if for_hr: @@ -283,6 +297,52 @@ class StableDiffusionProcessing: return self.token_merging_ratio or opts.token_merging_ratio + def setup_prompts(self): + if type(self.prompt) == list: + self.all_prompts = self.prompt + else: + self.all_prompts = self.batch_size * self.n_iter * [self.prompt] + + if type(self.negative_prompt) == list: + self.all_negative_prompts = self.negative_prompt + else: + self.all_negative_prompts = self.batch_size * self.n_iter * [self.negative_prompt] + + self.all_prompts = [shared.prompt_styles.apply_styles_to_prompt(x, self.styles) for x in self.all_prompts] + self.all_negative_prompts = [shared.prompt_styles.apply_negative_styles_to_prompt(x, self.styles) for x in self.all_negative_prompts] + + def get_conds_with_caching(self, function, required_prompts, steps, cache): + """ + Returns the result of calling function(shared.sd_model, required_prompts, steps) + using a cache to store the result if the same arguments have been used before. + + cache is an array containing two elements. The first element is a tuple + representing the previously used arguments, or None if no arguments + have been used before. The second element is where the previously + computed result is stored. + """ + + if cache[0] is not None and (required_prompts, steps) == cache[0]: + return cache[1] + + with devices.autocast(): + cache[1] = function(shared.sd_model, required_prompts, steps) + + cache[0] = (required_prompts, steps) + return cache[1] + + def setup_conds(self): + sampler_config = sd_samplers.find_sampler_config(self.sampler_name) + self.step_multiplier = 2 if sampler_config and sampler_config.options.get("second_order", False) else 1 + + self.uc = self.get_conds_with_caching(prompt_parser.get_learned_conditioning, self.negative_prompts, self.steps * self.step_multiplier, self.cached_uc) + self.c = self.get_conds_with_caching(prompt_parser.get_multicond_learned_conditioning, self.prompts, self.steps * self.step_multiplier, self.cached_c) + + def parse_extra_network_prompts(self): + self.prompts, extra_network_data = extra_networks.parse_prompts(self.prompts) + + return extra_network_data + class Processed: def __init__(self, p: StableDiffusionProcessing, images_list, seed=-1, info="", subseed=None, all_prompts=None, all_negative_prompts=None, all_seeds=None, all_subseeds=None, index_of_first_image=0, infotexts=None, comments=""): @@ -582,29 +642,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: comments = {} - if type(p.prompt) == list: - p.all_prompts = [shared.prompt_styles.apply_styles_to_prompt(x, p.styles) for x in p.prompt] - else: - p.all_prompts = p.batch_size * p.n_iter * [shared.prompt_styles.apply_styles_to_prompt(p.prompt, p.styles)] - - if type(p.negative_prompt) == list: - p.all_negative_prompts = [shared.prompt_styles.apply_negative_styles_to_prompt(x, p.styles) for x in p.negative_prompt] - else: - p.all_negative_prompts = p.batch_size * p.n_iter * [shared.prompt_styles.apply_negative_styles_to_prompt(p.negative_prompt, p.styles)] - - if type(p) == StableDiffusionProcessingTxt2Img: - if p.enable_hr and p.hr_prompt == '': - p.all_hr_prompts, p.all_hr_negative_prompts = p.all_prompts, p.all_negative_prompts - elif p.enable_hr and p.hr_prompt != '': - if type(p.prompt) == list: - p.all_hr_prompts = [shared.prompt_styles.apply_styles_to_prompt(x, p.styles) for x in p.hr_prompt] - else: - p.all_hr_prompts = p.batch_size * p.n_iter * [shared.prompt_styles.apply_styles_to_prompt(p.hr_prompt, p.styles)] - - if type(p.negative_prompt) == list: - p.all_hr_negative_prompts = [shared.prompt_styles.apply_negative_styles_to_prompt(x, p.styles) for x in p.hr_negative_prompt] - else: - p.all_hr_negative_prompts = p.batch_size * p.n_iter * [shared.prompt_styles.apply_negative_styles_to_prompt(p.hr_negative_prompt, p.styles)] + p.setup_prompts() if type(seed) == list: p.all_seeds = seed @@ -628,29 +666,6 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: infotexts = [] output_images = [] - cached_uc = [None, None] - cached_c = [None, None] - - def get_conds_with_caching(function, required_prompts, steps, cache): - """ - Returns the result of calling function(shared.sd_model, required_prompts, steps) - using a cache to store the result if the same arguments have been used before. - - cache is an array containing two elements. The first element is a tuple - representing the previously used arguments, or None if no arguments - have been used before. The second element is where the previously - computed result is stored. - """ - - if cache[0] is not None and (required_prompts, steps) == cache[0]: - return cache[1] - - with devices.autocast(): - cache[1] = function(shared.sd_model, required_prompts, steps) - - cache[0] = (required_prompts, steps) - return cache[1] - with torch.no_grad(), p.sd_model.ema_scope(): with devices.autocast(): p.init(p.all_prompts, p.all_seeds, p.all_subseeds) @@ -672,40 +687,25 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: if state.interrupted: break - prompts = p.all_prompts[n * p.batch_size:(n + 1) * p.batch_size] - negative_prompts = p.all_negative_prompts[n * p.batch_size:(n + 1) * p.batch_size] - - if type(p) == StableDiffusionProcessingTxt2Img: - if p.enable_hr: - if p.hr_prompt == '': - hr_prompts, hr_negative_prompts = prompts, negative_prompts - else: - hr_prompts = p.all_hr_prompts[n * p.batch_size:(n + 1) * p.batch_size] - hr_negative_prompts = p.all_hr_negative_prompts[n * p.batch_size:(n + 1) * p.batch_size] - - seeds = p.all_seeds[n * p.batch_size:(n + 1) * p.batch_size] - subseeds = p.all_subseeds[n * p.batch_size:(n + 1) * p.batch_size] + p.prompts = p.all_prompts[n * p.batch_size:(n + 1) * p.batch_size] + p.negative_prompts = p.all_negative_prompts[n * p.batch_size:(n + 1) * p.batch_size] + p.seeds = p.all_seeds[n * p.batch_size:(n + 1) * p.batch_size] + p.subseeds = p.all_subseeds[n * p.batch_size:(n + 1) * p.batch_size] if p.scripts is not None: - p.scripts.before_process_batch(p, batch_number=n, prompts=prompts, seeds=seeds, subseeds=subseeds) + p.scripts.before_process_batch(p, batch_number=n, prompts=p.prompts, seeds=p.seeds, subseeds=p.subseeds) - if len(prompts) == 0: + if len(p.prompts) == 0: break - prompts, extra_network_data = extra_networks.parse_prompts(prompts) - - if type(p) == StableDiffusionProcessingTxt2Img: - if p.enable_hr and hr_prompts != prompts: - _, hr_extra_network_data = extra_networks.parse_prompts(hr_prompts) - extra_network_data.update(hr_extra_network_data) - + extra_network_data = p.parse_extra_network_prompts() if not p.disable_extra_networks: with devices.autocast(): extra_networks.activate(p, extra_network_data) if p.scripts is not None: - p.scripts.process_batch(p, batch_number=n, prompts=prompts, seeds=seeds, subseeds=subseeds) + p.scripts.process_batch(p, batch_number=n, prompts=p.prompts, seeds=p.seeds, subseeds=p.subseeds) # params.txt should be saved after scripts.process_batch, since the # infotext could be modified by that callback @@ -716,18 +716,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: processed = Processed(p, [], p.seed, "") file.write(processed.infotext(p, 0)) - sampler_config = sd_samplers.find_sampler_config(p.sampler_name) - step_multiplier = 2 if sampler_config and sampler_config.options.get("second_order", False) else 1 - uc = get_conds_with_caching(prompt_parser.get_learned_conditioning, negative_prompts, p.steps * step_multiplier, cached_uc) - c = get_conds_with_caching(prompt_parser.get_multicond_learned_conditioning, prompts, p.steps * step_multiplier, cached_c) - - if type(p) == StableDiffusionProcessingTxt2Img: - if p.enable_hr: - if prompts != hr_prompts: - hr_uc = get_conds_with_caching(prompt_parser.get_learned_conditioning, hr_negative_prompts, p.steps, cached_uc) - hr_c = get_conds_with_caching(prompt_parser.get_multicond_learned_conditioning, hr_prompts, p.steps, cached_c) - else: - hr_uc, hr_c = uc, c + p.setup_conds() if len(model_hijack.comments) > 0: for comment in model_hijack.comments: @@ -736,15 +725,8 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: if p.n_iter > 1: shared.state.job = f"Batch {n+1} out of {p.n_iter}" - with devices.without_autocast() if devices.unet_needs_upcast else devices.autocast(): - if type(p) == StableDiffusionProcessingTxt2Img: - if p.enable_hr: - samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, hr_conditioning=hr_c, hr_unconditional_conditioning=hr_uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength, prompts=prompts) - else: - samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength, prompts=prompts) - else: - samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength, prompts=prompts) + samples_ddim = p.sample(conditioning=p.c, unconditional_conditioning=p.uc, seeds=p.seeds, subseeds=p.subseeds, subseed_strength=p.subseed_strength, prompts=p.prompts) x_samples_ddim = [decode_first_stage(p.sd_model, samples_ddim[i:i+1].to(dtype=devices.dtype_vae))[0].cpu() for i in range(samples_ddim.size(0))] for x in x_samples_ddim: @@ -771,7 +753,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: if p.restore_faces: if opts.save and not p.do_not_save_samples and opts.save_images_before_face_restoration: - images.save_image(Image.fromarray(x_sample), p.outpath_samples, "", seeds[i], prompts[i], opts.samples_format, info=infotext(n, i), p=p, suffix="-before-face-restoration") + images.save_image(Image.fromarray(x_sample), p.outpath_samples, "", p.seeds[i], p.prompts[i], opts.samples_format, info=infotext(n, i), p=p, suffix="-before-face-restoration") devices.torch_gc() @@ -788,13 +770,13 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: if p.color_corrections is not None and i < len(p.color_corrections): if opts.save and not p.do_not_save_samples and opts.save_images_before_color_correction: image_without_cc = apply_overlay(image, p.paste_to, i, p.overlay_images) - images.save_image(image_without_cc, p.outpath_samples, "", seeds[i], prompts[i], opts.samples_format, info=infotext(n, i), p=p, suffix="-before-color-correction") + images.save_image(image_without_cc, p.outpath_samples, "", p.seeds[i], p.prompts[i], opts.samples_format, info=infotext(n, i), p=p, suffix="-before-color-correction") image = apply_color_correction(p.color_corrections[i], image) image = apply_overlay(image, p.paste_to, i, p.overlay_images) if opts.samples_save and not p.do_not_save_samples: - images.save_image(image, p.outpath_samples, "", seeds[i], prompts[i], opts.samples_format, info=infotext(n, i), p=p) + images.save_image(image, p.outpath_samples, "", p.seeds[i], p.prompts[i], opts.samples_format, info=infotext(n, i), p=p) text = infotext(n, i) infotexts.append(text) @@ -807,10 +789,10 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: image_mask_composite = Image.composite(image.convert('RGBA').convert('RGBa'), Image.new('RGBa', image.size), images.resize_image(2, p.mask_for_overlay, image.width, image.height).convert('L')).convert('RGBA') if opts.save_mask: - images.save_image(image_mask, p.outpath_samples, "", seeds[i], prompts[i], opts.samples_format, info=infotext(n, i), p=p, suffix="-mask") + images.save_image(image_mask, p.outpath_samples, "", p.seeds[i], p.prompts[i], opts.samples_format, info=infotext(n, i), p=p, suffix="-mask") if opts.save_mask_composite: - images.save_image(image_mask_composite, p.outpath_samples, "", seeds[i], prompts[i], opts.samples_format, info=infotext(n, i), p=p, suffix="-mask-composite") + images.save_image(image_mask_composite, p.outpath_samples, "", p.seeds[i], p.prompts[i], opts.samples_format, info=infotext(n, i), p=p, suffix="-mask-composite") if opts.return_mask: output_images.append(image_mask) @@ -879,7 +861,7 @@ def old_hires_fix_first_pass_dimensions(width, height): class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): sampler = None - def __init__(self, enable_hr: bool = False, denoising_strength: float = 0.75, firstphase_width: int = 0, firstphase_height: int = 0, hr_scale: float = 2.0, hr_upscaler: str = None, hr_second_pass_steps: int = 0, hr_resize_x: int = 0, hr_resize_y: int = 0, hr_sampler: str = '---', hr_prompt: str = '', hr_negative_prompt: str = '', **kwargs): + def __init__(self, enable_hr: bool = False, denoising_strength: float = 0.75, firstphase_width: int = 0, firstphase_height: int = 0, hr_scale: float = 2.0, hr_upscaler: str = None, hr_second_pass_steps: int = 0, hr_resize_x: int = 0, hr_resize_y: int = 0, hr_sampler_name: str = None, hr_prompt: str = '', hr_negative_prompt: str = '', **kwargs): super().__init__(**kwargs) self.enable_hr = enable_hr self.denoising_strength = denoising_strength @@ -890,9 +872,9 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): self.hr_resize_y = hr_resize_y self.hr_upscale_to_x = hr_resize_x self.hr_upscale_to_y = hr_resize_y - self.hr_sampler = hr_sampler - self.hr_prompt = hr_prompt if hr_prompt != '' else '' - self.hr_negative_prompt = hr_negative_prompt if hr_negative_prompt != '' else '' + self.hr_sampler_name = hr_sampler_name + self.hr_prompt = hr_prompt + self.hr_negative_prompt = hr_negative_prompt self.all_hr_prompts = None self.all_hr_negative_prompts = None @@ -906,14 +888,23 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): self.truncate_y = 0 self.applied_old_hires_behavior_to = None + self.hr_prompts = None + self.hr_negative_prompts = None + self.hr_extra_network_data = None + + self.hr_c = None + self.hr_uc = None + def init(self, all_prompts, all_seeds, all_subseeds): if self.enable_hr: - if self.hr_sampler != '---': - self.extra_generation_params["Hires sampler"] = self.hr_sampler + if self.hr_sampler_name is not None and self.hr_sampler_name != self.sampler_name: + self.extra_generation_params["Hires sampler"] = self.hr_sampler_name + + if tuple(self.hr_prompt) != tuple(self.prompt): + self.extra_generation_params["Hires prompt"] = self.hr_prompt - if self.hr_prompt != '': - self.extra_generation_params["Hires prompt"] = f'({self.hr_prompt.replace(",", ";")})' - self.extra_generation_params["Hires negative prompt"] = f'({self.hr_negative_prompt.replace(",", ";")})' + if tuple(self.hr_negative_prompt) != tuple(self.negative_prompt): + self.extra_generation_params["Hires negative prompt"] = self.hr_negative_prompt if opts.use_old_hires_fix_width_height and self.applied_old_hires_behavior_to != (self.width, self.height): self.hr_resize_x = self.width @@ -975,7 +966,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): if self.hr_upscaler is not None: self.extra_generation_params["Hires upscaler"] = self.hr_upscaler - def sample(self, conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength, prompts, hr_conditioning=None, hr_unconditional_conditioning=None): + def sample(self, conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength, prompts): self.sampler = sd_samplers.create_sampler(self.sampler_name, self.sd_model) latent_scale_mode = shared.latent_upscale_modes.get(self.hr_upscaler, None) if self.hr_upscaler is not None else shared.latent_upscale_modes.get(shared.latent_upscale_default_mode, "nearest") @@ -1044,16 +1035,11 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): shared.state.nextjob() - img2img_sampler_name = self.sampler_name + img2img_sampler_name = self.hr_sampler_name or self.sampler_name if self.sampler_name in ['PLMS', 'UniPC']: # PLMS/UniPC do not support img2img so we just silently switch to DDIM img2img_sampler_name = 'DDIM' - if self.hr_sampler == '---': - pass - else: - img2img_sampler_name = self.hr_sampler - self.sampler = sd_samplers.create_sampler(img2img_sampler_name, self.sd_model) samples = samples[:, :, self.truncate_y//2:samples.shape[2]-(self.truncate_y+1)//2, self.truncate_x//2:samples.shape[3]-(self.truncate_x+1)//2] @@ -1064,9 +1050,13 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): x = None devices.torch_gc() + if not self.disable_extra_networks: + with devices.autocast(): + extra_networks.activate(self, self.hr_extra_network_data) + sd_models.apply_token_merging(self.sd_model, self.get_token_merging_ratio(for_hr=True)) - samples = self.sampler.sample_img2img(self, samples, noise, hr_conditioning, hr_unconditional_conditioning, steps=self.hr_second_pass_steps or self.steps, image_conditioning=image_conditioning) + samples = self.sampler.sample_img2img(self, samples, noise, self.hr_c, self.hr_uc, steps=self.hr_second_pass_steps or self.steps, image_conditioning=image_conditioning) sd_models.apply_token_merging(self.sd_model, self.get_token_merging_ratio()) @@ -1074,6 +1064,53 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): return samples + def close(self): + self.hr_c = None + self.hr_uc = None + + def setup_prompts(self): + super().setup_prompts() + + if not self.enable_hr: + return + + if self.hr_prompt == '': + self.hr_prompt = self.prompt + + if self.hr_negative_prompt == '': + self.hr_negative_prompt = self.negative_prompt + + if type(self.hr_prompt) == list: + self.all_hr_prompts = self.hr_prompt + else: + self.all_hr_prompts = self.batch_size * self.n_iter * [self.hr_prompt] + + if type(self.hr_negative_prompt) == list: + self.all_hr_negative_prompts = self.hr_negative_prompt + else: + self.all_hr_negative_prompts = self.batch_size * self.n_iter * [self.hr_negative_prompt] + + self.all_hr_prompts = [shared.prompt_styles.apply_styles_to_prompt(x, self.styles) for x in self.all_hr_prompts] + self.all_hr_negative_prompts = [shared.prompt_styles.apply_negative_styles_to_prompt(x, self.styles) for x in self.all_hr_negative_prompts] + + def setup_conds(self): + super().setup_conds() + + if self.enable_hr: + self.hr_uc = self.get_conds_with_caching(prompt_parser.get_learned_conditioning, self.hr_negative_prompts, self.steps * self.step_multiplier, self.cached_uc) + self.hr_c = self.get_conds_with_caching(prompt_parser.get_multicond_learned_conditioning, self.hr_prompts, self.steps * self.step_multiplier, self.cached_c) + + def parse_extra_network_prompts(self): + res = super().parse_extra_network_prompts() + + if self.enable_hr: + self.hr_prompts = self.all_hr_prompts[self.iteration * self.batch_size:(self.iteration + 1) * self.batch_size] + self.hr_negative_prompts = self.all_hr_negative_prompts[self.iteration * self.batch_size:(self.iteration + 1) * self.batch_size] + + self.hr_prompts, self.hr_extra_network_data = extra_networks.parse_prompts(self.hr_prompts) + + return res + class StableDiffusionProcessingImg2Img(StableDiffusionProcessing): sampler = None diff --git a/modules/shared.py b/modules/shared.py index 9e9e8cd4..fdbab5c4 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -454,6 +454,7 @@ options_templates.update(options_section(('extra_networks', "Extra Networks"), { "extra_networks_card_width": OptionInfo(0, "Card width for Extra Networks").info("in pixels"), "extra_networks_card_height": OptionInfo(0, "Card height for Extra Networks").info("in pixels"), "extra_networks_add_text_separator": OptionInfo(" ", "Extra networks separator").info("extra text to add before <...> when adding extra network to prompt"), + "ui_extra_networks_tab_reorder": OptionInfo("", "Extra networks tab order").needs_restart(), "sd_hypernetwork": OptionInfo("None", "Add hypernetwork to prompt", gr.Dropdown, lambda: {"choices": ["None", *hypernetworks]}, refresh=reload_hypernetworks), })) @@ -481,8 +482,9 @@ options_templates.update(options_section(('ui', "User interface"), { "quicksettings_list": OptionInfo(["sd_model_checkpoint"], "Quicksettings list", ui_components.DropdownMulti, lambda: {"choices": list(opts.data_labels.keys())}).js("info", "settingsHintsShowQuicksettings").info("setting entries that appear at the top of page rather than in settings tab").needs_restart(), "ui_tab_order": OptionInfo([], "UI tab order", ui_components.DropdownMulti, lambda: {"choices": list(tab_names)}).needs_restart(), "hidden_tabs": OptionInfo([], "Hidden UI tabs", ui_components.DropdownMulti, lambda: {"choices": list(tab_names)}).needs_restart(), - "ui_reorder": OptionInfo(", ".join(ui_reorder_categories), "txt2img/img2img UI item order"), - "ui_extra_networks_tab_reorder": OptionInfo("", "Extra networks tab order").needs_restart(), + "ui_reorder": OptionInfo(", ".join(ui_reorder_categories), "txt2img/img2img UI item order").needs_restart(), + "hires_fix_show_sampler": OptionInfo(False, "Hires fix: show hires sampler selection").needs_restart(), + "hires_fix_show_prompts": OptionInfo(False, "Hires fix: show hires prompt and negative prompt").needs_restart(), })) options_templates.update(options_section(('infotext', "Infotext"), { diff --git a/modules/txt2img.py b/modules/txt2img.py index 3b4c985e..2e7d202d 100644 --- a/modules/txt2img.py +++ b/modules/txt2img.py @@ -9,7 +9,7 @@ from modules.ui import plaintext_to_html def txt2img(id_task: str, prompt: str, negative_prompt: str, prompt_styles, steps: int, sampler_index: int, restore_faces: bool, tiling: bool, n_iter: int, batch_size: int, cfg_scale: float, seed: int, subseed: int, subseed_strength: float, seed_resize_from_h: int, seed_resize_from_w: int, seed_enable_extras: bool, height: int, width: int, enable_hr: bool, denoising_strength: float, hr_scale: float, hr_upscaler: str, hr_second_pass_steps: int, hr_resize_x: int, hr_resize_y: int, hr_sampler_index: int, hr_prompt: str, hr_negative_prompt, override_settings_texts, *args): override_settings = create_override_settings_dict(override_settings_texts) - + p = processing.StableDiffusionProcessingTxt2Img( sd_model=shared.sd_model, outpath_samples=opts.outdir_samples or opts.outdir_txt2img_samples, @@ -39,7 +39,7 @@ def txt2img(id_task: str, prompt: str, negative_prompt: str, prompt_styles, step hr_second_pass_steps=hr_second_pass_steps, hr_resize_x=hr_resize_x, hr_resize_y=hr_resize_y, - hr_sampler=sd_samplers.samplers_for_img2img[hr_sampler_index - 1].name if hr_sampler_index != 0 else '---', + hr_sampler_name=sd_samplers.samplers_for_img2img[hr_sampler_index - 1].name if hr_sampler_index != 0 else None, hr_prompt=hr_prompt, hr_negative_prompt=hr_negative_prompt, override_settings=override_settings, diff --git a/modules/ui.py b/modules/ui.py index c3ff48b4..2016ed74 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -499,16 +499,16 @@ def create_ui(): hr_resize_x = gr.Slider(minimum=0, maximum=2048, step=8, label="Resize width to", value=0, elem_id="txt2img_hr_resize_x") hr_resize_y = gr.Slider(minimum=0, maximum=2048, step=8, label="Resize height to", value=0, elem_id="txt2img_hr_resize_y") - with FormRow(elem_id="txt2img_hires_fix_row3", variant="compact"): - hr_sampler_index = gr.Dropdown(label='Hires sampling method', elem_id=f"hr_sampler", choices=["---"] + [x.name for x in samplers_for_img2img], value="---", type="index") + with FormRow(elem_id="txt2img_hires_fix_row3", variant="compact", visible=opts.hires_fix_show_sampler) as hr_sampler_container: + hr_sampler_index = gr.Dropdown(label='Hires sampling method', elem_id="hr_sampler", choices=["Use same sampler"] + [x.name for x in samplers_for_img2img], value="Use same sampler", type="index") - with FormRow(elem_id="txt2img_hires_fix_row4", variant="compact"): + with FormRow(elem_id="txt2img_hires_fix_row4", variant="compact", visible=opts.hires_fix_show_prompts) as hr_prompts_container: with gr.Column(scale=80): with gr.Row(): - hr_prompt = gr.Textbox(label="Prompt", elem_id=f"hires_prompt", show_label=False, lines=3, placeholder="Prompt that will be used for hires fix pass (leave it blank to use the same prompt as in initial txt2img gen)") + hr_prompt = gr.Textbox(label="Prompt", elem_id="hires_prompt", show_label=False, lines=3, placeholder="Prompt for hires fix pass.\nLeave empty to use the same prompt as in first pass.") with gr.Column(scale=80): with gr.Row(): - hr_negative_prompt = gr.Textbox(label="Negative prompt", elem_id=f"hires_neg_prompt", show_label=False, lines=3, placeholder="Negative prompt that will be used for hires fix pass (leave it blank to use the same prompt as in initial txt2img gen)") + hr_negative_prompt = gr.Textbox(label="Negative prompt", elem_id="hires_neg_prompt", show_label=False, lines=3, placeholder="Negative prompt for hires fix pass.\nLeave empty to use the same negative prompt as in first pass.") elif category == "batch": if not opts.dimensions_and_batch_together: @@ -646,9 +646,11 @@ def create_ui(): (hr_second_pass_steps, "Hires steps"), (hr_resize_x, "Hires resize-1"), (hr_resize_y, "Hires resize-2"), - (hr_sampler_index, "Hires sampling method"), + (hr_sampler_index, "Hires sampler"), + (hr_sampler_container, lambda d: gr.update(visible=True) if d.get("Hires sampler", "Use same sampler") != "Use same sampler" else gr.update()), (hr_prompt, "Hires prompt"), (hr_negative_prompt, "Hires negative prompt"), + (hr_prompts_container, lambda d: gr.update(visible=True) if d.get("Hires prompt", "") != "" or d.get("Hires negative prompt", "") != "" else gr.update()), *modules.scripts.scripts_txt2img.infotext_fields ] parameters_copypaste.add_paste_fields("txt2img", None, txt2img_paste_fields, override_settings) -- cgit v1.2.3