From 9feb034e343d6d7ef63395821658fb3774b30a24 Mon Sep 17 00:00:00 2001 From: wangqyqq Date: Thu, 21 Dec 2023 20:15:51 +0800 Subject: support for sdxl-inpaint model --- modules/processing.py | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'modules/processing.py') diff --git a/modules/processing.py b/modules/processing.py index 6f01c95f..159548db 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -106,6 +106,20 @@ def txt2img_image_conditioning(sd_model, x, width, height): return x.new_zeros(x.shape[0], 2*sd_model.noise_augmentor.time_embed.dim, dtype=x.dtype, device=x.device) else: + sd = sd_model.model.state_dict() + diffusion_model_input = sd.get('diffusion_model.input_blocks.0.0.weight', None) + if diffusion_model_input.shape[1] == 9: + # The "masked-image" in this case will just be all 0.5 since the entire image is masked. + image_conditioning = torch.ones(x.shape[0], 3, height, width, device=x.device) * 0.5 + image_conditioning = images_tensor_to_samples(image_conditioning, + approximation_indexes.get(opts.sd_vae_encode_method)) + + # Add the fake full 1s mask to the first dimension. + image_conditioning = torch.nn.functional.pad(image_conditioning, (0, 0, 0, 0, 1, 0), value=1.0) + image_conditioning = image_conditioning.to(x.dtype) + + return image_conditioning + # Dummy zero conditioning if we're not using inpainting or unclip models. # Still takes up a bit of memory, but no encoder call. # Pretty sure we can just make this a 1x1 image since its not going to be used besides its batch size. @@ -362,6 +376,11 @@ class StableDiffusionProcessing: if self.sampler.conditioning_key == "crossattn-adm": return self.unclip_image_conditioning(source_image) + sd = self.sampler.model_wrap.inner_model.model.state_dict() + diffusion_model_input = sd.get('diffusion_model.input_blocks.0.0.weight', None) + if diffusion_model_input.shape[1] == 9: + return self.inpainting_image_conditioning(source_image, latent_image, image_mask=image_mask) + # Dummy zero conditioning if we're not using inpainting or depth model. return latent_image.new_zeros(latent_image.shape[0], 5, 1, 1) -- cgit v1.2.3 From bfe418a58d39c69ca2672e7d8a1fd7ad2b34869b Mon Sep 17 00:00:00 2001 From: wangqyqq Date: Wed, 27 Dec 2023 10:20:56 +0800 Subject: add some codes for robust --- modules/processing.py | 24 +++++++++++++----------- modules/sd_models_xl.py | 5 +++-- 2 files changed, 16 insertions(+), 13 deletions(-) (limited to 'modules/processing.py') diff --git a/modules/processing.py b/modules/processing.py index 159548db..c05e608a 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -108,17 +108,18 @@ def txt2img_image_conditioning(sd_model, x, width, height): else: sd = sd_model.model.state_dict() diffusion_model_input = sd.get('diffusion_model.input_blocks.0.0.weight', None) - if diffusion_model_input.shape[1] == 9: - # The "masked-image" in this case will just be all 0.5 since the entire image is masked. - image_conditioning = torch.ones(x.shape[0], 3, height, width, device=x.device) * 0.5 - image_conditioning = images_tensor_to_samples(image_conditioning, - approximation_indexes.get(opts.sd_vae_encode_method)) + if diffusion_model_input is not None: + if diffusion_model_input.shape[1] == 9: + # The "masked-image" in this case will just be all 0.5 since the entire image is masked. + image_conditioning = torch.ones(x.shape[0], 3, height, width, device=x.device) * 0.5 + image_conditioning = images_tensor_to_samples(image_conditioning, + approximation_indexes.get(opts.sd_vae_encode_method)) - # Add the fake full 1s mask to the first dimension. - image_conditioning = torch.nn.functional.pad(image_conditioning, (0, 0, 0, 0, 1, 0), value=1.0) - image_conditioning = image_conditioning.to(x.dtype) + # Add the fake full 1s mask to the first dimension. + image_conditioning = torch.nn.functional.pad(image_conditioning, (0, 0, 0, 0, 1, 0), value=1.0) + image_conditioning = image_conditioning.to(x.dtype) - return image_conditioning + return image_conditioning # Dummy zero conditioning if we're not using inpainting or unclip models. # Still takes up a bit of memory, but no encoder call. @@ -378,8 +379,9 @@ class StableDiffusionProcessing: sd = self.sampler.model_wrap.inner_model.model.state_dict() diffusion_model_input = sd.get('diffusion_model.input_blocks.0.0.weight', None) - if diffusion_model_input.shape[1] == 9: - return self.inpainting_image_conditioning(source_image, latent_image, image_mask=image_mask) + if diffusion_model_input is not None: + if diffusion_model_input.shape[1] == 9: + return self.inpainting_image_conditioning(source_image, latent_image, image_mask=image_mask) # Dummy zero conditioning if we're not using inpainting or depth model. return latent_image.new_zeros(latent_image.shape[0], 5, 1, 1) diff --git a/modules/sd_models_xl.py b/modules/sd_models_xl.py index d8a9a73b..162d0fee 100644 --- a/modules/sd_models_xl.py +++ b/modules/sd_models_xl.py @@ -36,8 +36,9 @@ def get_learned_conditioning(self: sgm.models.diffusion.DiffusionEngine, batch: def apply_model(self: sgm.models.diffusion.DiffusionEngine, x, t, cond): sd = self.model.state_dict() diffusion_model_input = sd.get('diffusion_model.input_blocks.0.0.weight', None) - if diffusion_model_input.shape[1] == 9: - x = torch.cat([x] + cond['c_concat'], dim=1) + if diffusion_model_input is not None: + if diffusion_model_input.shape[1] == 9: + x = torch.cat([x] + cond['c_concat'], dim=1) return self.model(x, t, cond) -- cgit v1.2.3 From dc57ec0296e768ee91290e16ab262404837c566d Mon Sep 17 00:00:00 2001 From: w-e-w <40751091+w-e-w@users.noreply.github.com> Date: Fri, 29 Dec 2023 01:56:48 +0900 Subject: save info of init image --- 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 9351e3fb..141f2f11 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -1482,7 +1482,7 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing): # Save init image if opts.save_init_img: self.init_img_hash = hashlib.md5(img.tobytes()).hexdigest() - images.save_image(img, path=opts.outdir_init_images, basename=None, forced_filename=self.init_img_hash, save_to_dirs=False) + images.save_image(img, path=opts.outdir_init_images, basename=None, forced_filename=self.init_img_hash, save_to_dirs=False, existing_info=img.info) image = images.flatten(img, opts.img2img_background_color) -- cgit v1.2.3 From bb07cb6a0df60a96827125ffc09ea182a1ed272c Mon Sep 17 00:00:00 2001 From: AUTOMATIC1111 <16777216c@gmail.com> Date: Sun, 17 Dec 2023 10:22:03 +0300 Subject: a --- modules/api/api.py | 27 ++++++++++++++++++ modules/api/models.py | 2 ++ modules/generation_parameters_copypaste.py | 19 ++++++++++++ modules/processing.py | 2 +- modules/processing_scripts/refiner.py | 7 +++-- modules/processing_scripts/seed.py | 13 +++++---- modules/ui.py | 46 +++++++++++++++--------------- 7 files changed, 83 insertions(+), 33 deletions(-) (limited to 'modules/processing.py') diff --git a/modules/api/api.py b/modules/api/api.py index 7154c9d5..b3d70940 100644 --- a/modules/api/api.py +++ b/modules/api/api.py @@ -335,6 +335,29 @@ class Api: script_args[alwayson_script.args_from + idx] = request.alwayson_scripts[alwayson_script_name]["args"][idx] return script_args + def apply_infotext(self, request, tabname): + if not request.infotext: + return {} + + params = generation_parameters_copypaste.parse_generation_parameters(request.infotext) + + for field in generation_parameters_copypaste.paste_fields[tabname]["fields"]: + if not field.api: + continue + + value = field.function(params) if field.function else params.get(field.label) + target_type = request.__fields__[field.api].type_ + + if value is None: + continue + + if not isinstance(value, target_type): + value = target_type(value) + + setattr(request, field.api, value) + + return params + def text2imgapi(self, txt2imgreq: models.StableDiffusionTxt2ImgProcessingAPI): task_id = txt2imgreq.force_task_id or create_task_id("txt2img") @@ -342,6 +365,9 @@ class Api: if not script_runner.scripts: script_runner.initialize_scripts(False) ui.create_ui() + + infotext_params = self.apply_infotext(txt2imgreq, "txt2img") + if not self.default_script_arg_txt2img: self.default_script_arg_txt2img = self.init_default_script_args(script_runner) selectable_scripts, selectable_script_idx = self.get_selectable_script(txt2imgreq.script_name, script_runner) @@ -358,6 +384,7 @@ class Api: args.pop('script_name', None) args.pop('script_args', None) # will refeed them to the pipeline directly after initializing them args.pop('alwayson_scripts', None) + args.pop('infotext', None) script_args = self.init_script_args(txt2imgreq, self.default_script_arg_txt2img, selectable_scripts, selectable_script_idx, script_runner) diff --git a/modules/api/models.py b/modules/api/models.py index 58083a34..16edf11c 100644 --- a/modules/api/models.py +++ b/modules/api/models.py @@ -108,6 +108,7 @@ StableDiffusionTxt2ImgProcessingAPI = PydanticModelGenerator( {"key": "save_images", "type": bool, "default": False}, {"key": "alwayson_scripts", "type": dict, "default": {}}, {"key": "force_task_id", "type": str, "default": None}, + {"key": "infotext", "type": str, "default": None}, ] ).generate_model() @@ -126,6 +127,7 @@ StableDiffusionImg2ImgProcessingAPI = PydanticModelGenerator( {"key": "save_images", "type": bool, "default": False}, {"key": "alwayson_scripts", "type": dict, "default": {}}, {"key": "force_task_id", "type": str, "default": None}, + {"key": "infotext", "type": str, "default": None}, ] ).generate_model() diff --git a/modules/generation_parameters_copypaste.py b/modules/generation_parameters_copypaste.py index dbffe494..4b4727c4 100644 --- a/modules/generation_parameters_copypaste.py +++ b/modules/generation_parameters_copypaste.py @@ -28,6 +28,19 @@ class ParamBinding: self.paste_field_names = paste_field_names or [] +class PasteField(tuple): + def __new__(cls, component, target, *, api=None): + return super().__new__(cls, (component, target)) + + def __init__(self, component, target, *, api=None): + super().__init__() + + self.api = api + self.component = component + self.label = target if isinstance(target, str) else None + self.function = target if callable(target) else None + + paste_fields: dict[str, dict] = {} registered_param_bindings: list[ParamBinding] = [] @@ -84,6 +97,12 @@ def image_from_url_text(filedata): def add_paste_fields(tabname, init_img, fields, override_settings_component=None): + + if fields: + for i in range(len(fields)): + if not isinstance(fields[i], PasteField): + fields[i] = PasteField(*fields[i]) + paste_fields[tabname] = {"init_img": init_img, "fields": fields, "override_settings_component": override_settings_component} # backwards compatibility for existing extensions diff --git a/modules/processing.py b/modules/processing.py index 9351e3fb..ee2ccf46 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -1135,7 +1135,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): def init(self, all_prompts, all_seeds, all_subseeds): if self.enable_hr: - if self.hr_checkpoint_name: + if self.hr_checkpoint_name and self.hr_checkpoint_name != 'Use same checkpoint': self.hr_checkpoint_info = sd_models.get_closet_checkpoint_match(self.hr_checkpoint_name) if self.hr_checkpoint_info is None: diff --git a/modules/processing_scripts/refiner.py b/modules/processing_scripts/refiner.py index 29ccb78f..cefad32b 100644 --- a/modules/processing_scripts/refiner.py +++ b/modules/processing_scripts/refiner.py @@ -1,6 +1,7 @@ import gradio as gr from modules import scripts, sd_models +from modules.generation_parameters_copypaste import PasteField from modules.ui_common import create_refresh_button from modules.ui_components import InputAccordion @@ -31,9 +32,9 @@ class ScriptRefiner(scripts.ScriptBuiltinUI): return None if info is None else info.title self.infotext_fields = [ - (enable_refiner, lambda d: 'Refiner' in d), - (refiner_checkpoint, lambda d: lookup_checkpoint(d.get('Refiner'))), - (refiner_switch_at, 'Refiner switch at'), + PasteField(enable_refiner, lambda d: 'Refiner' in d), + PasteField(refiner_checkpoint, lambda d: lookup_checkpoint(d.get('Refiner')), api="refiner_checkpoint"), + PasteField(refiner_switch_at, 'Refiner switch at', api="refiner_switch_at"), ] return enable_refiner, refiner_checkpoint, refiner_switch_at diff --git a/modules/processing_scripts/seed.py b/modules/processing_scripts/seed.py index dc9c2da5..a3e16a12 100644 --- a/modules/processing_scripts/seed.py +++ b/modules/processing_scripts/seed.py @@ -3,6 +3,7 @@ import json import gradio as gr from modules import scripts, ui, errors +from modules.generation_parameters_copypaste import PasteField from modules.shared import cmd_opts from modules.ui_components import ToolButton @@ -51,12 +52,12 @@ class ScriptSeed(scripts.ScriptBuiltinUI): seed_checkbox.change(lambda x: gr.update(visible=x), show_progress=False, inputs=[seed_checkbox], outputs=[seed_extras]) self.infotext_fields = [ - (self.seed, "Seed"), - (seed_checkbox, lambda d: "Variation seed" in d or "Seed resize from-1" in d), - (subseed, "Variation seed"), - (subseed_strength, "Variation seed strength"), - (seed_resize_from_w, "Seed resize from-1"), - (seed_resize_from_h, "Seed resize from-2"), + PasteField(self.seed, "Seed", api="seed"), + PasteField(seed_checkbox, lambda d: "Variation seed" in d or "Seed resize from-1" in d), + PasteField(subseed, "Variation seed", api="subseed"), + PasteField(subseed_strength, "Variation seed strength", api="subseed_strength"), + PasteField(seed_resize_from_w, "Seed resize from-1", api="seed_resize_from_h"), + PasteField(seed_resize_from_h, "Seed resize from-2", api="seed_resize_from_w"), ] self.on_after_component(lambda x: connect_reuse_seed(self.seed, reuse_seed, x.component, False), elem_id=f'generation_info_{self.tabname}') diff --git a/modules/ui.py b/modules/ui.py index d80486dd..9db2407e 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -28,7 +28,7 @@ import modules.textual_inversion.textual_inversion as textual_inversion import modules.shared as shared from modules import prompt_parser from modules.sd_hijack import model_hijack -from modules.generation_parameters_copypaste import image_from_url_text +from modules.generation_parameters_copypaste import image_from_url_text, PasteField create_setting_component = ui_settings.create_setting_component @@ -436,28 +436,28 @@ def create_ui(): ) txt2img_paste_fields = [ - (toprow.prompt, "Prompt"), - (toprow.negative_prompt, "Negative prompt"), - (steps, "Steps"), - (sampler_name, "Sampler"), - (cfg_scale, "CFG scale"), - (width, "Size-1"), - (height, "Size-2"), - (batch_size, "Batch size"), - (toprow.ui_styles.dropdown, lambda d: d["Styles array"] if isinstance(d.get("Styles array"), list) else gr.update()), - (denoising_strength, "Denoising strength"), - (enable_hr, lambda d: "Denoising strength" in d and ("Hires upscale" in d or "Hires upscaler" in d or "Hires resize-1" in d)), - (hr_scale, "Hires upscale"), - (hr_upscaler, "Hires upscaler"), - (hr_second_pass_steps, "Hires steps"), - (hr_resize_x, "Hires resize-1"), - (hr_resize_y, "Hires resize-2"), - (hr_checkpoint_name, "Hires checkpoint"), - (hr_sampler_name, "Hires sampler"), - (hr_sampler_container, lambda d: gr.update(visible=True) if d.get("Hires sampler", "Use same sampler") != "Use same sampler" or d.get("Hires checkpoint", "Use same checkpoint") != "Use same checkpoint" 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()), + PasteField(toprow.prompt, "Prompt", api="prompt"), + PasteField(toprow.negative_prompt, "Negative prompt", api="negative_prompt"), + PasteField(steps, "Steps", api="steps"), + PasteField(sampler_name, "Sampler", api="sampler_name"), + PasteField(cfg_scale, "CFG scale", api="cfg_scale"), + PasteField(width, "Size-1", api="width"), + PasteField(height, "Size-2", api="height"), + PasteField(batch_size, "Batch size", api="batch_size"), + PasteField(toprow.ui_styles.dropdown, lambda d: d["Styles array"] if isinstance(d.get("Styles array"), list) else gr.update(), api="styles"), + PasteField(denoising_strength, "Denoising strength", api="denoising_strength"), + PasteField(enable_hr, lambda d: "Denoising strength" in d and ("Hires upscale" in d or "Hires upscaler" in d or "Hires resize-1" in d), api="enable_hr"), + PasteField(hr_scale, "Hires upscale", api="hr_scale"), + PasteField(hr_upscaler, "Hires upscaler", api="hr_upscaler"), + PasteField(hr_second_pass_steps, "Hires steps", api="hr_second_pass_steps"), + PasteField(hr_resize_x, "Hires resize-1", api="hr_resize_x"), + PasteField(hr_resize_y, "Hires resize-2", api="hr_resize_y"), + PasteField(hr_checkpoint_name, "Hires checkpoint", api="hr_checkpoint_name"), + PasteField(hr_sampler_name, "Hires sampler", api="hr_sampler_name"), + PasteField(hr_sampler_container, lambda d: gr.update(visible=True) if d.get("Hires sampler", "Use same sampler") != "Use same sampler" or d.get("Hires checkpoint", "Use same checkpoint") != "Use same checkpoint" else gr.update()), + PasteField(hr_prompt, "Hires prompt", api="hr_prompt"), + PasteField(hr_negative_prompt, "Hires negative prompt", api="hr_negative_prompt"), + PasteField(hr_prompts_container, lambda d: gr.update(visible=True) if d.get("Hires prompt", "") != "" or d.get("Hires negative prompt", "") != "" else gr.update()), *scripts.scripts_txt2img.infotext_fields ] parameters_copypaste.add_paste_fields("txt2img", None, txt2img_paste_fields, override_settings) -- cgit v1.2.3