From b32852ef037251eb3d846af76e2965594e1ac7a5 Mon Sep 17 00:00:00 2001 From: AUTOMATIC <16777216c@gmail.com> Date: Tue, 4 Oct 2022 20:49:54 +0300 Subject: add editor to img2img --- modules/ui.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'modules/ui.py') diff --git a/modules/ui.py b/modules/ui.py index 20dc8c37..6cd6761b 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -644,7 +644,7 @@ def create_ui(wrap_gradio_gpu_call): with gr.Tabs(elem_id="mode_img2img") as tabs_img2img_mode: with gr.TabItem('img2img', id='img2img'): - init_img = gr.Image(label="Image for img2img", show_label=False, source="upload", interactive=True, type="pil") + init_img = gr.Image(label="Image for img2img", elem_id="img2img_image", show_label=False, source="upload", interactive=True, type="pil", tool=cmd_opts.gradio_img2img_tool) with gr.TabItem('Inpaint', id='inpaint'): init_img_with_mask = gr.Image(label="Image for inpainting with mask", show_label=False, elem_id="img2maskimg", source="upload", interactive=True, type="pil", tool="sketch", image_mode="RGBA") -- cgit v1.2.3 From ef40e4cd4d383a3405e03f1da3f5b5a1820a8f53 Mon Sep 17 00:00:00 2001 From: xpscyho Date: Tue, 4 Oct 2022 15:12:38 -0400 Subject: Display time taken in mins, secs when relevant Fixes #1656 --- modules/ui.py | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'modules/ui.py') diff --git a/modules/ui.py b/modules/ui.py index 6cd6761b..de6342a4 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -196,6 +196,11 @@ def wrap_gradio_call(func, extra_outputs=None): res = extra_outputs_array + [f"
{plaintext_to_html(type(e).__name__+': '+str(e))}
"] elapsed = time.perf_counter() - t + elapsed_m = int(elapsed // 60) + elapsed_s = elapsed % 60 + elapsed_text = f"{elapsed_s:.2f}s" + if (elapsed_m > 0): + elapsed_text = f"{elapsed_m}m "+elapsed_text if run_memmon: mem_stats = {k: -(v//-(1024*1024)) for k, v in shared.mem_mon.stop().items()} @@ -210,7 +215,7 @@ def wrap_gradio_call(func, extra_outputs=None): vram_html = '' # last item is always HTML - res[-1] += f"

Time taken: {elapsed:.2f}s

{vram_html}
" + res[-1] += f"

Time taken: {elapsed_text}

{vram_html}
" shared.state.interrupted = False shared.state.job_count = 0 -- cgit v1.2.3 From bbdbbd36eda870cf0bd49fdf28476c78919a123e Mon Sep 17 00:00:00 2001 From: DepFA <35278260+dfaker@users.noreply.github.com> Date: Wed, 5 Oct 2022 04:43:05 +0100 Subject: shared.state.interrupt when restart is requested --- modules/ui.py | 1 + 1 file changed, 1 insertion(+) (limited to 'modules/ui.py') diff --git a/modules/ui.py b/modules/ui.py index de6342a4..523ab25b 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -1210,6 +1210,7 @@ def create_ui(wrap_gradio_gpu_call): ) def request_restart(): + shared.state.interrupt() settings_interface.gradio_ref.do_restart = True restart_gradio.click( -- cgit v1.2.3 From c26732fbee2a57e621ac22bf70decf7496daa4cd Mon Sep 17 00:00:00 2001 From: AUTOMATIC <16777216c@gmail.com> Date: Wed, 5 Oct 2022 23:16:27 +0300 Subject: added support for AND from https://energy-based-model.github.io/Compositional-Visual-Generation-with-Composable-Diffusion-Models/ --- modules/processing.py | 2 +- modules/prompt_parser.py | 114 ++++++++++++++++++++++++++++++++++++++++++++--- modules/sd_samplers.py | 35 ++++++++++----- modules/ui.py | 6 ++- 4 files changed, 138 insertions(+), 19 deletions(-) (limited to 'modules/ui.py') diff --git a/modules/processing.py b/modules/processing.py index bb94033b..d8c6b8d5 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -360,7 +360,7 @@ def process_images(p: StableDiffusionProcessing) -> Processed: #c = p.sd_model.get_learned_conditioning(prompts) with devices.autocast(): uc = prompt_parser.get_learned_conditioning(shared.sd_model, len(prompts) * [p.negative_prompt], p.steps) - c = prompt_parser.get_learned_conditioning(shared.sd_model, prompts, p.steps) + c = prompt_parser.get_multicond_learned_conditioning(shared.sd_model, prompts, p.steps) if len(model_hijack.comments) > 0: for comment in model_hijack.comments: diff --git a/modules/prompt_parser.py b/modules/prompt_parser.py index a3b12421..f7420daf 100644 --- a/modules/prompt_parser.py +++ b/modules/prompt_parser.py @@ -97,10 +97,26 @@ def get_learned_conditioning_prompt_schedules(prompts, steps): ScheduledPromptConditioning = namedtuple("ScheduledPromptConditioning", ["end_at_step", "cond"]) -ScheduledPromptBatch = namedtuple("ScheduledPromptBatch", ["shape", "schedules"]) def get_learned_conditioning(model, prompts, steps): + """converts a list of prompts into a list of prompt schedules - each schedule is a list of ScheduledPromptConditioning, specifying the comdition (cond), + and the sampling step at which this condition is to be replaced by the next one. + + Input: + (model, ['a red crown', 'a [blue:green:5] jeweled crown'], 20) + + Output: + [ + [ + ScheduledPromptConditioning(end_at_step=20, cond=tensor([[-0.3886, 0.0229, -0.0523, ..., -0.4901, -0.3066, 0.0674], ..., [ 0.3317, -0.5102, -0.4066, ..., 0.4119, -0.7647, -1.0160]], device='cuda:0')) + ], + [ + ScheduledPromptConditioning(end_at_step=5, cond=tensor([[-0.3886, 0.0229, -0.0522, ..., -0.4901, -0.3067, 0.0673], ..., [-0.0192, 0.3867, -0.4644, ..., 0.1135, -0.3696, -0.4625]], device='cuda:0')), + ScheduledPromptConditioning(end_at_step=20, cond=tensor([[-0.3886, 0.0229, -0.0522, ..., -0.4901, -0.3067, 0.0673], ..., [-0.7352, -0.4356, -0.7888, ..., 0.6994, -0.4312, -1.2593]], device='cuda:0')) + ] + ] + """ res = [] prompt_schedules = get_learned_conditioning_prompt_schedules(prompts, steps) @@ -123,13 +139,75 @@ def get_learned_conditioning(model, prompts, steps): cache[prompt] = cond_schedule res.append(cond_schedule) - return ScheduledPromptBatch((len(prompts),) + res[0][0].cond.shape, res) + return res + + +re_AND = re.compile(r"\bAND\b") +re_weight = re.compile(r"^(.*?)(?:\s*:\s*([-+]?\s*(?:\d+|\d*\.\d+)?))?\s*$") + + +def get_multicond_prompt_list(prompts): + res_indexes = [] + + prompt_flat_list = [] + prompt_indexes = {} + + for prompt in prompts: + subprompts = re_AND.split(prompt) + + indexes = [] + for subprompt in subprompts: + text, weight = re_weight.search(subprompt).groups() + + weight = float(weight) if weight is not None else 1.0 + + index = prompt_indexes.get(text, None) + if index is None: + index = len(prompt_flat_list) + prompt_flat_list.append(text) + prompt_indexes[text] = index + + indexes.append((index, weight)) + + res_indexes.append(indexes) + + return res_indexes, prompt_flat_list, prompt_indexes + + +class ComposableScheduledPromptConditioning: + def __init__(self, schedules, weight=1.0): + self.schedules: list[ScheduledPromptConditioning] = schedules + self.weight: float = weight + + +class MulticondLearnedConditioning: + def __init__(self, shape, batch): + self.shape: tuple = shape # the shape field is needed to send this object to DDIM/PLMS + self.batch: list[list[ComposableScheduledPromptConditioning]] = batch -def reconstruct_cond_batch(c: ScheduledPromptBatch, current_step): - param = c.schedules[0][0].cond - res = torch.zeros(c.shape, device=param.device, dtype=param.dtype) - for i, cond_schedule in enumerate(c.schedules): +def get_multicond_learned_conditioning(model, prompts, steps) -> MulticondLearnedConditioning: + """same as get_learned_conditioning, but returns a list of ScheduledPromptConditioning along with the weight objects for each prompt. + For each prompt, the list is obtained by splitting the prompt using the AND separator. + + https://energy-based-model.github.io/Compositional-Visual-Generation-with-Composable-Diffusion-Models/ + """ + + res_indexes, prompt_flat_list, prompt_indexes = get_multicond_prompt_list(prompts) + + learned_conditioning = get_learned_conditioning(model, prompt_flat_list, steps) + + res = [] + for indexes in res_indexes: + res.append([ComposableScheduledPromptConditioning(learned_conditioning[i], weight) for i, weight in indexes]) + + return MulticondLearnedConditioning(shape=(len(prompts),), batch=res) + + +def reconstruct_cond_batch(c: list[list[ScheduledPromptConditioning]], current_step): + param = c[0][0].cond + res = torch.zeros((len(c),) + param.shape, device=param.device, dtype=param.dtype) + for i, cond_schedule in enumerate(c): target_index = 0 for current, (end_at, cond) in enumerate(cond_schedule): if current_step <= end_at: @@ -140,6 +218,30 @@ def reconstruct_cond_batch(c: ScheduledPromptBatch, current_step): return res +def reconstruct_multicond_batch(c: MulticondLearnedConditioning, current_step): + param = c.batch[0][0].schedules[0].cond + + tensors = [] + conds_list = [] + + for batch_no, composable_prompts in enumerate(c.batch): + conds_for_batch = [] + + for cond_index, composable_prompt in enumerate(composable_prompts): + target_index = 0 + for current, (end_at, cond) in enumerate(composable_prompt.schedules): + if current_step <= end_at: + target_index = current + break + + conds_for_batch.append((len(tensors), composable_prompt.weight)) + tensors.append(composable_prompt.schedules[target_index].cond) + + conds_list.append(conds_for_batch) + + return conds_list, torch.stack(tensors).to(device=param.device, dtype=param.dtype) + + re_attention = re.compile(r""" \\\(| \\\)| diff --git a/modules/sd_samplers.py b/modules/sd_samplers.py index dbf570d2..d27c547b 100644 --- a/modules/sd_samplers.py +++ b/modules/sd_samplers.py @@ -109,9 +109,12 @@ class VanillaStableDiffusionSampler: return 0 def p_sample_ddim_hook(self, x_dec, cond, ts, unconditional_conditioning, *args, **kwargs): - cond = prompt_parser.reconstruct_cond_batch(cond, self.step) + conds_list, tensor = prompt_parser.reconstruct_multicond_batch(cond, self.step) unconditional_conditioning = prompt_parser.reconstruct_cond_batch(unconditional_conditioning, self.step) + assert all([len(conds) == 1 for conds in conds_list]), 'composition via AND is not supported for DDIM/PLMS samplers' + cond = tensor + if self.mask is not None: img_orig = self.sampler.model.q_sample(self.init_latent, ts) x_dec = img_orig * self.mask + self.nmask * x_dec @@ -183,19 +186,31 @@ class CFGDenoiser(torch.nn.Module): self.step = 0 def forward(self, x, sigma, uncond, cond, cond_scale): - cond = prompt_parser.reconstruct_cond_batch(cond, self.step) + conds_list, tensor = prompt_parser.reconstruct_multicond_batch(cond, self.step) uncond = prompt_parser.reconstruct_cond_batch(uncond, self.step) + batch_size = len(conds_list) + repeats = [len(conds_list[i]) for i in range(batch_size)] + + x_in = torch.cat([torch.stack([x[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [x]) + sigma_in = torch.cat([torch.stack([sigma[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [sigma]) + cond_in = torch.cat([tensor, uncond]) + if shared.batch_cond_uncond: - x_in = torch.cat([x] * 2) - sigma_in = torch.cat([sigma] * 2) - cond_in = torch.cat([uncond, cond]) - uncond, cond = self.inner_model(x_in, sigma_in, cond=cond_in).chunk(2) - denoised = uncond + (cond - uncond) * cond_scale + x_out = self.inner_model(x_in, sigma_in, cond=cond_in) else: - uncond = self.inner_model(x, sigma, cond=uncond) - cond = self.inner_model(x, sigma, cond=cond) - denoised = uncond + (cond - uncond) * cond_scale + x_out = torch.zeros_like(x_in) + for batch_offset in range(0, x_out.shape[0], batch_size): + a = batch_offset + b = a + batch_size + x_out[a:b] = self.inner_model(x_in[a:b], sigma_in[a:b], cond=cond_in[a:b]) + + denoised_uncond = x_out[-batch_size:] + denoised = torch.clone(denoised_uncond) + + for i, conds in enumerate(conds_list): + for cond_index, weight in conds: + denoised[i] += (x_out[cond_index] - denoised_uncond[i]) * (weight * cond_scale) if self.mask is not None: denoised = self.init_latent * self.mask + self.nmask * denoised diff --git a/modules/ui.py b/modules/ui.py index 523ab25b..9620350f 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -34,7 +34,7 @@ import modules.gfpgan_model import modules.codeformer_model import modules.styles import modules.generation_parameters_copypaste -from modules.prompt_parser import get_learned_conditioning_prompt_schedules +from modules import prompt_parser from modules.images import apply_filename_pattern, get_next_sequence_number import modules.textual_inversion.ui @@ -394,7 +394,9 @@ def connect_reuse_seed(seed: gr.Number, reuse_seed: gr.Button, generation_info: def update_token_counter(text, steps): try: - prompt_schedules = get_learned_conditioning_prompt_schedules([text], steps) + _, prompt_flat_list, _ = prompt_parser.get_multicond_prompt_list([text]) + prompt_schedules = prompt_parser.get_learned_conditioning_prompt_schedules(prompt_flat_list, steps) + except Exception: # a parsing error can happen here during typing, and we don't want to bother the user with # messages related to it in console -- cgit v1.2.3 From 0bb458f0ca06a7be27cf1a1003c536d1f06a5bd3 Mon Sep 17 00:00:00 2001 From: Milly Date: Wed, 5 Oct 2022 01:19:50 +0900 Subject: Removed duplicate image saving codes Use `modules.images.save_image()` instead. --- modules/images.py | 7 ++++--- modules/ui.py | 46 ++++++++++------------------------------------ 2 files changed, 14 insertions(+), 39 deletions(-) (limited to 'modules/ui.py') diff --git a/modules/images.py b/modules/images.py index c2fadab9..810f1446 100644 --- a/modules/images.py +++ b/modules/images.py @@ -353,7 +353,7 @@ def get_next_sequence_number(path, basename): return result + 1 -def save_image(image, path, basename, seed=None, prompt=None, extension='png', info=None, short_filename=False, no_prompt=False, grid=False, pnginfo_section_name='parameters', p=None, existing_info=None, forced_filename=None, suffix=""): +def save_image(image, path, basename, seed=None, prompt=None, extension='png', info=None, short_filename=False, no_prompt=False, grid=False, pnginfo_section_name='parameters', p=None, existing_info=None, forced_filename=None, suffix="", save_to_dirs=None): if short_filename or prompt is None or seed is None: file_decoration = "" elif opts.save_to_dirs: @@ -377,7 +377,8 @@ def save_image(image, path, basename, seed=None, prompt=None, extension='png', i else: pnginfo = None - save_to_dirs = (grid and opts.grid_save_to_dirs) or (not grid and opts.save_to_dirs and not no_prompt) + if save_to_dirs is None: + save_to_dirs = (grid and opts.grid_save_to_dirs) or (not grid and opts.save_to_dirs and not no_prompt) if save_to_dirs: dirname = apply_filename_pattern(opts.directories_filename_pattern or "[prompt_words]", p, seed, prompt).strip('\\ /') @@ -431,4 +432,4 @@ def save_image(image, path, basename, seed=None, prompt=None, extension='png', i with open(f"{fullfn_without_extension}.txt", "w", encoding="utf8") as file: file.write(info + "\n") - + return fullfn diff --git a/modules/ui.py b/modules/ui.py index 9620350f..4f18126f 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -35,7 +35,7 @@ import modules.codeformer_model import modules.styles import modules.generation_parameters_copypaste from modules import prompt_parser -from modules.images import apply_filename_pattern, get_next_sequence_number +from modules.images import save_image import modules.textual_inversion.ui # this is a fix for Windows users. Without it, javascript files will be served with text/html content-type and the bowser will not show any UI @@ -114,20 +114,13 @@ def save_files(js_data, images, index): p = MyObject(data) path = opts.outdir_save save_to_dirs = opts.use_save_to_dirs_for_ui - - if save_to_dirs: - dirname = apply_filename_pattern(opts.directories_filename_pattern or "[prompt_words]", p, p.seed, p.prompt) - path = os.path.join(opts.outdir_save, dirname) - - os.makedirs(path, exist_ok=True) - + extension: str = opts.samples_format + start_index = 0 if index > -1 and opts.save_selected_only and (index >= data["index_of_first_image"]): # ensures we are looking at a specific non-grid picture, and we have save_selected_only images = [images[index]] - infotexts = [data["infotexts"][index]] - else: - infotexts = data["infotexts"] + start_index = index with open(os.path.join(opts.outdir_save, "log.csv"), "a", encoding="utf8", newline='') as file: at_start = file.tell() == 0 @@ -135,37 +128,18 @@ def save_files(js_data, images, index): if at_start: writer.writerow(["prompt", "seed", "width", "height", "sampler", "cfgs", "steps", "filename", "negative_prompt"]) - file_decoration = opts.samples_filename_pattern or "[seed]-[prompt_spaces]" - if file_decoration != "": - file_decoration = "-" + file_decoration.lower() - file_decoration = apply_filename_pattern(file_decoration, p, p.seed, p.prompt) - truncated = (file_decoration[:240] + '..') if len(file_decoration) > 240 else file_decoration - filename_base = truncated - extension = opts.samples_format.lower() - - basecount = get_next_sequence_number(path, "") - for i, filedata in enumerate(images): - file_number = f"{basecount+i:05}" - filename = file_number + filename_base + f".{extension}" - filepath = os.path.join(path, filename) - - + for image_index, filedata in enumerate(images, start_index): if filedata.startswith("data:image/png;base64,"): filedata = filedata[len("data:image/png;base64,"):] image = Image.open(io.BytesIO(base64.decodebytes(filedata.encode('utf-8')))) - if opts.enable_pnginfo and extension == 'png': - pnginfo = PngImagePlugin.PngInfo() - pnginfo.add_text('parameters', infotexts[i]) - image.save(filepath, pnginfo=pnginfo) - else: - image.save(filepath, quality=opts.jpeg_quality) - if opts.enable_pnginfo and extension in ("jpg", "jpeg", "webp"): - piexif.insert(piexif.dump({"Exif": { - piexif.ExifIFD.UserComment: piexif.helper.UserComment.dump(infotexts[i], encoding="unicode") - }}), filepath) + is_grid = image_index < p.index_of_first_image + i = 0 if is_grid else (image_index - p.index_of_first_image) + + fullfn = save_image(image, path, "", seed=p.all_seeds[i], prompt=p.all_prompts[i], extension=extension, info=p.infotexts[image_index], grid=is_grid, p=p, save_to_dirs=save_to_dirs) + filename = os.path.relpath(fullfn, path) filenames.append(filename) writer.writerow([data["prompt"], data["seed"], data["width"], data["height"], data["sampler"], data["cfg_scale"], data["steps"], filenames[0], data["negative_prompt"]]) -- cgit v1.2.3