diff --git a/CHANGELOG.md b/CHANGELOG.md index b19c76c4c..1ba9389d3 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,11 +1,18 @@ # Change Log for SD.Next -## Update for 07/15/2023 +## Update for 07/16/2023 +- **diffusers**: + - samplers: add concept of *default* sampler to avoid needing to tweak settings for primary or second pass + note that sampler details will be printed in log when running in debug level + - samplers: allow overriding of sampler beta values in settings + - refiner: fix refiner applying only to first image in batch + - refiner: allow using direct latents or processed output in refiner + - model: basic support for one more model: [UniDiffuser](https://github.com/thu-ml/unidiffuser) + download using model downloader: `thu-ml/unidiffuser-v1` + use Default or DDIM sampler & disable live preview + (support for additional samplers and live previews can be added if there is interest) - **direct-ml** improvements: faster and less memory usage -- basic support for one more model: [UniDiffuser](https://github.com/thu-ml/unidiffuser): - download using model downloader: `thu-ml/unidiffuser-v1` - use DDIM sampler & disable live preview (support for additional samplers and live previews can be added if there is interest) - force requirements check on each start there are too many misbehaving extensions that change system requirements diff --git a/TODO.md b/TODO.md index 84720f501..47a8df4d6 100644 --- a/TODO.md +++ b/TODO.md @@ -10,12 +10,12 @@ Stuff to be fixed, in no particular order... - Kandinsky 2.2 (2.1 is working) - Misterious Extensions auto-enabling - Misterious Extra network corruptions -- Save interim image before refiner ## Features Stuff to be added, in no particular order... +- Diffusers save before refiner - Update `Wiki` - Create new `GitHub` hooks/actions for CI/CD - Import core repos diff --git a/extensions-builtin/sd-webui-agent-scheduler b/extensions-builtin/sd-webui-agent-scheduler index bdd7de257..e9056ee69 160000 --- a/extensions-builtin/sd-webui-agent-scheduler +++ b/extensions-builtin/sd-webui-agent-scheduler @@ -1 +1 @@ -Subproject commit bdd7de2574101063c385e95fcb5d62869f30d511 +Subproject commit e9056ee69c7d5cc2da1d8ea5924241fa09782974 diff --git a/extensions-builtin/stable-diffusion-webui-images-browser b/extensions-builtin/stable-diffusion-webui-images-browser index 9229ed5e7..c6fcf6c43 160000 --- a/extensions-builtin/stable-diffusion-webui-images-browser +++ b/extensions-builtin/stable-diffusion-webui-images-browser @@ -1 +1 @@ -Subproject commit 9229ed5e7e15608ec035d89cc5b2d19c3e629142 +Subproject commit c6fcf6c438bf5c447c6d3c4dfd0b36c36aa1e4e3 diff --git a/installer.py b/installer.py index 2f347235f..cf7a30cbe 100644 --- a/installer.py +++ b/installer.py @@ -287,6 +287,7 @@ def check_torch(): return if args.skip_torch: log.info('Skipping Torch tests') + return if args.profile: pr = cProfile.Profile() pr.enable() diff --git a/modules/api/api.py b/modules/api/api.py index f208ba664..c9dcee5ea 100644 --- a/modules/api/api.py +++ b/modules/api/api.py @@ -583,13 +583,8 @@ class Api: def shutdown(self): shared.log.info('Shutdown request received') - # from modules.shared import demo - # demo.close() - # time.sleep(0.5) - # import sys - # sys.exit(0) - import os - os._exit(0) + import sys + sys.exit(0) def get_memory(self): try: diff --git a/modules/processing.py b/modules/processing.py index 9553f41c3..ce67c9e0d 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -19,7 +19,6 @@ from installer import git_commit 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, sd_samplers_common # pylint: disable=unused-import from modules.sd_hijack import model_hijack -from modules.shared import opts, cmd_opts, state, log, Backend import modules.shared as shared import modules.paths as paths import modules.face_restoration @@ -35,13 +34,13 @@ opt_f = 8 def setup_color_correction(image): - log.debug("Calibrating color correction.") + shared.log.debug("Calibrating color correction.") correction_target = cv2.cvtColor(np.asarray(image.copy()), cv2.COLOR_RGB2LAB) return correction_target def apply_color_correction(correction, original_image): - log.debug("Applying color correction.") + shared.log.debug("Applying color correction.") image = Image.fromarray(cv2.cvtColor(exposure.match_histograms( cv2.cvtColor(np.asarray(original_image), cv2.COLOR_RGB2LAB), correction, @@ -124,12 +123,12 @@ class StableDiffusionProcessing: self.color_corrections = None self.denoising_strength: float = denoising_strength self.sampler_noise_scheduler_override = None - self.ddim_discretize = ddim_discretize or opts.ddim_discretize - self.s_min_uncond = s_min_uncond or opts.s_min_uncond - self.s_churn = s_churn or opts.s_churn - self.s_tmin = s_tmin or opts.s_tmin + self.ddim_discretize = ddim_discretize or shared.opts.ddim_discretize + self.s_min_uncond = s_min_uncond or shared.opts.s_min_uncond + self.s_churn = s_churn or shared.opts.s_churn + self.s_tmin = s_tmin or shared.opts.s_tmin self.s_tmax = s_tmax or float('inf') # not representable as a standard ui option - self.s_noise = s_noise or opts.s_noise + self.s_noise = s_noise or shared.opts.s_noise self.override_settings = {k: v for k, v in (override_settings or {}).items() if k not in shared.restricted_opts} self.override_settings_restore_afterwards = override_settings_restore_afterwards self.is_using_inpainting_conditioning = False @@ -153,7 +152,7 @@ class StableDiffusionProcessing: self.is_hr_pass = False self.enable_hr = None self.refiner_denoise_start = 0 - opts.data['clip_skip'] = clip_skip + shared.opts.data['clip_skip'] = clip_skip @property def sd_model(self): @@ -228,8 +227,8 @@ class StableDiffusionProcessing: source_image = devices.cond_cast_float(source_image) # HACK: Using introspection as the Depth2Image model doesn't appear to uniquely # identify itself with a field common to all models. The conditioning_key is also hybrid. - if shared.backend == Backend.DIFFUSERS: - log.warning('Diffusers not implemented: img2img_image_conditioning') + if shared.backend == shared.Backend.DIFFUSERS: + shared.log.warning('Diffusers not implemented: img2img_image_conditioning') if isinstance(self.sd_model, LatentDepth2ImageDiffusion): return self.depth2img_image_conditioning(source_image) if hasattr(self.sd_model, 'cond_stage_key') and self.sd_model.cond_stage_key == "edit": @@ -252,8 +251,8 @@ class StableDiffusionProcessing: 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 + return self.token_merging_ratio_hr or shared.opts.token_merging_ratio_hr or self.token_merging_ratio or shared.opts.token_merging_ratio + return self.token_merging_ratio or shared.opts.token_merging_ratio class Processed: @@ -274,7 +273,7 @@ class Processed: self.steps = p.steps self.batch_size = p.batch_size self.restore_faces = p.restore_faces - self.face_restoration_model = opts.face_restoration_model if p.restore_faces else None + self.face_restoration_model = shared.opts.face_restoration_model if p.restore_faces else None self.sd_model_hash = shared.sd_model.sd_model_hash self.seed_resize_from_w = p.seed_resize_from_w self.seed_resize_from_h = p.seed_resize_from_h @@ -282,7 +281,7 @@ class Processed: self.extra_generation_params = p.extra_generation_params self.index_of_first_image = index_of_first_image self.styles = p.styles - self.job_timestamp = state.job_timestamp + self.job_timestamp = shared.state.job_timestamp self.clip_skip = p.clip_skip self.eta = p.eta self.ddim_discretize = p.ddim_discretize @@ -361,14 +360,14 @@ def slerp(val, low, high): def create_random_tensors(shape, seeds, subseeds=None, subseed_strength=0.0, seed_resize_from_h=0, seed_resize_from_w=0, p=None): - eta_noise_seed_delta = opts.eta_noise_seed_delta or 0 + eta_noise_seed_delta = shared.opts.eta_noise_seed_delta or 0 xs = [] # if we have multiple seeds, this means we are working with batch size>1; this then # enables the generation of additional tensors with noise that the sampler will use during its processing. # Using those pre-generated tensors instead of simple torch.randn allows a batch with seeds [100, 101] to # produce the same images as with two batches [100], [101]. - if p is not None and p.sampler is not None and (len(seeds) > 1 and opts.enable_batch_seeds or eta_noise_seed_delta > 0): + if p is not None and p.sampler is not None and (len(seeds) > 1 and shared.opts.enable_batch_seeds or eta_noise_seed_delta > 0): sampler_noises = [[] for _ in range(p.sampler.number_of_needed_noises(p))] else: sampler_noises = None @@ -425,7 +424,12 @@ def create_random_tensors(shape, seeds, subseeds=None, subseed_strength=0.0, see def decode_first_stage(model, x): with devices.autocast(disable = x.dtype==devices.dtype_vae): - x = model.decode_first_stage(x) + if hasattr(model, 'decode_first_stage'): + x = model.decode_first_stage(x) + elif hasattr(model, 'vae'): + x = model.vae(x) + else: + shared.log.warning('Cannot decode first stage') return x @@ -446,7 +450,7 @@ def create_infotext(p: StableDiffusionProcessing, all_prompts, all_seeds, all_su 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 + uses_ensd = shared.opts.eta_noise_seed_delta != 0 if uses_ensd: uses_ensd = sd_samplers_common.is_sampler_using_eta_noise_seed_delta(p) @@ -457,24 +461,24 @@ def create_infotext(p: StableDiffusionProcessing, all_prompts, all_seeds, all_su "CFG scale": p.cfg_scale, "Image CFG scale": p.image_cfg_scale, "Seed": all_seeds[index], - "Face restoration": opts.face_restoration_model if p.restore_faces else None, + "Face restoration": shared.opts.face_restoration_model if p.restore_faces else None, "Size": f"{p.width}x{p.height}", - "Model hash": getattr(p, 'sd_model_hash', None if not opts.add_model_hash_to_info or not shared.sd_model.sd_model_hash else shared.sd_model.sd_model_hash), - "Model": None if not opts.add_model_name_to_info or not shared.sd_model.sd_checkpoint_info.model_name else shared.sd_model.sd_checkpoint_info.model_name.replace(',', '').replace(':', ''), - "Refiner": None if not opts.add_model_name_to_info or not shared.sd_refiner or not shared.sd_refiner.sd_checkpoint_info.model_name else shared.sd_refiner.sd_checkpoint_info.model_name.replace(',', '').replace(':', ''), - "VAE": None if not opts.add_model_name_to_info or sd_vae.loaded_vae_file is None else os.path.splitext(os.path.basename(sd_vae.loaded_vae_file))[0], + "Model hash": getattr(p, 'sd_model_hash', None if not shared.opts.add_model_hash_to_info or not shared.sd_model.sd_model_hash else shared.sd_model.sd_model_hash), + "Model": None if not shared.opts.add_model_name_to_info or not shared.sd_model.sd_checkpoint_info.model_name else shared.sd_model.sd_checkpoint_info.model_name.replace(',', '').replace(':', ''), + "Refiner": None if not shared.opts.add_model_name_to_info or not shared.sd_refiner or not shared.sd_refiner.sd_checkpoint_info.model_name else shared.sd_refiner.sd_checkpoint_info.model_name.replace(',', '').replace(':', ''), + "VAE": None if not shared.opts.add_model_name_to_info or sd_vae.loaded_vae_file is None else os.path.splitext(os.path.basename(sd_vae.loaded_vae_file))[0], "Variation seed": None if p.subseed_strength == 0 else all_subseeds[index], "Variation seed strength": None if p.subseed_strength == 0 else p.subseed_strength, "Seed resize from": None if p.seed_resize_from_w == 0 or p.seed_resize_from_h == 0 else f"{p.seed_resize_from_w}x{p.seed_resize_from_h}", "Denoising strength": p.denoising_strength, "Conditional mask weight": getattr(p, "inpainting_mask_weight", shared.opts.inpainting_mask_weight) if p.is_using_inpainting_conditioning else None, "Clip skip": p.clip_skip if p.clip_skip > 1 else None, - "ENSD": opts.eta_noise_seed_delta if uses_ensd else None, + "ENSD": shared.opts.eta_noise_seed_delta if uses_ensd else None, "Init image hash": getattr(p, 'init_img_hash', None), "Version": git_commit, "Token merging ratio": None if token_merging_ratio == 0 else token_merging_ratio, "Token merging ratio hr": None if not p.enable_hr or token_merging_ratio_hr == 0 else token_merging_ratio_hr, - "Parser": opts.prompt_attention, + "Parser": shared.opts.prompt_attention, } 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]) @@ -513,14 +517,14 @@ def print_profile(profile, msg: str): def process_images(p: StableDiffusionProcessing) -> Processed: - stored_opts = {k: opts.data[k] for k in p.override_settings.keys()} + stored_opts = {k: shared.opts.data[k] for k in p.override_settings.keys()} try: # if no checkpoint override or the override checkpoint can't be found, remove override entry and load opts checkpoint if p.override_settings.get('sd_model_checkpoint', None) is not None and sd_models.checkpoint_aliases.get(p.override_settings.get('sd_model_checkpoint')) is None: p.override_settings.pop('sd_model_checkpoint', None) sd_models.reload_model_weights() for k, v in p.override_settings.items(): - setattr(opts, k, v) + setattr(shared.opts, k, v) if k == 'sd_model_checkpoint': sd_models.reload_model_weights() if k == 'sd_vae': @@ -529,7 +533,7 @@ def process_images(p: StableDiffusionProcessing) -> Processed: if not shared.opts.cuda_compile: sd_models.apply_token_merging(p.sd_model, p.get_token_merging_ratio()) - if cmd_opts.profile: + if shared.cmd_opts.profile: """ import torch.profiler # pylint: disable=redefined-outer-name with torch.profiler.profile(profile_memory=True, with_modules=True) as prof: @@ -549,7 +553,7 @@ def process_images(p: StableDiffusionProcessing) -> Processed: sd_models.apply_token_merging(p.sd_model, 0) if p.override_settings_restore_afterwards: # restore opts to original state for k, v in stored_opts.items(): - setattr(opts, k, v) + setattr(shared.opts, k, v) if k == 'sd_model_checkpoint': sd_models.reload_model_weights() @@ -568,7 +572,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: seed = get_fixed_seed(p.seed) subseed = get_fixed_seed(p.subseed) - if shared.backend == Backend.ORIGINAL: + if shared.backend == shared.Backend.ORIGINAL: modules.sd_hijack.model_hijack.apply_circular(p.tiling) modules.sd_hijack.model_hijack.clear_comments() comments = {} @@ -593,7 +597,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: def infotext(iteration=0, position_in_batch=0): return create_infotext(p, p.all_prompts, p.all_seeds, p.all_subseeds, comments, iteration, position_in_batch) - if os.path.exists(opts.embeddings_dir) and not p.do_not_reload_embeddings: + if os.path.exists(shared.opts.embeddings_dir) and not p.do_not_reload_embeddings: model_hijack.embedding_db.load_textual_inversion_embeddings() if p.scripts is not None: p.scripts.process(p) @@ -653,27 +657,35 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: for arg in kwargs: if arg in possible: args[arg] = kwargs[arg] - # log.debug(f'Diffuser pipeline: {pipeline.__class__.__name__} possible={possible}') - log.debug(f'Diffuser pipeline: {pipeline.__class__.__name__} set={args.keys()}') + # shared.log.debug(f'Diffuser pipeline: {pipeline.__class__.__name__} possible={possible}') + clean = args.copy() + clean.pop('callback', None) + clean.pop('callback_steps', None) + clean.pop('image', None) + clean.pop('mask_image', None) + clean.pop('prompt', None) + clean.pop('negative_prompt', None) + clean['generator'] = generator_device + shared.log.debug(f'Diffuser pipeline: {pipeline.__class__.__name__} set={clean}') return args - ema_scope_context = p.sd_model.ema_scope if shared.backend == Backend.ORIGINAL else nullcontext + ema_scope_context = p.sd_model.ema_scope if shared.backend == shared.Backend.ORIGINAL else nullcontext with torch.no_grad(), ema_scope_context(): with devices.autocast(): p.init(p.all_prompts, p.all_seeds, p.all_subseeds) - if shared.opts.live_previews_enable and opts.show_progress_type == "Approximate NN" and shared.backend == Backend.ORIGINAL: + if shared.opts.live_previews_enable and shared.opts.show_progress_type == "Approximate NN" and shared.backend == shared.Backend.ORIGINAL: sd_vae_approx.model() - if state.job_count == -1: - state.job_count = p.n_iter + if shared.state.job_count == -1: + shared.state.job_count = p.n_iter extra_network_data = None for n in range(p.n_iter): p.iteration = n - if state.skipped: + if shared.state.skipped: shared.log.debug(f'Process skipped: {n}/{p.n_iter}') - state.skipped = False + shared.state.skipped = False continue - if state.interrupted: + if shared.state.interrupted: shared.log.debug(f'Process interrupted: {n}/{p.n_iter}') break prompts = p.all_prompts[n * p.batch_size:(n + 1) * p.batch_size] @@ -700,7 +712,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: if p.n_iter > 1: shared.state.job = f"Batch {n+1} out of {p.n_iter}" - if shared.backend == Backend.ORIGINAL: + if shared.backend == shared.Backend.ORIGINAL: 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 len(model_hijack.comments) > 0: @@ -714,7 +726,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: devices.test_for_nans(x, "vae") except devices.NansException as e: if not shared.opts.no_half and not shared.opts.no_half_vae and shared.cmd_opts.rollback_vae: - log.warning('Tensor with all NaNs was produced in VAE') + shared.log.warning('Tensor with all NaNs was produced in VAE') devices.dtype_vae = torch.bfloat16 vae_file, vae_source = sd_vae.resolve_vae(p.sd_model.sd_model_checkpoint) sd_vae.load_vae(p.sd_model, vae_file, vae_source) @@ -727,12 +739,12 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: x_samples_ddim = torch.clamp((x_samples_ddim + 1.0) / 2.0, min=0.0, max=1.0) del samples_ddim - elif shared.backend == Backend.DIFFUSERS: - # if (not hasattr(shared.sd_model.scheduler, 'name')) or (shared.sd_model.scheduler.name != p.sampler_name): - sampler = sd_samplers.all_samplers_map.get(p.sampler_name, None) - if sampler is None: - sampler = sd_samplers.all_samplers_map.get("UniPC") - sd_samplers.create_sampler(sampler.name, shared.sd_model) # TODO(Patrick): For wrapped pipelines this is currently a no-op + elif shared.backend == shared.Backend.DIFFUSERS: + if (not hasattr(shared.sd_model.scheduler, 'name')) or (shared.sd_model.scheduler.name != p.sampler_name) and (p.sampler_name != 'Default'): + sampler = sd_samplers.all_samplers_map.get(p.sampler_name, None) + if sampler is None: + sampler = sd_samplers.all_samplers_map.get("UniPC") + sd_samplers.create_sampler(sampler.name, shared.sd_model) # TODO(Patrick): For wrapped pipelines this is currently a no-op cross_attention_kwargs={} if lora_state['active']: @@ -754,7 +766,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: eta=shared.opts.eta_ddim, guidance_rescale=p.diffusers_guidance_rescale, # aesthetic_score=shared.opts.diffusers_aesthetics_score, - output_type='np' if (shared.sd_refiner is None or p.enable_hr is False) else 'latent', + output_type='np' if (shared.sd_refiner is None or p.enable_hr is False or not shared.opts.diffusers_refiner_latents) else 'latent', **task_specific_kwargs ) output = shared.sd_model(**pipe_args) # pylint: disable=not-callable @@ -765,38 +777,52 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: shared.log.debug('Moving base model to CPU') shared.sd_model.to('cpu') - # if (not hasattr(shared.sd_refiner.scheduler, 'name')) or (shared.sd_refiner.scheduler.name != p.latent_sampler): - sampler = sd_samplers.all_samplers_map.get(p.latent_sampler, None) - if sampler is None: - sampler = sd_samplers.all_samplers_map.get("UniPC") - sd_samplers.create_sampler(sampler.name, shared.sd_refiner) # TODO(Patrick): For wrapped pipelines this is currently a no-op + if (not hasattr(shared.sd_refiner.scheduler, 'name')) or (shared.sd_refiner.scheduler.name != p.latent_sampler) and (p.sampler_name != 'Default'): + sampler = sd_samplers.all_samplers_map.get(p.latent_sampler, None) + if sampler is None: + sampler = sd_samplers.all_samplers_map.get("UniPC") + sd_samplers.create_sampler(sampler.name, shared.sd_refiner) # TODO(Patrick): For wrapped pipelines this is currently a no-op shared.sd_refiner.to(devices.device) devices.torch_gc() - pipe_args = set_pipeline_args( - model=shared.sd_refiner, - prompt=[p.refiner_prompt] if len(p.refiner_prompt) > 0 else prompts, - negative_prompt=[p.refiner_negative] if len(p.refiner_negative) > 0 else negative_prompts, - num_inference_steps=p.hr_second_pass_steps, - eta=shared.opts.eta_ddim, - strength=p.denoising_strength, - guidance_scale=p.image_cfg_scale if p.image_cfg_scale is not None else p.cfg_scale, - guidance_rescale=p.diffusers_guidance_rescale, - # aesthetic_score=shared.opts.diffusers_aesthetics_score, - denoising_start=p.refiner_denoise_start, - denoising_end=p.refiner_denoise_end, - image=output.images[0], - output_type='np' - ) - output = shared.sd_refiner(**pipe_args) # pylint: disable=not-callable - if shared.opts.diffusers_move_refiner: - log.debug('Moving refiner model to CPU') - shared.sd_refiner.to('cpu') + x_samples_ddim = [] - x_samples_ddim = output.images + for i in range(len(output.images)): + + """ + # TODO save before refiner + if shared.opts.save and not p.do_not_save_samples and shared.opts.save_images_before_refiner and hasattr(shared.sd_model, 'vae'): + info=infotext(n, i) + image = decode_first_stage(shared.sd_model, output.images[i].to(dtype=devices.dtype_vae)) + images.save_image(image, path=p.outpath_samples, basename="", seed=seeds[i], prompt=prompts[i], extension=shared.opts.samples_format, info=info, p=p, suffix="-before-refiner") + """ + + pipe_args = set_pipeline_args( + model=shared.sd_refiner, + prompt=[p.refiner_prompt] if len(p.refiner_prompt) > 0 else prompts, + negative_prompt=[p.refiner_negative] if len(p.refiner_negative) > 0 else negative_prompts, + num_inference_steps=p.hr_second_pass_steps, + eta=shared.opts.eta_ddim, + strength=p.denoising_strength, + guidance_scale=p.image_cfg_scale if p.image_cfg_scale is not None else p.cfg_scale, + guidance_rescale=p.diffusers_guidance_rescale, + # aesthetic_score=shared.opts.diffusers_aesthetics_score, + denoising_start=p.refiner_denoise_start, + denoising_end=p.refiner_denoise_end, + image=output.images[i], + output_type='np', + ) + output = shared.sd_refiner(**pipe_args) # pylint: disable=not-callable + x_samples_ddim.append(output.images[0]) + + if shared.opts.diffusers_move_refiner: + shared.log.debug('Moving refiner model to CPU') + shared.sd_refiner.to('cpu') + else: + x_samples_ddim = output.images if p.is_hr_pass: - log.warning('Diffusers not implemented: hires fix') + shared.log.warning('Diffusers not implemented: hires fix') if lora_state['active']: unload_diffusers_lora() @@ -812,18 +838,18 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: for i, x_sample in enumerate(x_samples_ddim): p.batch_index = i - if shared.backend == Backend.ORIGINAL: + if shared.backend == shared.Backend.ORIGINAL: x_sample = 255. * np.moveaxis(x_sample.cpu().numpy(), 0, 2) x_sample = x_sample.astype(np.uint8) else: x_sample = (255. * x_sample).astype(np.uint8) if p.restore_faces: - if opts.save and not p.do_not_save_samples and opts.save_images_before_face_restoration: + if shared.opts.save and not p.do_not_save_samples and shared.opts.save_images_before_face_restoration: orig = p.restore_faces p.restore_faces = False info=infotext(n, i) p.restore_faces = orig - images.save_image(Image.fromarray(x_sample), path=p.outpath_samples, basename="", seed=seeds[i], prompt=prompts[i], extension=opts.samples_format, info=info, p=p, suffix="-before-face-restoration") + images.save_image(Image.fromarray(x_sample), path=p.outpath_samples, basename="", seed=seeds[i], prompt=prompts[i], extension=shared.opts.samples_format, info=info, p=p, suffix="-before-face-restoration") x_sample = modules.face_restoration.restore_faces(x_sample) image = Image.fromarray(x_sample) if p.scripts is not None: @@ -831,50 +857,50 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: p.scripts.postprocess_image(p, pp) image = pp.image 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: + if shared.opts.save and not p.do_not_save_samples and shared.opts.save_images_before_color_correction: orig = p.color_corrections p.color_corrections = None info=infotext(n, i) p.color_corrections = orig image_without_cc = apply_overlay(image, p.paste_to, i, p.overlay_images) - images.save_image(image_without_cc, path=p.outpath_samples, basename="", seed=seeds[i], prompt=prompts[i], extension=opts.samples_format, info=info, p=p, suffix="-before-color-correction") + images.save_image(image_without_cc, path=p.outpath_samples, basename="", seed=seeds[i], prompt=prompts[i], extension=shared.opts.samples_format, info=info, 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) + if shared.opts.samples_save and not p.do_not_save_samples: + images.save_image(image, p.outpath_samples, "", seeds[i], prompts[i], shared.opts.samples_format, info=infotext(n, i), p=p) text = infotext(n, i) infotexts.append(text) image.info["parameters"] = text output_images.append(image) - if hasattr(p, 'mask_for_overlay') and p.mask_for_overlay and any([opts.save_mask, opts.save_mask_composite, opts.return_mask, opts.return_mask_composite]): + if hasattr(p, 'mask_for_overlay') and p.mask_for_overlay and any([shared.opts.save_mask, shared.opts.save_mask_composite, shared.opts.return_mask, shared.opts.return_mask_composite]): image_mask = p.mask_for_overlay.convert('RGB') 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") - 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") - if opts.return_mask: + if shared.opts.save_mask: + images.save_image(image_mask, p.outpath_samples, "", seeds[i], prompts[i], shared.opts.samples_format, info=infotext(n, i), p=p, suffix="-mask") + if shared.opts.save_mask_composite: + images.save_image(image_mask_composite, p.outpath_samples, "", seeds[i], prompts[i], shared.opts.samples_format, info=infotext(n, i), p=p, suffix="-mask-composite") + if shared.opts.return_mask: output_images.append(image_mask) - if opts.return_mask_composite: + if shared.opts.return_mask_composite: output_images.append(image_mask_composite) del x_samples_ddim devices.torch_gc() - state.nextjob() + shared.state.nextjob() p.color_corrections = None index_of_first_image = 0 - unwanted_grid_because_of_img_count = len(output_images) < 2 and opts.grid_only_if_multiple - if (opts.return_grid or opts.grid_save) and not p.do_not_save_grid and not unwanted_grid_because_of_img_count: + unwanted_grid_because_of_img_count = len(output_images) < 2 and shared.opts.grid_only_if_multiple + if (shared.opts.return_grid or shared.opts.grid_save) and not p.do_not_save_grid and not unwanted_grid_because_of_img_count: if images.check_grid_size(output_images): grid = images.image_grid(output_images, p.batch_size) - if opts.return_grid: + if shared.opts.return_grid: text = infotext() infotexts.insert(0, text) grid.info["parameters"] = text output_images.insert(0, grid) index_of_first_image = 1 - if opts.grid_save: - 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 shared.opts.grid_save: + images.save_image(grid, p.outpath_grids, "grid", p.all_seeds[0], p.all_prompts[0], shared.opts.grid_format, info=infotext(), short_filename=not shared.opts.grid_extended_filename, p=p, grid=True) if not p.disable_extra_networks and extra_network_data: extra_networks.deactivate(p, extra_network_data) @@ -888,7 +914,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: index_of_first_image=index_of_first_image, infotexts=infotexts, ) - if p.scripts is not None and not state.interrupted: + if p.scripts is not None and not shared.state.interrupted: p.scripts.postprocess(p, res) return res @@ -932,14 +958,14 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): self.refiner_negative = refiner_negative def init(self, all_prompts, all_seeds, all_subseeds): - if shared.backend == Backend.DIFFUSERS: + if shared.backend == shared.Backend.DIFFUSERS: sd_models.set_diffuser_pipe(self.sd_model, sd_models.DiffusersTaskType.TEXT_2_IMAGE) self.width = self.width or 512 self.height = self.height or 512 if self.enable_hr: - if opts.use_old_hires_fix_width_height and self.applied_old_hires_behavior_to != (self.width, self.height): + if shared.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 self.hr_upscale_to_x = self.width @@ -973,15 +999,14 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): self.truncate_y = (self.hr_upscale_to_y - target_h) // opt_f # special case: the user has chosen to do nothing if self.hr_upscale_to_x == self.width and self.hr_upscale_to_y == self.height: - self.denoising_strength = None self.extra_generation_params.pop("Hires upscale", None) self.extra_generation_params.pop("Hires resize", None) return - if not state.processing_has_refined_job_count: - if state.job_count == -1: - state.job_count = self.n_iter - state.job_count = state.job_count * 2 - state.processing_has_refined_job_count = True + if not shared.state.processing_has_refined_job_count: + if shared.state.job_count == -1: + shared.state.job_count = self.n_iter + shared.state.job_count = shared.state.job_count * 2 + shared.state.processing_has_refined_job_count = True if self.hr_second_pass_steps: self.extra_generation_params["Hires steps"] = self.hr_second_pass_steps if self.hr_upscaler is not None: @@ -991,7 +1016,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): def save_intermediate(image, index): """saves image before applying hires fix, if enabled in options; takes as an argument either an image or batch with latent space images""" - if not opts.save or self.do_not_save_samples or not opts.save_images_before_highres_fix: + if not shared.opts.save or self.do_not_save_samples or not shared.opts.save_images_before_highres_fix: return if not isinstance(image, Image.Image): image = sd_samplers.sample_to_image(image, index, approximation=0) @@ -1002,20 +1027,20 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): info = create_infotext(self, self.all_prompts, self.all_seeds, self.all_subseeds, [], iteration=self.iteration, position_in_batch=index) self.extra_generation_params = orig1 self.restore_faces = orig2 - images.save_image(image, self.outpath_samples, "", seeds[index], prompts[index], opts.samples_format, info=info, suffix="-before-highres-fix") + images.save_image(image, self.outpath_samples, "", seeds[index], prompts[index], shared.opts.samples_format, info=info, suffix="-before-highres-fix") - if shared.backend == Backend.DIFFUSERS: + if shared.backend == shared.Backend.DIFFUSERS: sd_models.set_diffuser_pipe(self.sd_model, sd_models.DiffusersTaskType.TEXT_2_IMAGE) 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") if self.enable_hr and latent_scale_mode is None: if len([x for x in shared.sd_upscalers if x.name == self.hr_upscaler]) == 0: - log.warning("Could not find upscaler to use with hrfix") + shared.log.warning("Could not find upscaler to use with hrfix") self.enable_hr = False x = create_random_tensors([opt_C, self.height // opt_f, self.width // opt_f], seeds=seeds, subseeds=subseeds, subseed_strength=self.subseed_strength, seed_resize_from_h=self.seed_resize_from_h, seed_resize_from_w=self.seed_resize_from_w, p=self) samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x)) - if not self.enable_hr or state.interrupted or state.skipped: + if not self.enable_hr or shared.state.interrupted or shared.state.skipped: return samples self.is_hr_pass = True target_width = self.hr_upscale_to_x @@ -1076,7 +1101,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): class StableDiffusionProcessingImg2Img(StableDiffusionProcessing): sampler = None - def __init__(self, init_images: list = None, resize_mode: int = 0, denoising_strength: float = 0.75, image_cfg_scale: float = None, mask: Any = None, mask_blur: int = 4, inpainting_fill: int = 0, inpaint_full_res: bool = True, inpaint_full_res_padding: int = 0, inpainting_mask_invert: int = 0, initial_noise_multiplier: float = None, refiner_denoise_start: float = 0, refiner_denoise_end: float = 0, refiner_prompt: str = '', refiner_negative: str = '', **kwargs): + def __init__(self, init_images: list = None, resize_mode: int = 0, denoising_strength: float = 0.3, image_cfg_scale: float = None, mask: Any = None, mask_blur: int = 4, inpainting_fill: int = 0, inpaint_full_res: bool = True, inpaint_full_res_padding: int = 0, inpainting_mask_invert: int = 0, initial_noise_multiplier: float = None, refiner_denoise_start: float = 0, refiner_denoise_end: float = 0, refiner_prompt: str = '', refiner_negative: str = '', **kwargs): super().__init__(**kwargs) self.init_images = init_images self.resize_mode: int = resize_mode @@ -1091,7 +1116,7 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing): self.inpaint_full_res = inpaint_full_res self.inpaint_full_res_padding = inpaint_full_res_padding self.inpainting_mask_invert = inpainting_mask_invert - self.initial_noise_multiplier = opts.initial_noise_multiplier if initial_noise_multiplier is None else initial_noise_multiplier + self.initial_noise_multiplier = shared.opts.initial_noise_multiplier if initial_noise_multiplier is None else initial_noise_multiplier self.mask = None self.nmask = None self.image_conditioning = None @@ -1104,9 +1129,9 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing): def init(self, all_prompts, all_seeds, all_subseeds): image_mask = self.image_mask - if shared.backend == Backend.DIFFUSERS and image_mask is None: + if shared.backend == shared.Backend.DIFFUSERS and image_mask is None: sd_models.set_diffuser_pipe(self.sd_model, sd_models.DiffusersTaskType.IMAGE_2_IMAGE) - elif shared.backend == Backend.DIFFUSERS and image_mask is not None: + elif shared.backend == shared.Backend.DIFFUSERS and image_mask is not None: sd_models.set_diffuser_pipe(self.sd_model, sd_models.DiffusersTaskType.INPAINTING) self.sd_model.dtype = self.sd_model.unet.dtype @@ -1137,16 +1162,16 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing): self.mask_for_overlay = Image.fromarray(np_mask) self.overlay_images = [] latent_mask = self.latent_mask if self.latent_mask is not None else image_mask - add_color_corrections = opts.img2img_color_correction and self.color_corrections is None + add_color_corrections = shared.opts.img2img_color_correction and self.color_corrections is None if add_color_corrections: self.color_corrections = [] imgs = [] for img in self.init_images: # Save init image - if opts.save_init_img: + if shared.opts.save_init_img: self.init_img_hash = hashlib.md5(img.tobytes()).hexdigest() # pylint: disable=attribute-defined-outside-init - images.save_image(img, path=opts.outdir_init_images, basename=None, forced_filename=self.init_img_hash, save_to_dirs=False) - image = images.flatten(img, opts.img2img_background_color) + images.save_image(img, path=shared.opts.outdir_init_images, basename=None, forced_filename=self.init_img_hash, save_to_dirs=False) + image = images.flatten(img, shared.opts.img2img_background_color) if crop_region is None and self.resize_mode != 3: image = images.resize_image(self.resize_mode, image, self.width, self.height) if image_mask is not None: @@ -1180,7 +1205,7 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing): image = 2. * image - 1. image = image.to(device=shared.device, dtype=devices.dtype_vae) - if shared.backend == Backend.ORIGINAL: + if shared.backend == shared.Backend.ORIGINAL: self.init_latent = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(image)) else: # TODO Diffusers don't pre-encode the latents for diffusers to allow the UI to stay general for different model types @@ -1205,7 +1230,7 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing): self.image_conditioning = self.img2img_image_conditioning(image, self.init_latent, image_mask) def sample(self, conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength, prompts): - if shared.backend == Backend.DIFFUSERS: + if shared.backend == shared.Backend.DIFFUSERS: if self.init_mask is None: # pylint: disable=no-member sd_models.set_diffuser_pipe(self.sd_model, sd_models.DiffusersTaskType.IMAGE_2_IMAGE) else: @@ -1224,4 +1249,4 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing): 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 + return self.token_merging_ratio or ("token_merging_ratio" in self.override_settings and shared.opts.token_merging_ratio) or shared.opts.token_merging_ratio_img2img or shared.opts.token_merging_ratio diff --git a/modules/sd_samplers.py b/modules/sd_samplers.py index cf77e1b70..c91f97dbf 100644 --- a/modules/sd_samplers.py +++ b/modules/sd_samplers.py @@ -23,7 +23,7 @@ def list_samplers(backend_name = shared.backend): samplers = all_samplers samplers_for_img2img = all_samplers samplers_map = {} - shared.log.debug(f'Enumerated samplers: {len(all_samplers)}') + shared.log.debug(f'Samplers enumerated: {[x.name for x in all_samplers]}') list_samplers() @@ -37,6 +37,10 @@ def find_sampler_config(name): def create_sampler(name, model): + if name == 'Default' and hasattr(model, 'scheduler'): + config = {k: v for k, v in model.scheduler.config.items() if not k.startswith('_')} + shared.log.debug(f'Sampler default {type(model.scheduler).__name__}: {config}') + return model.scheduler config = find_sampler_config(name) if config is None: shared.log.error(f'Attempting to use unknown sampler: {name}') @@ -44,12 +48,15 @@ def create_sampler(name, model): if shared.backend == shared.Backend.ORIGINAL: sampler = config.constructor(model) sampler.config = config + sampler.name = name + shared.log.debug(f'Sampler: {sampler.name} {sampler.config.options}') return sampler elif shared.backend == shared.Backend.DIFFUSERS: sampler = config.constructor(model) if not hasattr(model, 'scheduler_config'): model.scheduler_config = sampler.sampler.config.copy() model.scheduler = sampler.sampler + shared.log.debug(f'Sampler: {sampler.name} {sampler.config}') return sampler.sampler else: return None diff --git a/modules/sd_samplers_diffusers.py b/modules/sd_samplers_diffusers.py index bb374fa46..9ce715114 100644 --- a/modules/sd_samplers_diffusers.py +++ b/modules/sd_samplers_diffusers.py @@ -41,6 +41,7 @@ config = { } samplers_data_diffusers = [ + sd_samplers_common.SamplerData('Default', None, [], {}), sd_samplers_common.SamplerData('UniPC', lambda model: DiffusionSampler('UniPC', UniPCMultistepScheduler, model), [], {}), sd_samplers_common.SamplerData('DDIM', lambda model: DiffusionSampler('DDIM', DDIMScheduler, model), [], {}), sd_samplers_common.SamplerData('DDPM', lambda model: DiffusionSampler('DDPM', DDPMScheduler, model), [], {}), @@ -58,6 +59,9 @@ samplers_data_diffusers = [ class DiffusionSampler: def __init__(self, name, constructor, model, **kwargs): + if name == 'Default': + return + self.name = name self.config = {} self.config = config['All'].copy() # apply global defaults if not hasattr(model, 'scheduler'): @@ -91,6 +95,9 @@ class DiffusionSampler: self.config['predict_x0'] = opts.uni_pc_variant if name == 'DPM 2M': self.config['algorithm_type'] = opts.schedulers_dpm_solver + if 'beta_start' in self.config and opts.schedulers_beta_start > 0: + self.config['beta_start'] = opts.schedulers_beta_start + if 'beta_end' in self.config and opts.schedulers_beta_end > 0: + self.config['beta_end'] = opts.schedulers_beta_end self.sampler = constructor(**self.config) self.sampler.name = name - log.debug(f'Diffusers sampler: {name} {self.config}') diff --git a/modules/sd_samplers_kdiffusion.py b/modules/sd_samplers_kdiffusion.py index 7b4a7cdab..39de81b9a 100644 --- a/modules/sd_samplers_kdiffusion.py +++ b/modules/sd_samplers_kdiffusion.py @@ -228,7 +228,6 @@ class TorchHijack: class KDiffusionSampler: def __init__(self, funcname, sd_model): denoiser = k_diffusion.external.CompVisVDenoiser if sd_model.parameterization == "v" else k_diffusion.external.CompVisDenoiser - self.model_wrap = denoiser(sd_model, quantize=shared.opts.enable_quantization) self.funcname = funcname self.func = getattr(k_diffusion.sampling, self.funcname) @@ -240,7 +239,6 @@ class KDiffusionSampler: self.config = None # set by the function calling the constructor self.last_latent = None self.s_min_uncond = None - self.conditioning_key = sd_model.model.conditioning_key def callback_state(self, d): diff --git a/modules/shared.py b/modules/shared.py index 4e9c3bf24..85b72be6a 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -362,6 +362,7 @@ options_templates.update(options_section(('cuda', "Compute Settings"), { options_templates.update(options_section(('diffusers', "Diffusers Settings"), { "diffusers_allow_safetensors": OptionInfo(True, 'Diffusers allow loading from safetensors files'), "diffusers_pipeline": OptionInfo(pipelines[0], 'Select diffuser pipeline when loading from safetensors', gr.Dropdown, lambda: {"choices": pipelines}), + "diffusers_refiner_latents": OptionInfo(True, "Use latents when using refiner"), "diffusers_move_base": OptionInfo(False, "Move base model to CPU when using refiner"), "diffusers_move_refiner": OptionInfo(True, "Move refiner model to CPU when not in use"), "diffusers_extract_ema": OptionInfo(True, "Use model EMA weights when possible"), @@ -413,8 +414,9 @@ options_templates.update(options_section(('saving-images', "Image Options"), { "n_rows": OptionInfo(-1, "Grid row count", gr.Slider, {"minimum": -1, "maximum": 16, "step": 1}), "save_txt": OptionInfo(False, "Create text file next to every image with generation parameters"), "save_log_fn": OptionInfo("", "Create JSON log file for each saved image", component_args=hide_dirs), - "save_images_before_face_restoration": OptionInfo(False, "Save copy of image before doing face restoration"), "save_images_before_highres_fix": OptionInfo(False, "Save copy of image before applying highres fix"), + # "save_images_before_refiner": OptionInfo(False, "Save copy of image before running refiner"), + "save_images_before_face_restoration": OptionInfo(False, "Save copy of image before doing face restoration"), "save_images_before_color_correction": OptionInfo(False, "Save copy of image before applying color correction"), "save_mask": OptionInfo(False, "Save copy of the inpainting greyscale mask"), "save_mask_composite": OptionInfo(False, "Save copy of inpainting masked composite"), @@ -489,7 +491,7 @@ options_templates.update(options_section(('live-preview', "Live Previews"), { })) options_templates.update(options_section(('sampler-params', "Sampler Settings"), { - "show_samplers": OptionInfo(["Euler a", "UniPC", "DEIS", "DDIM", "DPM 1S", "DPM 2M", "DPM++ 2M SDE", "DPM++ 2M SDE Karras", "DPM2 Karras", "DPM++ 2M Karras"], "Show samplers in user interface", gr.CheckboxGroup, lambda: {"choices": [x.name for x in list_samplers() if x.name != "PLMS"]}), + "show_samplers": OptionInfo(["Default", "Euler a", "UniPC", "DEIS", "DDIM", "DPM 1S", "DPM 2M", "DPM++ 2M SDE", "DPM++ 2M SDE Karras", "DPM2 Karras", "DPM++ 2M Karras"], "Show samplers in user interface", gr.CheckboxGroup, lambda: {"choices": [x.name for x in list_samplers() if x.name != "PLMS"]}), "fallback_sampler": OptionInfo("Euler a", "Secondary sampler", gr.Dropdown, lambda: {"choices": ["None"] + [x.name for x in list_samplers()]}), # "force_latent_sampler": OptionInfo("None", "Force latent upscaler sampler", gr.Dropdown, lambda: {"choices": ["None"] + [x.name for x in list_samplers()]}), 'uni_pc_variant': OptionInfo("bh1", "UniPC variant", gr.Radio, {"choices": ["bh1", "bh2", "vary_coeff"]}), @@ -500,11 +502,13 @@ options_templates.update(options_section(('sampler-params', "Sampler Settings"), "schedulers_sep_diffusers": OptionInfo("

Diffusers specific config

", "", gr.HTML), "schedulers_prediction_type": OptionInfo("default", "Samplers override model prediction type", gr.Radio, lambda: {"choices": ['default', 'epsilon', 'sample', 'v-prediction']}), - "schedulers_beta_schedule": OptionInfo("default", "Samplers override beta schedule", gr.Radio, lambda: {"choices": ['default', 'linear', 'scaled_linear', 'squaredcos_cap_v2']}), "schedulers_use_karras": OptionInfo(True, "Samplers should use Karras sigmas where applicable"), "schedulers_use_loworder": OptionInfo(True, "Samplers should use use lower-order solvers in the final steps where applicable"), "schedulers_use_thresholding": OptionInfo(False, "Samplers should use dynamic thresholding where applicable"), "schedulers_dpm_solver": OptionInfo("sde-dpmsolver++", "Samplers DPM solver algorithm", gr.Radio, lambda: {"choices": ['dpmsolver', 'dpmsolver++', 'sde-dpmsolver++']}), + "schedulers_beta_schedule": OptionInfo("default", "Samplers override beta schedule", gr.Radio, lambda: {"choices": ['default', 'linear', 'scaled_linear', 'squaredcos_cap_v2']}), + 'schedulers_beta_start': OptionInfo(0, "Samplers override beta start", gr.Number, {}), + 'schedulers_beta_end': OptionInfo(0, "Samplers override beta end", gr.Number, {}), "schedulers_sep_kdiffusers": OptionInfo("

K-Diffusion specific config

", "", gr.HTML), "always_batch_cond_uncond": OptionInfo(False, "Disable conditional batching enabled on low memory systems"), diff --git a/modules/txt2img.py b/modules/txt2img.py index 098d5fcf8..c0366504b 100644 --- a/modules/txt2img.py +++ b/modules/txt2img.py @@ -44,7 +44,7 @@ def txt2img(id_task: str, prompt: str, negative_prompt: str, prompt_styles, step restore_faces=restore_faces, tiling=tiling, enable_hr=enable_hr, - denoising_strength=denoising_strength if enable_hr else None, + denoising_strength=denoising_strength, hr_scale=hr_scale, hr_upscaler=hr_upscaler, hr_second_pass_steps=hr_second_pass_steps, diff --git a/modules/ui.py b/modules/ui.py index afb1b65a4..9090c75a4 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -155,8 +155,8 @@ def create_seed_inputs(target_interface): reuse_subseed = ToolButton(reuse_symbol, elem_id=f"{target_interface}_reuse_subseed") subseed_strength = gr.Slider(label='Variation strength', value=0.0, minimum=0, maximum=1, step=0.01, elem_id=f"{target_interface}_subseed_strength") with FormRow(visible=False): - seed_resize_from_w = gr.Slider(minimum=0, maximum=2048, step=8, label="Resize seed from width", value=0, elem_id=f"{target_interface}_seed_resize_from_w") - seed_resize_from_h = gr.Slider(minimum=0, maximum=2048, step=8, label="Resize seed from height", value=0, elem_id=f"{target_interface}_seed_resize_from_h") + seed_resize_from_w = gr.Slider(minimum=0, maximum=4096, step=8, label="Resize seed from width", value=0, elem_id=f"{target_interface}_seed_resize_from_w") + seed_resize_from_h = gr.Slider(minimum=0, maximum=4096, step=8, label="Resize seed from height", value=0, elem_id=f"{target_interface}_seed_resize_from_h") random_seed.click(fn=lambda: [-1, -1], show_progress=False, inputs=[], outputs=[seed, subseed]) random_subseed.click(fn=lambda: -1, show_progress=False, inputs=[], outputs=[subseed]) return seed, reuse_seed, subseed, reuse_subseed, subseed_strength, seed_resize_from_h, seed_resize_from_w @@ -302,13 +302,7 @@ def create_refresh_button(refresh_component, refresh_method, refreshed_args, ele def create_sampler_and_steps_selection(choices, tabname, primary: bool = True): with FormRow(elem_id=f"sampler_selection_{tabname}{'_alt' if not primary else ''}"): - if 'UniPC' in [sampler.name for sampler in choices]: - default_sampler_name = 'UniPC' - elif 'Euler a' in [sampler.name for sampler in choices]: - default_sampler_name = 'Euler a' - else: - default_sampler_name = modules.sd_samplers.samplers[0].name - sampler_index = gr.Dropdown(label='Sampling method' if primary else 'Secondary sampler', elem_id=f"{tabname}_sampling{'_alt' if not primary else ''}", choices=[x.name for x in choices], value=default_sampler_name, type="index") + sampler_index = gr.Dropdown(label='Sampling method' if primary else 'Secondary sampler', elem_id=f"{tabname}_sampling{'_alt' if not primary else ''}", choices=[x.name for x in choices], value='Default', type="index") steps = gr.Slider(minimum=0, maximum=99, step=1, label="Sampling steps" if primary else 'Secondary steps', elem_id=f"{tabname}_steps{'_alt' if not primary else ''}", value=20) return steps, sampler_index @@ -360,8 +354,8 @@ def create_ui(startup_timer = None): with FormRow(): with gr.Column(elem_id="txt2img_column_size", scale=4): with FormRow(elem_id="txt2img_row_dimension"): - width = gr.Slider(minimum=64, maximum=2048, step=8, label="Width", value=512, elem_id="txt2img_width") - height = gr.Slider(minimum=64, maximum=2048, step=8, label="Height", value=512, elem_id="txt2img_height") + width = gr.Slider(minimum=64, maximum=4096, step=8, label="Width", value=512, elem_id="txt2img_width") + height = gr.Slider(minimum=64, maximum=4096, step=8, label="Height", value=512, elem_id="txt2img_height") with gr.Column(elem_id="txt2img_dimensions_row", scale=1, elem_classes="dimensions-tools"): res_switch_btn = ToolButton(value=switch_values_symbol, elem_id="txt2img_res_switch_btn", label="Switch dims") with gr.Column(elem_id="txt2img_column_batch"): @@ -383,7 +377,7 @@ def create_ui(startup_timer = None): with FormGroup(visible=False, elem_id="txt2img_second_pass") as hr_options: hr_second_pass_steps, latent_index = create_sampler_and_steps_selection(modules.sd_samplers.samplers, "txt2img", False) with FormRow(elem_id="txt2img_hires_fix_row1", variant="compact"): - denoising_strength = gr.Slider(minimum=0.0, maximum=1.0, step=0.01, label='Denoising strength', value=0.7, elem_id="txt2img_denoising_strength") + denoising_strength = gr.Slider(minimum=0.0, maximum=1.0, step=0.01, label='Denoising strength', value=0.3, elem_id="txt2img_denoising_strength") with FormRow(): hr_final_resolution = FormHTML(value="", elem_id="txtimg_hr_finalres", label="Upscaled resolution", interactive=False) @@ -391,13 +385,13 @@ def create_ui(startup_timer = None): hr_upscaler = gr.Dropdown(label="Upscaler", elem_id="txt2img_hr_upscaler", choices=[*modules.shared.latent_upscale_modes, *[x.name for x in modules.shared.sd_upscalers]], value=modules.shared.latent_upscale_default_mode) hr_scale = gr.Slider(minimum=1.0, maximum=4.0, step=0.05, label="Upscale by", value=2.0, elem_id="txt2img_hr_scale") with FormRow(elem_id="txt2img_hires_fix_row3", variant="compact"): - 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") + hr_resize_x = gr.Slider(minimum=0, maximum=4096, step=8, label="Resize width to", value=0, elem_id="txt2img_hr_resize_x") + hr_resize_y = gr.Slider(minimum=0, maximum=4096, step=8, label="Resize height to", value=0, elem_id="txt2img_hr_resize_y") with FormRow(): hr_refiner = FormHTML(value="Refiner", elem_id="txtimg_hr_finalres", interactive=False) with FormRow(elem_id="txt2img_refiner_row1", variant="compact"): - image_cfg_scale = gr.Slider(minimum=1.0, maximum=30.0, step=0.1, label='Secondary CFG Scale', value=6.0, elem_id="txt2img_image_cfg_scale") + image_cfg_scale = gr.Slider(minimum=1.1, maximum=30.0, step=0.1, label='Secondary CFG Scale', value=6.0, elem_id="txt2img_image_cfg_scale") diffusers_guidance_rescale = gr.Slider(minimum=0.0, maximum=1.0, step=0.05, label='Guidance rescale', value=0.7, elem_id="txt2img_image_cfg_rescale") refiner_denoise_start = gr.Slider(minimum=0.0, maximum=1.0, step=0.05, label='Denoise start', value=0.0, elem_id="txt2img_refiner_denoise_start") refiner_denoise_end = gr.Slider(minimum=0.0, maximum=1.0, step=0.05, label='Denoise end', value=1.0, elem_id="txt2img_refiner_denoise_end") @@ -619,8 +613,8 @@ def create_ui(startup_timer = None): with FormRow(): with gr.Column(elem_id="img2img_column_size", scale=4): with FormRow(): - width = gr.Slider(minimum=64, maximum=2048, step=8, label="Width", value=512, elem_id="img2img_width") - height = gr.Slider(minimum=64, maximum=2048, step=8, label="Height", value=512, elem_id="img2img_height") + width = gr.Slider(minimum=64, maximum=4096, step=8, label="Width", value=512, elem_id="img2img_width") + height = gr.Slider(minimum=64, maximum=4096, step=8, label="Height", value=512, elem_id="img2img_height") with gr.Column(elem_id="img2img_column_dim", scale=1, elem_classes="dimensions-tools"): with FormRow(): res_switch_btn = ToolButton(value=switch_values_symbol, elem_id="img2img_res_switch_btn") diff --git a/modules/ui_loadsave.py b/modules/ui_loadsave.py index 78ff6ccaa..1ce4af25d 100644 --- a/modules/ui_loadsave.py +++ b/modules/ui_loadsave.py @@ -97,8 +97,11 @@ class UiLoadsave: self.add_component(f"{path}/{x.value}", x) def read_from_file(self): - with open(self.filename, "r", encoding="utf8") as file: - return json.load(file) + if os.path.exists(self.filename): + with open(self.filename, "r", encoding="utf8") as file: + return json.load(file) + else: + return {} def write_to_file(self, current_ui_settings): with open(self.filename, "w", encoding="utf8") as file: diff --git a/requirements.txt b/requirements.txt index 7722d9577..b1cb94aab 100644 --- a/requirements.txt +++ b/requirements.txt @@ -42,6 +42,7 @@ yapf scikit-image basicsr compel +pyarrow==11.0.0 typing-extensions==4.7.1 antlr4-python3-runtime==4.9.3 pydantic==1.10.11 diff --git a/scripts/xyz_grid.py b/scripts/xyz_grid.py index ca5b55ac6..96088d68a 100644 --- a/scripts/xyz_grid.py +++ b/scripts/xyz_grid.py @@ -52,14 +52,14 @@ def apply_order(p, x, xs): def apply_sampler(p, x, xs): - sampler_name = sd_samplers.samplers_map.get(x.lower(), None) + sampler_name = sd_samplers.samplers_map.get(x, None) if sampler_name is None: shared.log.warning(f"XYZ grid: unknown sampler: {x}") else: p.sampler_name = sampler_name def apply_latent_sampler(p, x, xs): - latent_sampler = sd_samplers.samplers_map.get(x.lower(), None) + latent_sampler = sd_samplers.samplers_map.get(x, None) if latent_sampler is None: shared.log.warning(f"XYZ grid: unknown sampler: {x}") else: @@ -67,7 +67,7 @@ def apply_latent_sampler(p, x, xs): def confirm_samplers(p, xs): for x in xs: - if x.lower() not in sd_samplers.samplers_map: + if x not in sd_samplers.samplers_map: shared.log.warning(f"XYZ grid: unknown sampler: {x}") diff --git a/webui.py b/webui.py index 84b56ccc3..6edb35cb8 100644 --- a/webui.py +++ b/webui.py @@ -159,7 +159,7 @@ def initialize(): # make the program just exit at ctrl+c without waiting for anything def sigint_handler(_sig, _frame): log.info('Exiting') - os._exit(0) + sys.exit(0) signal.signal(signal.SIGINT, sigint_handler)