From 865c0bc7a38579574ba2047b2a028279ec84bf93 Mon Sep 17 00:00:00 2001 From: Vladimir Mandic Date: Thu, 4 May 2023 07:51:28 -0400 Subject: [PATCH] merge from upstream --- extensions-builtin/LDSR/scripts/ldsr_model.py | 20 +-- .../ScuNET/scripts/scunet_model.py | 81 +++++++++--- extensions-builtin/a1111-sd-webui-lycoris | 2 +- .../multidiffusion-upscaler-for-automatic1111 | 2 +- .../javascript/prompt-bracket-checker.js | 119 +++++------------- extensions-builtin/sd-webui-controlnet | 2 +- javascript/edit-attention.js | 38 ++++-- modules/api/api.py | 17 ++- modules/extensions.py | 33 ++++- modules/extras.py | 47 ++++++- modules/images.py | 32 ++++- modules/img2img.py | 8 +- modules/processing.py | 21 +++- modules/realesrgan_model.py | 17 ++- modules/script_callbacks.py | 14 +++ modules/sd_samplers_kdiffusion.py | 44 +++++-- modules/textual_inversion/preprocess.py | 20 +-- 17 files changed, 339 insertions(+), 178 deletions(-) diff --git a/extensions-builtin/LDSR/scripts/ldsr_model.py b/extensions-builtin/LDSR/scripts/ldsr_model.py index b8cff29b9..da19cff12 100644 --- a/extensions-builtin/LDSR/scripts/ldsr_model.py +++ b/extensions-builtin/LDSR/scripts/ldsr_model.py @@ -25,22 +25,28 @@ class UpscalerLDSR(Upscaler): yaml_path = os.path.join(self.model_path, "project.yaml") old_model_path = os.path.join(self.model_path, "model.pth") new_model_path = os.path.join(self.model_path, "model.ckpt") - safetensors_model_path = os.path.join(self.model_path, "model.safetensors") + + local_model_paths = self.find_models(ext_filter=[".ckpt", ".safetensors"]) + local_ckpt_path = next(iter([local_model for local_model in local_model_paths if local_model.endswith("model.ckpt")]), None) + local_safetensors_path = next(iter([local_model for local_model in local_model_paths if local_model.endswith("model.safetensors")]), None) + local_yaml_path = next(iter([local_model for local_model in local_model_paths if local_model.endswith("project.yaml")]), None) + if os.path.exists(yaml_path): statinfo = os.stat(yaml_path) if statinfo.st_size >= 10485760: print("Removing invalid LDSR YAML file.") os.remove(yaml_path) + if os.path.exists(old_model_path): print("Renaming model from model.pth to model.ckpt") os.rename(old_model_path, new_model_path) - if os.path.exists(safetensors_model_path): - model = safetensors_model_path + + if local_safetensors_path is not None and os.path.exists(local_safetensors_path): + model = local_safetensors_path else: - model = load_file_from_url(url=self.model_url, model_dir=self.model_path, - file_name="model.ckpt", progress=True) - yaml = load_file_from_url(url=self.yaml_url, model_dir=self.model_path, - file_name="project.yaml", progress=True) + model = local_ckpt_path if local_ckpt_path is not None else load_file_from_url(url=self.model_url, model_dir=self.model_path, file_name="model.ckpt", progress=True) + + yaml = local_yaml_path if local_yaml_path is not None else load_file_from_url(url=self.yaml_url, model_dir=self.model_path, file_name="project.yaml", progress=True) try: return LDSR(model, yaml) diff --git a/extensions-builtin/ScuNET/scripts/scunet_model.py b/extensions-builtin/ScuNET/scripts/scunet_model.py index e0fbf3a33..c7fd5739b 100644 --- a/extensions-builtin/ScuNET/scripts/scunet_model.py +++ b/extensions-builtin/ScuNET/scripts/scunet_model.py @@ -5,11 +5,15 @@ import traceback import PIL.Image import numpy as np import torch +from tqdm import tqdm + from basicsr.utils.download_util import load_file_from_url import modules.upscaler from modules import devices, modelloader from scunet_model_arch import SCUNet as net +from modules.shared import opts +from modules import images class UpscalerScuNET(modules.upscaler.Upscaler): @@ -42,28 +46,78 @@ class UpscalerScuNET(modules.upscaler.Upscaler): scalers.append(scaler_data2) self.scalers = scalers - def do_upscale(self, img: PIL.Image, selected_file): + @staticmethod + @torch.no_grad() + def tiled_inference(img, model): + # test the image tile by tile + h, w = img.shape[2:] + tile = opts.SCUNET_tile + tile_overlap = opts.SCUNET_tile_overlap + if tile == 0: + return model(img) + + device = devices.get_device_for('scunet') + assert tile % 8 == 0, "tile size should be a multiple of window_size" + sf = 1 + + stride = tile - tile_overlap + h_idx_list = list(range(0, h - tile, stride)) + [h - tile] + w_idx_list = list(range(0, w - tile, stride)) + [w - tile] + E = torch.zeros(1, 3, h * sf, w * sf, dtype=img.dtype, device=device) + W = torch.zeros_like(E, dtype=devices.dtype, device=device) + + with tqdm(total=len(h_idx_list) * len(w_idx_list), desc="ScuNET tiles") as pbar: + for h_idx in h_idx_list: + + for w_idx in w_idx_list: + + in_patch = img[..., h_idx: h_idx + tile, w_idx: w_idx + tile] + + out_patch = model(in_patch) + out_patch_mask = torch.ones_like(out_patch) + + E[ + ..., h_idx * sf: (h_idx + tile) * sf, w_idx * sf: (w_idx + tile) * sf + ].add_(out_patch) + W[ + ..., h_idx * sf: (h_idx + tile) * sf, w_idx * sf: (w_idx + tile) * sf + ].add_(out_patch_mask) + pbar.update(1) + output = E.div_(W) + + return output + + def do_upscale(self, img: PIL.Image.Image, selected_file): + torch.cuda.empty_cache() model = self.load_model(selected_file) if model is None: + print(f"ScuNET: Unable to load model from {selected_file}", file=sys.stderr) return img device = devices.get_device_for('scunet') - img = np.array(img) - img = img[:, :, ::-1] - img = np.moveaxis(img, 2, 0) / 255 - img = torch.from_numpy(img).float() - img = img.unsqueeze(0).to(device) + tile = opts.SCUNET_tile + h, w = img.height, img.width + np_img = np.array(img) + np_img = np_img[:, :, ::-1] # RGB to BGR + np_img = np_img.transpose((2, 0, 1)) / 255 # HWC to CHW + torch_img = torch.from_numpy(np_img).float().unsqueeze(0).to(device) # type: ignore - with torch.no_grad(): - output = model(img) - output = output.squeeze().float().cpu().clamp_(0, 1).numpy() - output = 255. * np.moveaxis(output, 0, 2) - output = output.astype(np.uint8) - output = output[:, :, ::-1] + if tile > h or tile > w: + _img = torch.zeros(1, 3, max(h, tile), max(w, tile), dtype=torch_img.dtype, device=torch_img.device) + _img[:, :, :h, :w] = torch_img # pad image + torch_img = _img + + torch_output = self.tiled_inference(torch_img, model).squeeze(0) + torch_output = torch_output[:, :h * 1, :w * 1] # remove padding, if any + np_output: np.ndarray = torch_output.float().cpu().clamp_(0, 1).numpy() + del torch_img, torch_output torch.cuda.empty_cache() - return PIL.Image.fromarray(output, 'RGB') + + output = np_output.transpose((1, 2, 0)) # CHW to HWC + output = output[:, :, ::-1] # BGR to RGB + return PIL.Image.fromarray((output * 255).astype(np.uint8)) def load_model(self, path: str): device = devices.get_device_for('scunet') @@ -84,4 +138,3 @@ class UpscalerScuNET(modules.upscaler.Upscaler): model = model.to(device) return model - diff --git a/extensions-builtin/a1111-sd-webui-lycoris b/extensions-builtin/a1111-sd-webui-lycoris index 3176baedf..b2a4e5f92 160000 --- a/extensions-builtin/a1111-sd-webui-lycoris +++ b/extensions-builtin/a1111-sd-webui-lycoris @@ -1 +1 @@ -Subproject commit 3176baedf003c382fea4dfc32bd926ce210bf883 +Subproject commit b2a4e5f9292ab0f4cb17739afc7af5d3a713eb54 diff --git a/extensions-builtin/multidiffusion-upscaler-for-automatic1111 b/extensions-builtin/multidiffusion-upscaler-for-automatic1111 index 8d8be4c33..fbe34db70 160000 --- a/extensions-builtin/multidiffusion-upscaler-for-automatic1111 +++ b/extensions-builtin/multidiffusion-upscaler-for-automatic1111 @@ -1 +1 @@ -Subproject commit 8d8be4c3390b7356d06645b1f8eb486a09663b71 +Subproject commit fbe34db704736e5745c3a4e855939508eef344ce diff --git a/extensions-builtin/prompt-bracket-checker/javascript/prompt-bracket-checker.js b/extensions-builtin/prompt-bracket-checker/javascript/prompt-bracket-checker.js index f0918e260..5c7a836a2 100644 --- a/extensions-builtin/prompt-bracket-checker/javascript/prompt-bracket-checker.js +++ b/extensions-builtin/prompt-bracket-checker/javascript/prompt-bracket-checker.js @@ -1,103 +1,42 @@ // Stable Diffusion WebUI - Bracket checker -// Version 1.0 -// By Hingashi no Florin/Bwin4L +// By Hingashi no Florin/Bwin4L & @akx // Counts open and closed brackets (round, square, curly) in the prompt and negative prompt text boxes in the txt2img and img2img tabs. // If there's a mismatch, the keyword counter turns red and if you hover on it, a tooltip tells you what's wrong. -function checkBrackets(evt, textArea, counterElt) { - errorStringParen = '(...) - Different number of opening and closing parentheses detected.\n'; - errorStringSquare = '[...] - Different number of opening and closing square brackets detected.\n'; - errorStringCurly = '{...} - Different number of opening and closing curly brackets detected.\n'; +function checkBrackets(textArea, counterElt) { + var counts = {}; + (textArea.value.match(/[(){}\[\]]/g) || []).forEach(bracket => { + counts[bracket] = (counts[bracket] || 0) + 1; + }); + var errors = []; - openBracketRegExp = /\(/g; - closeBracketRegExp = /\)/g; - - openSquareBracketRegExp = /\[/g; - closeSquareBracketRegExp = /\]/g; - - openCurlyBracketRegExp = /\{/g; - closeCurlyBracketRegExp = /\}/g; - - totalOpenBracketMatches = 0; - totalCloseBracketMatches = 0; - totalOpenSquareBracketMatches = 0; - totalCloseSquareBracketMatches = 0; - totalOpenCurlyBracketMatches = 0; - totalCloseCurlyBracketMatches = 0; - - openBracketMatches = textArea.value.match(openBracketRegExp); - if(openBracketMatches) { - totalOpenBracketMatches = openBracketMatches.length; - } - - closeBracketMatches = textArea.value.match(closeBracketRegExp); - if(closeBracketMatches) { - totalCloseBracketMatches = closeBracketMatches.length; - } - - openSquareBracketMatches = textArea.value.match(openSquareBracketRegExp); - if(openSquareBracketMatches) { - totalOpenSquareBracketMatches = openSquareBracketMatches.length; - } - - closeSquareBracketMatches = textArea.value.match(closeSquareBracketRegExp); - if(closeSquareBracketMatches) { - totalCloseSquareBracketMatches = closeSquareBracketMatches.length; - } - - openCurlyBracketMatches = textArea.value.match(openCurlyBracketRegExp); - if(openCurlyBracketMatches) { - totalOpenCurlyBracketMatches = openCurlyBracketMatches.length; - } - - closeCurlyBracketMatches = textArea.value.match(closeCurlyBracketRegExp); - if(closeCurlyBracketMatches) { - totalCloseCurlyBracketMatches = closeCurlyBracketMatches.length; - } - - if(totalOpenBracketMatches != totalCloseBracketMatches) { - if(!counterElt.title.includes(errorStringParen)) { - counterElt.title += errorStringParen; + function checkPair(open, close, kind) { + if (counts[open] !== counts[close]) { + errors.push( + `${open}...${close} - Detected ${counts[open] || 0} opening and ${counts[close] || 0} closing ${kind}.` + ); } - } else { - counterElt.title = counterElt.title.replace(errorStringParen, ''); } - if(totalOpenSquareBracketMatches != totalCloseSquareBracketMatches) { - if(!counterElt.title.includes(errorStringSquare)) { - counterElt.title += errorStringSquare; - } - } else { - counterElt.title = counterElt.title.replace(errorStringSquare, ''); - } + checkPair('(', ')', 'round brackets'); + checkPair('[', ']', 'square brackets'); + checkPair('{', '}', 'curly brackets'); + counterElt.title = errors.join('\n'); + counterElt.classList.toggle('error', errors.length !== 0); +} - if(totalOpenCurlyBracketMatches != totalCloseCurlyBracketMatches) { - if(!counterElt.title.includes(errorStringCurly)) { - counterElt.title += errorStringCurly; - } - } else { - counterElt.title = counterElt.title.replace(errorStringCurly, ''); - } +function setupBracketChecking(id_prompt, id_counter) { + var textarea = gradioApp().querySelector("#" + id_prompt + " > label > textarea"); + var counter = gradioApp().getElementById(id_counter) - if(counterElt.title != '') { - counterElt.classList.add('error'); - } else { - counterElt.classList.remove('error'); + if (textarea && counter) { + textarea.addEventListener("input", () => checkBrackets(textarea, counter)); } } -function setupBracketChecking(id_prompt, id_counter){ - var textarea = gradioApp().querySelector("#" + id_prompt + " > label > textarea"); - var counter = gradioApp().getElementById(id_counter) - - textarea.addEventListener("input", function(evt){ - checkBrackets(evt, textarea, counter) - }); -} - -onUiLoaded(function(){ - setupBracketChecking('txt2img_prompt', 'txt2img_token_counter') - setupBracketChecking('txt2img_neg_prompt', 'txt2img_negative_token_counter') - setupBracketChecking('img2img_prompt', 'img2img_token_counter') - setupBracketChecking('img2img_neg_prompt', 'img2img_negative_token_counter') -}) \ No newline at end of file +onUiLoaded(function () { + setupBracketChecking('txt2img_prompt', 'txt2img_token_counter'); + setupBracketChecking('txt2img_neg_prompt', 'txt2img_negative_token_counter'); + setupBracketChecking('img2img_prompt', 'img2img_token_counter'); + setupBracketChecking('img2img_neg_prompt', 'img2img_negative_token_counter'); +}); diff --git a/extensions-builtin/sd-webui-controlnet b/extensions-builtin/sd-webui-controlnet index 23c0c8030..5d387abf1 160000 --- a/extensions-builtin/sd-webui-controlnet +++ b/extensions-builtin/sd-webui-controlnet @@ -1 +1 @@ -Subproject commit 23c0c80306861c1b90a9025dd1f52d3810a3c0d5 +Subproject commit 5d387abf19d9eedf58dd294ccc373c0e361b2907 diff --git a/javascript/edit-attention.js b/javascript/edit-attention.js index 20a5aadfb..588c7b773 100644 --- a/javascript/edit-attention.js +++ b/javascript/edit-attention.js @@ -17,7 +17,7 @@ function keyupEditAttention(event){ // Find opening parenthesis around current cursor const before = text.substring(0, selectionStart); let beforeParen = before.lastIndexOf(OPEN); - if (beforeParen == -1) return false; + if (beforeParen == -1) return false; let beforeParenClose = before.lastIndexOf(CLOSE); while (beforeParenClose !== -1 && beforeParenClose > beforeParen) { beforeParen = before.lastIndexOf(OPEN, beforeParen - 1); @@ -27,7 +27,7 @@ function keyupEditAttention(event){ // Find closing parenthesis around current cursor const after = text.substring(selectionStart); let afterParen = after.indexOf(CLOSE); - if (afterParen == -1) return false; + if (afterParen == -1) return false; let afterParenOpen = after.indexOf(OPEN); while (afterParenOpen !== -1 && afterParen > afterParenOpen) { afterParen = after.indexOf(CLOSE, afterParen + 1); @@ -43,10 +43,28 @@ function keyupEditAttention(event){ target.setSelectionRange(selectionStart, selectionEnd); return true; } + + function selectCurrentWord(){ + if (selectionStart !== selectionEnd) return false; + const delimiters = opts.keyedit_delimiters + " \r\n\t"; + + // seek backward until to find beggining + while (!delimiters.includes(text[selectionStart - 1]) && selectionStart > 0) { + selectionStart--; + } + + // seek forward to find end + while (!delimiters.includes(text[selectionEnd]) && selectionEnd < text.length) { + selectionEnd++; + } - // If the user hasn't selected anything, let's select their current parenthesis block - if(! selectCurrentParenthesisBlock('<', '>')){ - selectCurrentParenthesisBlock('(', ')') + target.setSelectionRange(selectionStart, selectionEnd); + return true; + } + + // If the user hasn't selected anything, let's select their current parenthesis block or word + if (!selectCurrentParenthesisBlock('<', '>') && !selectCurrentParenthesisBlock('(', ')')) { + selectCurrentWord(); } event.preventDefault(); @@ -81,7 +99,13 @@ function keyupEditAttention(event){ weight = parseFloat(weight.toPrecision(12)); if(String(weight).length == 1) weight += ".0" - text = text.slice(0, selectionEnd + 1) + weight + text.slice(selectionEnd + 1 + end - 1); + if (closeCharacter == ')' && weight == 1) { + text = text.slice(0, selectionStart - 1) + text.slice(selectionStart, selectionEnd) + text.slice(selectionEnd + 5); + selectionStart--; + selectionEnd--; + } else { + text = text.slice(0, selectionEnd + 1) + weight + text.slice(selectionEnd + 1 + end - 1); + } target.focus(); target.value = text; @@ -93,4 +117,4 @@ function keyupEditAttention(event){ addEventListener('keydown', (event) => { keyupEditAttention(event); -}); \ No newline at end of file +}); diff --git a/modules/api/api.py b/modules/api/api.py index 28ccff02f..b3eb04f05 100644 --- a/modules/api/api.py +++ b/modules/api/api.py @@ -14,7 +14,7 @@ import piexif.helper import uvicorn import gradio as gr # from gradio.processing_utils import decode_base64_to_file # gradio 3.23 -from gradio_client.utils import decode_base64_to_file # gradio 3.28 +# from gradio_client.utils import decode_base64_to_file # gradio 3.28 from modules import errors, shared, sd_samplers, deepbooru, sd_hijack, images, scripts, ui, postprocessing from modules.api.models import * # pylint: disable=unused-wildcard-import, wildcard-import @@ -198,7 +198,9 @@ class Api: raise HTTPException(status_code=422, detail=f"Selectable script cannot be in always on params: {alwayson_script_name}") if "args" in request.alwayson_scripts[alwayson_script_name]: # TODO this can corrupt values for other scripts - script_args[alwayson_script.args_from:alwayson_script.args_to] = request.alwayson_scripts[alwayson_script_name]["args"] + # min between arg length in scriptrunner and arg length in the request + for idx in range(0, min((alwayson_script.args_to - alwayson_script.args_from), len(request.alwayson_scripts[alwayson_script_name]["args"]))): + script_args[alwayson_script.args_from + idx] = request.alwayson_scripts[alwayson_script_name]["args"][idx] p.per_script_args[alwayson_script.title()] = request.alwayson_scripts[alwayson_script_name]["args"] return script_args @@ -306,16 +308,11 @@ class Api: def extras_batch_images_api(self, req: ExtrasBatchImagesRequest): reqDict = setUpscalers(req) - def prepareFiles(file): - file = decode_base64_to_file(file.data, file_path=file.name) - file.orig_name = file.name - return file - - reqDict['image_folder'] = list(map(prepareFiles, reqDict['imageList'])) - reqDict.pop('imageList') + image_list = reqDict.pop('imageList', []) + image_folder = [decode_base64_to_image(x.data) for x in image_list] with self.queue_lock: - result = postprocessing.run_extras(extras_mode=1, image="", input_dir="", output_dir="", save_output=False, **reqDict) + result = postprocessing.run_extras(extras_mode=1, image_folder=image_folder, image="", input_dir="", output_dir="", save_output=False, **reqDict) return ExtrasBatchImagesResponse(images=list(map(encode_pil_to_base64, result[0])), html_info=result[1]) diff --git a/modules/extensions.py b/modules/extensions.py index 349c8e671..b0d78259a 100644 --- a/modules/extensions.py +++ b/modules/extensions.py @@ -28,12 +28,15 @@ class Extension: self.status = '' self.can_update = False self.is_builtin = is_builtin + self.commit_hash = '' + self.commit_date = None self.version = '' + self.branch = None self.remote = None self.have_info_from_repo = False def read_info_from_repo(self): - if self.have_info_from_repo: + if self.is_builtin or self.have_info_from_repo: return self.have_info_from_repo = True @@ -52,10 +55,15 @@ class Extension: self.status = 'unknown' self.remote = next(repo.remote().urls, None) head = repo.head.commit - ts = time.asctime(time.gmtime(repo.head.commit.committed_date)) - self.version = f'{head.hexsha[:8]} ({ts})' + self.commit_date = repo.head.commit.committed_date + ts = time.asctime(time.gmtime(self.commit_date)) + if repo.active_branch: + self.branch = repo.active_branch.name + self.commit_hash = head.hexsha + self.version = f'{self.commit_hash[:8]} ({ts})' - except Exception: + except Exception as ex: + shared.log.error(f"Failed reading extension data from Git repository: {self.name}: {ex}") self.remote = None def list_files(self, subdir, extension): @@ -82,18 +90,31 @@ class Extension: for fetch in repo.remote().fetch(dry_run=True): if fetch.flags != fetch.HEAD_UPTODATE: self.can_update = True - self.status = "behind" + self.status = "new commits" return + try: + origin = repo.rev_parse('origin') + if repo.head.commit != origin: + self.can_update = True + self.status = "behind HEAD" + return + except Exception: + self.can_update = False + self.status = "unknown (remote error)" + return + self.can_update = False self.status = "latest" - def fetch_and_reset_hard(self): + def fetch_and_reset_hard(self, commit='origin'): repo = git.Repo(self.path) # Fix: `error: Your local changes to the following files would be overwritten by merge`, # because WSL2 Docker set 755 file permissions instead of 644, this results to the error. repo.git.fetch(all=True) repo.git.reset('origin', hard=True) + repo.git.reset(commit, hard=True) + self.have_info_from_repo = False def list_extensions(): diff --git a/modules/extras.py b/modules/extras.py index 76f74b248..cdfb78410 100644 --- a/modules/extras.py +++ b/modules/extras.py @@ -1,6 +1,7 @@ import os import re import html +import json import shutil import torch @@ -63,7 +64,7 @@ def to_half(tensor, enable): return tensor -def run_modelmerger(id_task, primary_model_name, secondary_model_name, tertiary_model_name, interp_method, multiplier, save_as_half, custom_name, checkpoint_format, config_source, bake_in_vae, discard_weights): # pylint: disable=unused-argument +def run_modelmerger(id_task, primary_model_name, secondary_model_name, tertiary_model_name, interp_method, multiplier, save_as_half, custom_name, checkpoint_format, config_source, bake_in_vae, discard_weights, save_metadata): # pylint: disable=unused-argument shared.state.begin() shared.state.job = 'model-merge' @@ -231,15 +232,55 @@ def run_modelmerger(id_task, primary_model_name, secondary_model_name, tertiary_ shared.state.nextjob() shared.state.textinfo = "Saving" - shared.log.info(f"Saving to {output_modelname}...") + + metadata = {"format": "pt", "sd_merge_models": {}, "sd_merge_recipe": None} + + if save_metadata: + merge_recipe = { + "type": "webui", # indicate this model was merged with webui's built-in merger + "primary_model_hash": primary_model_info.sha256, + "secondary_model_hash": secondary_model_info.sha256 if secondary_model_info else None, + "tertiary_model_hash": tertiary_model_info.sha256 if tertiary_model_info else None, + "interp_method": interp_method, + "multiplier": multiplier, + "save_as_half": save_as_half, + "custom_name": custom_name, + "config_source": config_source, + "bake_in_vae": bake_in_vae, + "discard_weights": discard_weights, + "is_inpainting": result_is_inpainting_model, + "is_instruct_pix2pix": result_is_instruct_pix2pix_model + } + metadata["sd_merge_recipe"] = json.dumps(merge_recipe) + + def add_model_metadata(checkpoint_info): + checkpoint_info.calculate_shorthash() + metadata["sd_merge_models"][checkpoint_info.sha256] = { + "name": checkpoint_info.name, + "legacy_hash": checkpoint_info.hash, + "sd_merge_recipe": checkpoint_info.metadata.get("sd_merge_recipe", None) + } + + metadata["sd_merge_models"].update(checkpoint_info.metadata.get("sd_merge_models", {})) + + add_model_metadata(primary_model_info) + if secondary_model_info: + add_model_metadata(secondary_model_info) + if tertiary_model_info: + add_model_metadata(tertiary_model_info) + + metadata["sd_merge_models"] = json.dumps(metadata["sd_merge_models"]) _, extension = os.path.splitext(output_modelname) if extension.lower() == ".safetensors": - safetensors.torch.save_file(theta_0, output_modelname, metadata={"format": "pt"}) + safetensors.torch.save_file(theta_0, output_modelname, metadata=metadata) else: torch.save(theta_0, output_modelname) sd_models.list_models() + created_model = next((ckpt for ckpt in sd_models.checkpoints_list.values() if ckpt.name == filename), None) + if created_model: + created_model.calculate_shorthash() create_config(output_modelname, config_source, primary_model_info, secondary_model_info, tertiary_model_info) diff --git a/modules/images.py b/modules/images.py index 610fd7291..f23232225 100644 --- a/modules/images.py +++ b/modules/images.py @@ -313,6 +313,7 @@ re_nonletters = re.compile(r'[\s' + string.punctuation + ']+') re_pattern = re.compile(r"(.*?)(?:\[([^\[\]]+)\]|$)") re_pattern_arg = re.compile(r"(.*)<([^>]*)>$") max_filename_part_length = 128 +NOTHING_AND_SKIP_PREVIOUS_TEXT = object() def sanitize_filename_part(text, replace_spaces=True): @@ -347,6 +348,10 @@ class FilenameGenerator: 'prompt_no_styles': lambda self: self.prompt_no_style(), 'prompt_spaces': lambda self: sanitize_filename_part(self.prompt, replace_spaces=False), 'prompt_words': lambda self: self.prompt_words(), + 'batch_number': lambda self: NOTHING_AND_SKIP_PREVIOUS_TEXT if self.p.batch_size == 1 else self.p.batch_index + 1, + 'generation_number': lambda self: NOTHING_AND_SKIP_PREVIOUS_TEXT if self.p.n_iter == 1 and self.p.batch_size == 1 else self.p.iteration * self.p.batch_size + self.p.batch_index + 1, + 'hasprompt': lambda self, *args: self.hasprompt(*args), # accepts formats:[hasprompt..] + 'clip_skip': lambda self: opts.data["CLIP_stop_at_last_layers"], } default_time_format = '%Y%m%d%H%M%S' @@ -356,6 +361,22 @@ class FilenameGenerator: self.prompt = prompt self.image = image + def hasprompt(self, *args): + lower = self.prompt.lower() + if self.p is None or self.prompt is None: + return None + outres = "" + for arg in args: + if arg != "": + division = arg.split("|") + expected = division[0].lower() + default = division[1] if len(division) > 1 else "" + if lower.find(expected) >= 0: + outres = f'{outres}{expected}' + else: + outres = outres if default == "" else f'{outres}{default}' + return sanitize_filename_part(outres) + def prompt_no_style(self): if self.p is None or self.prompt is None: return None @@ -398,9 +419,8 @@ class FilenameGenerator: for m in re_pattern.finditer(x): text, pattern = m.groups() - res += text - if pattern is None: + res += text continue pattern_args = [] @@ -420,11 +440,13 @@ class FilenameGenerator: replacement = None errors.display(e, 'filename pattern') - if replacement is not None: - res += str(replacement) + if replacement == NOTHING_AND_SKIP_PREVIOUS_TEXT: + continue + elif replacement is not None: + res += text + str(replacement) continue - res += f'[{pattern}]' + res += f'{text}[{pattern}]' return res diff --git a/modules/img2img.py b/modules/img2img.py index 612d68b79..58b9449aa 100644 --- a/modules/img2img.py +++ b/modules/img2img.py @@ -64,7 +64,8 @@ def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args): debug(f'Processed: {len(images)} Memory: {memory_stats()} batch') -def img2img(id_task: str, mode: int, prompt: str, negative_prompt: str, prompt_styles, init_img, sketch, init_img_with_mask, inpaint_color_sketch, inpaint_color_sketch_orig, init_img_inpaint, init_mask_inpaint, steps: int, sampler_index: int, mask_blur: int, mask_alpha: float, inpainting_fill: int, restore_faces: bool, tiling: bool, n_iter: int, batch_size: int, cfg_scale: float, image_cfg_scale: float, denoising_strength: float, seed: int, subseed: int, subseed_strength: float, seed_resize_from_h: int, seed_resize_from_w: int, seed_enable_extras: bool, height: int, width: int, resize_mode: int, inpaint_full_res: bool, inpaint_full_res_padding: int, inpainting_mask_invert: int, img2img_batch_input_dir: str, img2img_batch_output_dir: str, img2img_batch_inpaint_mask_dir: str, override_settings_texts, *args): # pylint: disable=unused-argument +def img2img(id_task: str, mode: int, prompt: str, negative_prompt: str, prompt_styles, init_img, sketch, init_img_with_mask, inpaint_color_sketch, inpaint_color_sketch_orig, init_img_inpaint, init_mask_inpaint, steps: int, sampler_index: int, mask_blur: int, mask_alpha: float, inpainting_fill: int, restore_faces: bool, tiling: bool, n_iter: int, batch_size: int, cfg_scale: float, image_cfg_scale: float, denoising_strength: float, seed: int, subseed: int, subseed_strength: float, seed_resize_from_h: int, seed_resize_from_w: int, seed_enable_extras: bool, selected_scale_tab: int, height: int, width: int, scale_by: float, resize_mode: int, inpaint_full_res: bool, inpaint_full_res_padding: int, inpainting_mask_invert: int, img2img_batch_input_dir: str, img2img_batch_output_dir: str, img2img_batch_inpaint_mask_dir: str, override_settings_texts, *args): # pylint: disable=unused-argument + override_settings = create_override_settings_dict(override_settings_texts) is_batch = mode == 5 @@ -96,6 +97,11 @@ def img2img(id_task: str, mode: int, prompt: str, negative_prompt: str, prompt_s mask = None if image is not None: image = ImageOps.exif_transpose(image) + if selected_scale_tab == 1: + assert image, "Can't scale by because no image is selected" + width = int(image.width * scale_by) + height = int(image.height * scale_by) + assert 0. <= denoising_strength <= 1., 'can only work with strength in [0.0, 1.0]' p = StableDiffusionProcessingImg2Img( diff --git a/modules/processing.py b/modules/processing.py index 2ba6bd3ed..6c2877576 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -1,6 +1,7 @@ import json import math import os +import hashlib import random import logging from typing import Any, Dict, List @@ -100,7 +101,7 @@ class StableDiffusionProcessing: """ The first set of paramaters: sd_models -> do_not_reload_embeddings represent the minimum required to create a StableDiffusionProcessing """ - def __init__(self, sd_model=None, outpath_samples=None, outpath_grids=None, prompt: str = "", styles: List[str] = None, seed: int = -1, subseed: int = -1, subseed_strength: float = 0, seed_resize_from_h: int = -1, seed_resize_from_w: int = -1, seed_enable_extras: bool = True, sampler_name: str = None, batch_size: int = 1, n_iter: int = 1, steps: int = 20, cfg_scale: float = 6.0, width: int = 512, height: int = 512, restore_faces: bool = False, tiling: bool = False, do_not_save_samples: bool = False, do_not_save_grid: bool = False, extra_generation_params: Dict[Any, Any] = None, overlay_images: Any = None, negative_prompt: str = None, eta: float = None, do_not_reload_embeddings: bool = False, denoising_strength: float = 0, ddim_discretize: str = None, s_churn: float = 0.0, s_tmax: float = None, s_tmin: float = 0.0, s_noise: float = 1.0, override_settings: Dict[str, Any] = None, override_settings_restore_afterwards: bool = True, sampler_index: int = None, script_args: list = None): # pylint: disable=unused-argument + def __init__(self, sd_model=None, outpath_samples=None, outpath_grids=None, prompt: str = "", styles: List[str] = None, seed: int = -1, subseed: int = -1, subseed_strength: float = 0, seed_resize_from_h: int = -1, seed_resize_from_w: int = -1, seed_enable_extras: bool = True, sampler_name: str = None, batch_size: int = 1, n_iter: int = 1, steps: int = 50, cfg_scale: float = 7.0, width: int = 512, height: int = 512, restore_faces: bool = False, tiling: bool = False, do_not_save_samples: bool = False, do_not_save_grid: bool = False, extra_generation_params: Dict[Any, Any] = None, overlay_images: Any = None, negative_prompt: str = None, eta: float = None, do_not_reload_embeddings: bool = False, denoising_strength: float = 0, ddim_discretize: str = None, s_min_uncond: float = 0.0, s_churn: float = 0.0, s_tmax: float = None, s_tmin: float = 0.0, s_noise: float = 1.0, override_settings: Dict[str, Any] = None, override_settings_restore_afterwards: bool = True, sampler_index: int = None, script_args: list = None): # pylint: disable=unused-argument self.outpath_samples: str = outpath_samples self.outpath_grids: str = outpath_grids @@ -133,6 +134,7 @@ class StableDiffusionProcessing: 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.s_tmax = s_tmax or float('inf') # not representable as a standard ui option @@ -155,6 +157,7 @@ class StableDiffusionProcessing: self.all_subseeds = None self.clip_skip = opts.CLIP_stop_at_last_layers self.iteration = 0 + self.is_hr_pass = False @property def sd_model(self): @@ -465,6 +468,7 @@ def create_infotext(p: StableDiffusionProcessing, all_prompts, all_seeds, all_su "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, "ENSD": None if opts.eta_noise_seed_delta == 0 else opts.eta_noise_seed_delta, + "Init image hash": getattr(p, 'init_img_hash', None), "Token merging ratio": None if not (opts.token_merging or cmd_opts.token_merging) or opts.token_merging_hr_only else opts.token_merging_ratio, "Token merging ratio hr": None if not (opts.token_merging or cmd_opts.token_merging) else opts.token_merging_ratio_hr, "Token merging random": None if opts.token_merging_random is False else opts.token_merging_random, @@ -487,12 +491,12 @@ def process_images(p: StableDiffusionProcessing) -> Processed: stored_opts = {k: 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 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) - - if k == 'sd_model_checkpoint': - sd_models.reload_model_weights() - if k == 'sd_vae': sd_vae.reload_vae_weights() @@ -701,6 +705,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: p.scripts.postprocess_batch(p, x_samples_ddim, batch_number=n) for i, x_sample in enumerate(x_samples_ddim): + p.batch_index = i x_sample = 255. * np.moveaxis(x_sample.cpu().numpy(), 0, 2) x_sample = x_sample.astype(np.uint8) @@ -865,6 +870,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x)) if not self.enable_hr: return samples + self.is_hr_pass = True target_width = self.hr_upscale_to_x target_height = self.hr_upscale_to_y @@ -928,6 +934,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): sd_models.apply_token_merging(sd_model=self.sd_model, hr=True) log.debug('Applied token merging for high-res pass') samples = self.sampler.sample_img2img(self, samples, noise, conditioning, unconditional_conditioning, steps=self.hr_second_pass_steps or self.steps, image_conditioning=image_conditioning) + self.is_hr_pass = False return samples @@ -988,6 +995,10 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing): self.color_corrections = [] imgs = [] for img in self.init_images: + # Save init image + if 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) if crop_region is None and self.resize_mode != 3: image = images.resize_image(self.resize_mode, image, self.width, self.height) diff --git a/modules/realesrgan_model.py b/modules/realesrgan_model.py index c9b6cddf0..5b6109eac 100644 --- a/modules/realesrgan_model.py +++ b/modules/realesrgan_model.py @@ -7,6 +7,7 @@ from basicsr.utils.download_util import load_file_from_url from modules.upscaler import Upscaler, UpscalerData from modules.shared import cmd_opts, opts, device +from modules import modelloader import modules.errors as errors @@ -16,13 +17,19 @@ class UpscalerRealESRGAN(Upscaler): self.model_path = path super().__init__() try: - from basicsr.archs.rrdbnet_arch import RRDBNet - from realesrgan import RealESRGANer - from realesrgan.archs.srvgg_arch import SRVGGNetCompact + from basicsr.archs.rrdbnet_arch import RRDBNet # pylint: disable=unused-import + from realesrgan import RealESRGANer # pylint: disable=unused-import + from realesrgan.archs.srvgg_arch import SRVGGNetCompact # pylint: disable=unused-import self.enable = True self.scalers = [] scalers = self.load_models(path) + local_model_paths = self.find_models(ext_filter=[".pth"]) for scaler in scalers: + if scaler.local_data_path.startswith("http"): + filename = modelloader.friendly_name(scaler.local_data_path) + local = next(iter([local_model for local_model in local_model_paths if local_model.endswith(filename + '.pth')]), None) + if local: + scaler.local_data_path = local if scaler.name in opts.realesrgan_enabled_models: self.scalers.append(scaler) @@ -64,11 +71,11 @@ class UpscalerRealESRGAN(Upscaler): def load_model(self, path): try: info = next(iter([scaler for scaler in self.scalers if scaler.data_path == path]), None) - if info is None: print(f"Unable to find model info: {path}") return None - info.local_data_path = load_file_from_url(url=info.data_path, model_dir=self.model_path, progress=True) + if info.local_data_path.startswith("http"): + info.local_data_path = load_file_from_url(url=info.data_path, model_dir=self.model_path, progress=True) return info except Exception as e: errors.display(e, 'real-esrgan model list') diff --git a/modules/script_callbacks.py b/modules/script_callbacks.py index 98cb1d98b..10141281f 100644 --- a/modules/script_callbacks.py +++ b/modules/script_callbacks.py @@ -110,6 +110,7 @@ callback_map = dict( callbacks_infotext_pasted=[], callbacks_script_unloaded=[], callbacks_before_ui=[], + callbacks_on_reload=[], ) @@ -126,6 +127,14 @@ def app_started_callback(demo: Optional[Blocks], app: FastAPI): report_exception(e, c, 'app_started_callback') +def app_reload_callback(): + for c in callback_map['callbacks_on_reload']: + try: + c.callback() + except Exception as e: + report_exception(e, c, 'callbacks_on_reload') + + def model_loaded_callback(sd_model): for c in callback_map['callbacks_model_loaded']: try: @@ -279,6 +288,11 @@ def on_app_started(callback): add_callback(callback_map['callbacks_app_started'], callback) +def on_before_reload(callback): + """register a function to be called just before the server reloads.""" + add_callback(callback_map['callbacks_on_reload'], callback) + + def on_model_loaded(callback): """register a function to be called when the stable diffusion model is created; the model is passed as an argument; this function is also called when the script is reloaded. """ diff --git a/modules/sd_samplers_kdiffusion.py b/modules/sd_samplers_kdiffusion.py index a30d351fc..8b4bf0652 100644 --- a/modules/sd_samplers_kdiffusion.py +++ b/modules/sd_samplers_kdiffusion.py @@ -76,7 +76,7 @@ class CFGDenoiser(torch.nn.Module): return denoised - def forward(self, x, sigma, uncond, cond, cond_scale, image_cond): + def forward(self, x, sigma, uncond, cond, cond_scale, s_min_uncond, image_cond): if state.interrupted or state.skipped: raise sd_samplers_common.InterruptedException @@ -115,12 +115,21 @@ class CFGDenoiser(torch.nn.Module): sigma_in = denoiser_params.sigma tensor = denoiser_params.text_cond uncond = denoiser_params.text_uncond + skip_uncond = False - if tensor.shape[1] == uncond.shape[1]: - if not is_edit_model: - cond_in = torch.cat([tensor, uncond]) - else: + # alternating uncond allows for higher thresholds without the quality loss normally expected from raising it + if self.step % 2 and s_min_uncond > 0 and sigma[0] < s_min_uncond and not is_edit_model: + skip_uncond = True + x_in = x_in[:-batch_size] + sigma_in = sigma_in[:-batch_size] + + if tensor.shape[1] == uncond.shape[1] or skip_uncond: + if is_edit_model: cond_in = torch.cat([tensor, uncond, uncond]) + elif skip_uncond: + cond_in = tensor + else: + cond_in = torch.cat([tensor, uncond]) if shared.batch_cond_uncond: x_out = self.inner_model(x_in, sigma_in, cond=make_condition_dict([cond_in], image_cond_in)) @@ -144,7 +153,13 @@ class CFGDenoiser(torch.nn.Module): x_out[a:b] = self.inner_model(x_in[a:b], sigma_in[a:b], cond=make_condition_dict(c_crossattn, image_cond_in[a:b])) - x_out[-uncond.shape[0]:] = self.inner_model(x_in[-uncond.shape[0]:], sigma_in[-uncond.shape[0]:], cond=make_condition_dict([uncond], image_cond_in[-uncond.shape[0]:])) + if not skip_uncond: + x_out[-uncond.shape[0]:] = self.inner_model(x_in[-uncond.shape[0]:], sigma_in[-uncond.shape[0]:], cond=make_condition_dict([uncond], image_cond_in[-uncond.shape[0]:])) + + denoised_image_indexes = [x[0][0] for x in conds_list] + if skip_uncond: + fake_uncond = torch.cat([x_out[i:i+1] for i in denoised_image_indexes]) + x_out = torch.cat([x_out, fake_uncond]) # we skipped uncond denoising, so we put cond-denoised image to where the uncond-denoised image should be denoised_params = CFGDenoisedParams(x_out, state.sampling_step, state.sampling_steps, self.inner_model) cfg_denoised_callback(denoised_params) @@ -154,14 +169,16 @@ class CFGDenoiser(torch.nn.Module): if opts.live_preview_content == "Prompt": p_step = len(x_out) // batch_size - 1 p_step = p_step if p_step > 1 else 1 - sd_samplers_common.store_latent(x_out[0:-uncond.shape[0]:p_step]) + sd_samplers_common.store_latent(torch.cat([x_out[i:i+1] for i in denoised_image_indexes])) elif opts.live_preview_content == "Negative prompt": sd_samplers_common.store_latent(x_out[-uncond.shape[0]:]) - if not is_edit_model: - denoised = self.combine_denoised(x_out, conds_list, uncond, cond_scale) - else: + if is_edit_model: denoised = self.combine_denoised_for_edit_model(x_out, cond_scale) + elif skip_uncond: + denoised = self.combine_denoised(x_out, conds_list, uncond, 1.0) + else: + denoised = self.combine_denoised(x_out, conds_list, uncond, cond_scale) if self.mask is not None: denoised = self.init_latent * self.mask + self.nmask * denoised @@ -217,7 +234,7 @@ class KDiffusionSampler: self.eta = None self.config = None self.last_latent = None - + self.s_min_uncond = None self.conditioning_key = sd_model.model.conditioning_key def callback_state(self, d): @@ -250,6 +267,7 @@ class KDiffusionSampler: self.model_wrap_cfg.step = 0 self.model_wrap_cfg.image_cfg_scale = getattr(p, 'image_cfg_scale', None) self.eta = p.eta if p.eta is not None else opts.eta_ancestral + self.s_min_uncond = getattr(p, 's_min_uncond', 0.0) k_diffusion.sampling.torch = TorchHijack(self.sampler_noises if self.sampler_noises is not None else []) @@ -328,6 +346,7 @@ class KDiffusionSampler: 'image_cond': image_conditioning, 'uncond': unconditional_conditioning, 'cond_scale': p.cfg_scale, + 's_min_uncond': self.s_min_uncond } samples = self.launch_sampling(t_enc + 1, lambda: self.func(self.model_wrap_cfg, xi, extra_args=extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs)) @@ -361,7 +380,8 @@ class KDiffusionSampler: 'cond': conditioning, 'image_cond': image_conditioning, 'uncond': unconditional_conditioning, - 'cond_scale': p.cfg_scale + 'cond_scale': p.cfg_scale, + 's_min_uncond': self.s_min_uncond }, disable=False, callback=self.callback_state, **extra_params_kwargs)) return samples diff --git a/modules/textual_inversion/preprocess.py b/modules/textual_inversion/preprocess.py index de1ddb59b..2b0714df3 100644 --- a/modules/textual_inversion/preprocess.py +++ b/modules/textual_inversion/preprocess.py @@ -1,17 +1,12 @@ import os -from PIL import Image, ImageOps import math -import platform -import sys import tqdm -import time - +from PIL import Image, ImageOps from modules import paths, shared, images, deepbooru -from modules.shared import opts, cmd_opts from modules.textual_inversion import autocrop -def preprocess(id_task, process_src, process_dst, process_width, process_height, preprocess_txt_action, process_flip, process_split, process_caption, process_caption_deepbooru=False, split_threshold=0.5, overlap_ratio=0.2, process_focal_crop=False, process_focal_crop_face_weight=0.9, process_focal_crop_entropy_weight=0.3, process_focal_crop_edges_weight=0.5, process_focal_crop_debug=False, process_multicrop=None, process_multicrop_mindim=None, process_multicrop_maxdim=None, process_multicrop_minarea=None, process_multicrop_maxarea=None, process_multicrop_objective=None, process_multicrop_threshold=None): +def preprocess(id_task, process_src, process_dst, process_width, process_height, preprocess_txt_action, process_keep_original_size, process_flip, process_split, process_caption, process_caption_deepbooru=False, split_threshold=0.5, overlap_ratio=0.2, process_focal_crop=False, process_focal_crop_face_weight=0.9, process_focal_crop_entropy_weight=0.3, process_focal_crop_edges_weight=0.5, process_focal_crop_debug=False, process_multicrop=None, process_multicrop_mindim=None, process_multicrop_maxdim=None, process_multicrop_minarea=None, process_multicrop_maxarea=None, process_multicrop_objective=None, process_multicrop_threshold=None): # pylint: disable=unused-argument try: if process_caption: shared.interrogator.load() @@ -19,7 +14,7 @@ def preprocess(id_task, process_src, process_dst, process_width, process_height, if process_caption_deepbooru: deepbooru.model.start() - preprocess_work(process_src, process_dst, process_width, process_height, preprocess_txt_action, process_flip, process_split, process_caption, process_caption_deepbooru, split_threshold, overlap_ratio, process_focal_crop, process_focal_crop_face_weight, process_focal_crop_entropy_weight, process_focal_crop_edges_weight, process_focal_crop_debug, process_multicrop, process_multicrop_mindim, process_multicrop_maxdim, process_multicrop_minarea, process_multicrop_maxarea, process_multicrop_objective, process_multicrop_threshold) + preprocess_work(process_src, process_dst, process_width, process_height, preprocess_txt_action, process_keep_original_size, process_flip, process_split, process_caption, process_caption_deepbooru, split_threshold, overlap_ratio, process_focal_crop, process_focal_crop_face_weight, process_focal_crop_entropy_weight, process_focal_crop_edges_weight, process_focal_crop_debug, process_multicrop, process_multicrop_mindim, process_multicrop_maxdim, process_multicrop_minarea, process_multicrop_maxarea, process_multicrop_objective, process_multicrop_threshold) finally: @@ -129,9 +124,10 @@ def multicrop_pic(image: Image, mindim, maxdim, minarea, maxarea, objective, thr default=None ) return wh and center_crop(image, *wh) - -def preprocess_work(process_src, process_dst, process_width, process_height, preprocess_txt_action, process_flip, process_split, process_caption, process_caption_deepbooru=False, split_threshold=0.5, overlap_ratio=0.2, process_focal_crop=False, process_focal_crop_face_weight=0.9, process_focal_crop_entropy_weight=0.3, process_focal_crop_edges_weight=0.5, process_focal_crop_debug=False, process_multicrop=None, process_multicrop_mindim=None, process_multicrop_maxdim=None, process_multicrop_minarea=None, process_multicrop_maxarea=None, process_multicrop_objective=None, process_multicrop_threshold=None): + +def preprocess_work(process_src, process_dst, process_width, process_height, preprocess_txt_action, process_keep_original_size, process_flip, process_split, process_caption, process_caption_deepbooru=False, split_threshold=0.5, overlap_ratio=0.2, process_focal_crop=False, process_focal_crop_face_weight=0.9, process_focal_crop_entropy_weight=0.3, process_focal_crop_edges_weight=0.5, process_focal_crop_debug=False, process_multicrop=None, process_multicrop_mindim=None, process_multicrop_maxdim=None, process_multicrop_minarea=None, process_multicrop_maxarea=None, process_multicrop_objective=None, process_multicrop_threshold=None): + width = process_width height = process_height src = os.path.abspath(process_src) @@ -225,6 +221,10 @@ def preprocess_work(process_src, process_dst, process_width, process_height, pre print(f"skipped {img.width}x{img.height} image {filename} (can't find suitable size within error threshold)") process_default_resize = False + if process_keep_original_size: + save_pic(img, index, params, existing_caption=existing_caption) + process_default_resize = False + if process_default_resize: img = images.resize_image(1, img, width, height) save_pic(img, index, params, existing_caption=existing_caption)