From 99b05addb1c98169d78957f13efef308aef0af94 Mon Sep 17 00:00:00 2001 From: Bruno Seoane Date: Sat, 5 Nov 2022 18:46:47 -0300 Subject: Fix options endpoint not showing the full list of options --- modules/api/models.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'modules/api/models.py') diff --git a/modules/api/models.py b/modules/api/models.py index f89da1ff..0ea62155 100644 --- a/modules/api/models.py +++ b/modules/api/models.py @@ -168,9 +168,9 @@ class ProgressResponse(BaseModel): current_image: str = Field(default=None, title="Current image", description="The current image in base64 format. opts.show_progress_every_n_steps is required for this to work.") fields = {} -for key, value in opts.data.items(): - metadata = opts.data_labels.get(key) - optType = opts.typemap.get(type(value), type(value)) +for key, metadata in opts.data_labels.items(): + value = opts.data.get(key) + optType = opts.typemap.get(type(metadata.default), type(value)) if (metadata is not None): fields.update({key: (Optional[optType], Field( -- cgit v1.2.3 From 67c8e11be74180be19341aebbd6a246c37a79fbb Mon Sep 17 00:00:00 2001 From: snowmeow2 Date: Mon, 7 Nov 2022 02:32:06 +0800 Subject: Adding DeepDanbooru to the interrogation API --- modules/api/api.py | 16 ++++++++++++++-- modules/api/models.py | 1 + 2 files changed, 15 insertions(+), 2 deletions(-) (limited to 'modules/api/models.py') diff --git a/modules/api/api.py b/modules/api/api.py index 688469ad..596a6616 100644 --- a/modules/api/api.py +++ b/modules/api/api.py @@ -15,6 +15,9 @@ from modules.sd_models import checkpoints_list from modules.realesrgan_model import get_realesrgan_models from typing import List +if shared.cmd_opts.deepdanbooru: + from modules.deepbooru import get_deepbooru_tags + def upscaler_to_index(name: str): try: return [x.name.lower() for x in shared.sd_upscalers].index(name.lower()) @@ -220,11 +223,20 @@ class Api: if image_b64 is None: raise HTTPException(status_code=404, detail="Image not found") - img = self.__base64_to_image(image_b64) + img = decode_base64_to_image(image_b64) + img = img.convert('RGB') # Override object param with self.queue_lock: - processed = shared.interrogator.interrogate(img) + if interrogatereq.model == "clip": + processed = shared.interrogator.interrogate(img) + elif interrogatereq.model == "deepdanbooru": + if shared.cmd_opts.deepdanbooru: + processed = get_deepbooru_tags(img) + else: + raise HTTPException(status_code=404, detail="Model not found. Add --deepdanbooru when launching for using the model.") + else: + raise HTTPException(status_code=404, detail="Model not found") return InterrogateResponse(caption=processed) diff --git a/modules/api/models.py b/modules/api/models.py index 34dbfa16..f9cd929e 100644 --- a/modules/api/models.py +++ b/modules/api/models.py @@ -170,6 +170,7 @@ class ProgressResponse(BaseModel): class InterrogateRequest(BaseModel): image: str = Field(default="", title="Image", description="Image to work on, must be a Base64 string containing the image's data.") + model: str = Field(default="clip", title="Model", description="The interrogate model used.") class InterrogateResponse(BaseModel): caption: str = Field(default=None, title="Caption", description="The generated caption for the image.") -- cgit v1.2.3 From c0355caefe3d82e304e6d832699d581fc8f9fbf9 Mon Sep 17 00:00:00 2001 From: Jim Hays Date: Wed, 14 Dec 2022 21:01:32 -0500 Subject: Fix various typos --- README.md | 4 ++-- javascript/contextMenus.js | 24 ++++++++++++------------ javascript/progressbar.js | 12 ++++++------ javascript/ui.js | 2 +- modules/api/api.py | 18 +++++++++--------- modules/api/models.py | 2 +- modules/images.py | 4 ++-- modules/processing.py | 14 +++++++------- modules/safe.py | 4 ++-- modules/scripts.py | 4 ++-- modules/sd_hijack_inpainting.py | 6 +++--- modules/sd_hijack_unet.py | 2 +- modules/textual_inversion/dataset.py | 10 +++++----- modules/textual_inversion/textual_inversion.py | 16 ++++++++-------- scripts/prompt_matrix.py | 10 +++++----- webui.py | 4 ++-- 16 files changed, 68 insertions(+), 68 deletions(-) (limited to 'modules/api/models.py') diff --git a/README.md b/README.md index 55990581..556000fb 100644 --- a/README.md +++ b/README.md @@ -82,8 +82,8 @@ Check the [custom scripts](https://github.com/AUTOMATIC1111/stable-diffusion-web - Use VAEs - Estimated completion time in progress bar - API -- Support for dedicated [inpainting model](https://github.com/runwayml/stable-diffusion#inpainting-with-stable-diffusion) by RunwayML. -- via extension: [Aesthetic Gradients](https://github.com/AUTOMATIC1111/stable-diffusion-webui-aesthetic-gradients), a way to generate images with a specific aesthetic by using clip images embds (implementation of [https://github.com/vicgalle/stable-diffusion-aesthetic-gradients](https://github.com/vicgalle/stable-diffusion-aesthetic-gradients)) +- Support for dedicated [inpainting model](https://github.com/runwayml/stable-diffusion#inpainting-with-stable-diffusion) by RunwayML. +- via extension: [Aesthetic Gradients](https://github.com/AUTOMATIC1111/stable-diffusion-webui-aesthetic-gradients), a way to generate images with a specific aesthetic by using clip images embeds (implementation of [https://github.com/vicgalle/stable-diffusion-aesthetic-gradients](https://github.com/vicgalle/stable-diffusion-aesthetic-gradients)) - [Stable Diffusion 2.0](https://github.com/Stability-AI/stablediffusion) support - see [wiki](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#stable-diffusion-20) for instructions ## Installation and Running diff --git a/javascript/contextMenus.js b/javascript/contextMenus.js index fe67c42e..11bcce1b 100644 --- a/javascript/contextMenus.js +++ b/javascript/contextMenus.js @@ -9,7 +9,7 @@ contextMenuInit = function(){ function showContextMenu(event,element,menuEntries){ let posx = event.clientX + document.body.scrollLeft + document.documentElement.scrollLeft; - let posy = event.clientY + document.body.scrollTop + document.documentElement.scrollTop; + let posy = event.clientY + document.body.scrollTop + document.documentElement.scrollTop; let oldMenu = gradioApp().querySelector('#context-menu') if(oldMenu){ @@ -61,15 +61,15 @@ contextMenuInit = function(){ } - function appendContextMenuOption(targetEmementSelector,entryName,entryFunction){ - - currentItems = menuSpecs.get(targetEmementSelector) - + function appendContextMenuOption(targetElementSelector,entryName,entryFunction){ + + currentItems = menuSpecs.get(targetElementSelector) + if(!currentItems){ currentItems = [] - menuSpecs.set(targetEmementSelector,currentItems); + menuSpecs.set(targetElementSelector,currentItems); } - let newItem = {'id':targetEmementSelector+'_'+uid(), + let newItem = {'id':targetElementSelector+'_'+uid(), 'name':entryName, 'func':entryFunction, 'isNew':true} @@ -97,7 +97,7 @@ contextMenuInit = function(){ if(source.id && source.id.indexOf('check_progress')>-1){ return } - + let oldMenu = gradioApp().querySelector('#context-menu') if(oldMenu){ oldMenu.remove() @@ -117,7 +117,7 @@ contextMenuInit = function(){ }) }); eventListenerApplied=true - + } return [appendContextMenuOption, removeContextMenuOption, addContextMenuEventListener] @@ -152,8 +152,8 @@ addContextMenuEventListener = initResponse[2]; generateOnRepeat('#img2img_generate','#img2img_interrupt'); }) - let cancelGenerateForever = function(){ - clearInterval(window.generateOnRepeatInterval) + let cancelGenerateForever = function(){ + clearInterval(window.generateOnRepeatInterval) } appendContextMenuOption('#txt2img_interrupt','Cancel generate forever',cancelGenerateForever) @@ -162,7 +162,7 @@ addContextMenuEventListener = initResponse[2]; appendContextMenuOption('#img2img_generate', 'Cancel generate forever',cancelGenerateForever) appendContextMenuOption('#roll','Roll three', - function(){ + function(){ let rollbutton = get_uiCurrentTabContent().querySelector('#roll'); setTimeout(function(){rollbutton.click()},100) setTimeout(function(){rollbutton.click()},200) diff --git a/javascript/progressbar.js b/javascript/progressbar.js index d58737c4..d6323ed9 100644 --- a/javascript/progressbar.js +++ b/javascript/progressbar.js @@ -3,7 +3,7 @@ global_progressbars = {} galleries = {} galleryObservers = {} -// this tracks laumnches of window.setTimeout for progressbar to prevent starting a new timeout when the previous is still running +// this tracks launches of window.setTimeout for progressbar to prevent starting a new timeout when the previous is still running timeoutIds = {} function check_progressbar(id_part, id_progressbar, id_progressbar_span, id_skip, id_interrupt, id_preview, id_gallery){ @@ -20,21 +20,21 @@ function check_progressbar(id_part, id_progressbar, id_progressbar_span, id_skip var skip = id_skip ? gradioApp().getElementById(id_skip) : null var interrupt = gradioApp().getElementById(id_interrupt) - + if(opts.show_progress_in_title && progressbar && progressbar.offsetParent){ if(progressbar.innerText){ let newtitle = '[' + progressbar.innerText.trim() + '] Stable Diffusion'; if(document.title != newtitle){ - document.title = newtitle; + document.title = newtitle; } }else{ let newtitle = 'Stable Diffusion' if(document.title != newtitle){ - document.title = newtitle; + document.title = newtitle; } } } - + if(progressbar!= null && progressbar != global_progressbars[id_progressbar]){ global_progressbars[id_progressbar] = progressbar @@ -63,7 +63,7 @@ function check_progressbar(id_part, id_progressbar, id_progressbar_span, id_skip skip.style.display = "none" } interrupt.style.display = "none" - + //disconnect observer once generation finished, so user can close selected image if they want if (galleryObservers[id_gallery]) { galleryObservers[id_gallery].disconnect(); diff --git a/javascript/ui.js b/javascript/ui.js index 2cb280e5..587dd782 100644 --- a/javascript/ui.js +++ b/javascript/ui.js @@ -100,7 +100,7 @@ function create_submit_args(args){ // As it is currently, txt2img and img2img send back the previous output args (txt2img_gallery, generation_info, html_info) whenever you generate a new image. // This can lead to uploading a huge gallery of previously generated images, which leads to an unnecessary delay between submitting and beginning to generate. - // I don't know why gradio is seding outputs along with inputs, but we can prevent sending the image gallery here, which seems to be an issue for some. + // I don't know why gradio is sending outputs along with inputs, but we can prevent sending the image gallery here, which seems to be an issue for some. // If gradio at some point stops sending outputs, this may break something if(Array.isArray(res[res.length - 3])){ res[res.length - 3] = null diff --git a/modules/api/api.py b/modules/api/api.py index 89935a70..33845045 100644 --- a/modules/api/api.py +++ b/modules/api/api.py @@ -67,10 +67,10 @@ def encode_pil_to_base64(image): class Api: def __init__(self, app: FastAPI, queue_lock: Lock): if shared.cmd_opts.api_auth: - self.credenticals = dict() + self.credentials = dict() for auth in shared.cmd_opts.api_auth.split(","): user, password = auth.split(":") - self.credenticals[user] = password + self.credentials[user] = password self.router = APIRouter() self.app = app @@ -93,7 +93,7 @@ class Api: self.add_api_route("/sdapi/v1/hypernetworks", self.get_hypernetworks, methods=["GET"], response_model=List[HypernetworkItem]) self.add_api_route("/sdapi/v1/face-restorers", self.get_face_restorers, methods=["GET"], response_model=List[FaceRestorerItem]) self.add_api_route("/sdapi/v1/realesrgan-models", self.get_realesrgan_models, methods=["GET"], response_model=List[RealesrganItem]) - self.add_api_route("/sdapi/v1/prompt-styles", self.get_promp_styles, methods=["GET"], response_model=List[PromptStyleItem]) + self.add_api_route("/sdapi/v1/prompt-styles", self.get_prompt_styles, methods=["GET"], response_model=List[PromptStyleItem]) self.add_api_route("/sdapi/v1/artist-categories", self.get_artists_categories, methods=["GET"], response_model=List[str]) self.add_api_route("/sdapi/v1/artists", self.get_artists, methods=["GET"], response_model=List[ArtistItem]) @@ -102,9 +102,9 @@ class Api: return self.app.add_api_route(path, endpoint, dependencies=[Depends(self.auth)], **kwargs) return self.app.add_api_route(path, endpoint, **kwargs) - def auth(self, credenticals: HTTPBasicCredentials = Depends(HTTPBasic())): - if credenticals.username in self.credenticals: - if compare_digest(credenticals.password, self.credenticals[credenticals.username]): + def auth(self, credentials: HTTPBasicCredentials = Depends(HTTPBasic())): + if credentials.username in self.credentials: + if compare_digest(credentials.password, self.credentials[credentials.username]): return True raise HTTPException(status_code=401, detail="Incorrect username or password", headers={"WWW-Authenticate": "Basic"}) @@ -239,7 +239,7 @@ class Api: def interrogateapi(self, interrogatereq: InterrogateRequest): image_b64 = interrogatereq.image if image_b64 is None: - raise HTTPException(status_code=404, detail="Image not found") + raise HTTPException(status_code=404, detail="Image not found") img = decode_base64_to_image(image_b64) img = img.convert('RGB') @@ -252,7 +252,7 @@ class Api: processed = deepbooru.model.tag(img) else: raise HTTPException(status_code=404, detail="Model not found") - + return InterrogateResponse(caption=processed) def interruptapi(self): @@ -308,7 +308,7 @@ class Api: def get_realesrgan_models(self): return [{"name":x.name,"path":x.data_path, "scale":x.scale} for x in get_realesrgan_models(None)] - def get_promp_styles(self): + def get_prompt_styles(self): styleList = [] for k in shared.prompt_styles.styles: style = shared.prompt_styles.styles[k] diff --git a/modules/api/models.py b/modules/api/models.py index f77951fc..a22bc6b3 100644 --- a/modules/api/models.py +++ b/modules/api/models.py @@ -128,7 +128,7 @@ class ExtrasBaseRequest(BaseModel): upscaling_resize: float = Field(default=2, title="Upscaling Factor", ge=1, le=4, description="By how much to upscale the image, only used when resize_mode=0.") upscaling_resize_w: int = Field(default=512, title="Target Width", ge=1, description="Target width for the upscaler to hit. Only used when resize_mode=1.") upscaling_resize_h: int = Field(default=512, title="Target Height", ge=1, description="Target height for the upscaler to hit. Only used when resize_mode=1.") - upscaling_crop: bool = Field(default=True, title="Crop to fit", description="Should the upscaler crop the image to fit in the choosen size?") + upscaling_crop: bool = Field(default=True, title="Crop to fit", description="Should the upscaler crop the image to fit in the chosen size?") upscaler_1: str = Field(default="None", title="Main upscaler", description=f"The name of the main upscaler to use, it has to be one of this list: {' , '.join([x.name for x in sd_upscalers])}") upscaler_2: str = Field(default="None", title="Secondary upscaler", description=f"The name of the secondary upscaler to use, it has to be one of this list: {' , '.join([x.name for x in sd_upscalers])}") extras_upscaler_2_visibility: float = Field(default=0, title="Secondary upscaler visibility", ge=0, le=1, allow_inf_nan=False, description="Sets the visibility of secondary upscaler, values should be between 0 and 1.") diff --git a/modules/images.py b/modules/images.py index 8146f580..93a14289 100644 --- a/modules/images.py +++ b/modules/images.py @@ -429,7 +429,7 @@ def save_image(image, path, basename, seed=None, prompt=None, extension='png', i The directory to save the image. Note, the option `save_to_dirs` will make the image to be saved into a sub directory. basename (`str`): The base filename which will be applied to `filename pattern`. - seed, prompt, short_filename, + seed, prompt, short_filename, extension (`str`): Image file extension, default is `png`. pngsectionname (`str`): @@ -590,7 +590,7 @@ def read_info_from_image(image): Negative prompt: {json_info["uc"]} Steps: {json_info["steps"]}, Sampler: {sampler}, CFG scale: {json_info["scale"]}, Seed: {json_info["seed"]}, Size: {image.width}x{image.height}, Clip skip: 2, ENSD: 31337""" except Exception: - print(f"Error parsing NovelAI iamge generation parameters:", file=sys.stderr) + print(f"Error parsing NovelAI image generation parameters:", file=sys.stderr) print(traceback.format_exc(), file=sys.stderr) return geninfo, items diff --git a/modules/processing.py b/modules/processing.py index 24c537d1..fe7f4faf 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -147,11 +147,11 @@ class StableDiffusionProcessing(): # The "masked-image" in this case will just be all zeros since the entire image is masked. image_conditioning = torch.zeros(x.shape[0], 3, height, width, device=x.device) - image_conditioning = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(image_conditioning)) + image_conditioning = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(image_conditioning)) # Add the fake full 1s mask to the first dimension. image_conditioning = torch.nn.functional.pad(image_conditioning, (0, 0, 0, 0, 1, 0), value=1.0) - image_conditioning = image_conditioning.to(x.dtype) + image_conditioning = image_conditioning.to(x.dtype) return image_conditioning @@ -199,7 +199,7 @@ class StableDiffusionProcessing(): source_image * (1.0 - conditioning_mask), getattr(self, "inpainting_mask_weight", shared.opts.inpainting_mask_weight) ) - + # Encode the new masked image using first stage of network. conditioning_image = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(conditioning_image)) @@ -537,7 +537,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: for n in range(p.n_iter): if state.skipped: state.skipped = False - + if state.interrupted: break @@ -612,7 +612,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: image.info["parameters"] = text output_images.append(image) - del x_samples_ddim + del x_samples_ddim devices.torch_gc() @@ -704,7 +704,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): samples = samples[:, :, self.truncate_y//2:samples.shape[2]-self.truncate_y//2, self.truncate_x//2:samples.shape[3]-self.truncate_x//2] - """saves image before applying hires fix, if enabled in options; takes as an arguyment either an image or batch with latent space images""" + """saves image before applying hires fix, if enabled in options; takes as an argument either an image or batch with latent space images""" def save_intermediate(image, index): if not opts.save or self.do_not_save_samples or not opts.save_images_before_highres_fix: return @@ -720,7 +720,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): samples = torch.nn.functional.interpolate(samples, size=(self.height // opt_f, self.width // opt_f), mode="bilinear") - # Avoid making the inpainting conditioning unless necessary as + # Avoid making the inpainting conditioning unless necessary as # this does need some extra compute to decode / encode the image again. if getattr(self, "inpainting_mask_weight", shared.opts.inpainting_mask_weight) < 1.0: image_conditioning = self.img2img_image_conditioning(decode_first_stage(self.sd_model, samples), samples) diff --git a/modules/safe.py b/modules/safe.py index 10460ad0..20e9d2fa 100644 --- a/modules/safe.py +++ b/modules/safe.py @@ -80,7 +80,7 @@ def check_pt(filename, extra_handler): # new pytorch format is a zip file with zipfile.ZipFile(filename) as z: check_zip_filenames(filename, z.namelist()) - + # find filename of data.pkl in zip file: '/data.pkl' data_pkl_filenames = [f for f in z.namelist() if data_pkl_re.match(f)] if len(data_pkl_filenames) == 0: @@ -108,7 +108,7 @@ def load(filename, *args, **kwargs): def load_with_extra(filename, extra_handler=None, *args, **kwargs): """ - this functon is intended to be used by extensions that want to load models with + this function is intended to be used by extensions that want to load models with some extra classes in them that the usual unpickler would find suspicious. Use the extra_handler argument to specify a function that takes module and field name as text, diff --git a/modules/scripts.py b/modules/scripts.py index 23ca195d..722f8685 100644 --- a/modules/scripts.py +++ b/modules/scripts.py @@ -36,7 +36,7 @@ class Script: def ui(self, is_img2img): """this function should create gradio UI elements. See https://gradio.app/docs/#components The return value should be an array of all components that are used in processing. - Values of those returned componenbts will be passed to run() and process() functions. + Values of those returned components will be passed to run() and process() functions. """ pass @@ -47,7 +47,7 @@ class Script: This function should return: - False if the script should not be shown in UI at all - - True if the script should be shown in UI if it's scelected in the scripts drowpdown + - True if the script should be shown in UI if it's selected in the scripts dropdown - script.AlwaysVisible if the script should be shown in UI at all times """ diff --git a/modules/sd_hijack_inpainting.py b/modules/sd_hijack_inpainting.py index 938f9a58..d72f83fd 100644 --- a/modules/sd_hijack_inpainting.py +++ b/modules/sd_hijack_inpainting.py @@ -209,7 +209,7 @@ def p_sample_plms(self, x, c, t, index, repeat_noise=False, use_original_steps=F else: x_in = torch.cat([x] * 2) t_in = torch.cat([t] * 2) - + if isinstance(c, dict): assert isinstance(unconditional_conditioning, dict) c_in = dict() @@ -278,7 +278,7 @@ def p_sample_plms(self, x, c, t, index, repeat_noise=False, use_original_steps=F x_prev, pred_x0 = get_x_prev_and_pred_x0(e_t_prime, index) return x_prev, pred_x0, e_t - + # ================================================================================================= # Monkey patch LatentInpaintDiffusion to load the checkpoint with a proper config. # Adapted from: @@ -326,7 +326,7 @@ def do_inpainting_hijack(): # most of this stuff seems to no longer be needed because it is already included into SD2.0 # LatentInpaintDiffusion remains because SD2.0's LatentInpaintDiffusion can't be loaded without specifying a checkpoint # p_sample_plms is needed because PLMS can't work with dicts as conditionings - # this file should be cleaned up later if weverything tuens out to work fine + # this file should be cleaned up later if everything turns out to work fine # ldm.models.diffusion.ddpm.get_unconditional_conditioning = get_unconditional_conditioning ldm.models.diffusion.ddpm.LatentInpaintDiffusion = LatentInpaintDiffusion diff --git a/modules/sd_hijack_unet.py b/modules/sd_hijack_unet.py index 1b9d7757..18daf8c1 100644 --- a/modules/sd_hijack_unet.py +++ b/modules/sd_hijack_unet.py @@ -4,7 +4,7 @@ import torch class TorchHijackForUnet: """ This is torch, but with cat that resizes tensors to appropriate dimensions if they do not match; - this makes it possible to create pictures with dimensions that are muliples of 8 rather than 64 + this makes it possible to create pictures with dimensions that are multiples of 8 rather than 64 """ def __getattr__(self, item): diff --git a/modules/textual_inversion/dataset.py b/modules/textual_inversion/dataset.py index 2dc64c3c..88d68c76 100644 --- a/modules/textual_inversion/dataset.py +++ b/modules/textual_inversion/dataset.py @@ -28,9 +28,9 @@ class DatasetEntry: class PersonalizedBase(Dataset): - def __init__(self, data_root, width, height, repeats, flip_p=0.5, placeholder_token="*", model=None, cond_model=None, device=None, template_file=None, include_cond=False, batch_size=1, gradient_step=1, shuffle_tags=False, tag_drop_out=0, latent_sampling_method='once'): + def __init__(self, data_root, width, height, repeats, flip_p=0.5, placeholder_token="*", model=None, cond_model=None, device=None, template_file=None, include_cond=False, batch_size=1, gradient_step=1, shuffle_tags=False, tag_drop_out=0, latent_sampling_method='once'): re_word = re.compile(shared.opts.dataset_filename_word_regex) if len(shared.opts.dataset_filename_word_regex) > 0 else None - + self.placeholder_token = placeholder_token self.width = width @@ -50,14 +50,14 @@ class PersonalizedBase(Dataset): self.image_paths = [os.path.join(data_root, file_path) for file_path in os.listdir(data_root)] - + self.shuffle_tags = shuffle_tags self.tag_drop_out = tag_drop_out print("Preparing dataset...") for path in tqdm.tqdm(self.image_paths): if shared.state.interrupted: - raise Exception("inturrupted") + raise Exception("interrupted") try: image = Image.open(path).convert('RGB').resize((self.width, self.height), PIL.Image.BICUBIC) except Exception: @@ -144,7 +144,7 @@ class PersonalizedDataLoader(DataLoader): self.collate_fn = collate_wrapper_random else: self.collate_fn = collate_wrapper - + class BatchLoader: def __init__(self, data): diff --git a/modules/textual_inversion/textual_inversion.py b/modules/textual_inversion/textual_inversion.py index e28c357a..daf3997b 100644 --- a/modules/textual_inversion/textual_inversion.py +++ b/modules/textual_inversion/textual_inversion.py @@ -133,7 +133,7 @@ class EmbeddingDatabase: process_file(fullfn, fn) except Exception: - print(f"Error loading emedding {fn}:", file=sys.stderr) + print(f"Error loading embedding {fn}:", file=sys.stderr) print(traceback.format_exc(), file=sys.stderr) continue @@ -194,7 +194,7 @@ def write_loss(log_directory, filename, step, epoch_len, values): csv_writer.writeheader() epoch = (step - 1) // epoch_len - epoch_step = (step - 1) % epoch_len + epoch_step = (step - 1) % epoch_len csv_writer.writerow({ "step": step, @@ -270,9 +270,9 @@ def train_embedding(embedding_name, learn_rate, batch_size, gradient_step, data_ # dataset loading may take a while, so input validations and early returns should be done before this shared.state.textinfo = f"Preparing dataset from {html.escape(data_root)}..." old_parallel_processing_allowed = shared.parallel_processing_allowed - + pin_memory = shared.opts.pin_memory - + ds = modules.textual_inversion.dataset.PersonalizedBase(data_root=data_root, width=training_width, height=training_height, repeats=shared.opts.training_image_repeats_per_epoch, placeholder_token=embedding_name, model=shared.sd_model, cond_model=shared.sd_model.cond_stage_model, device=devices.device, template_file=template_file, batch_size=batch_size, gradient_step=gradient_step, shuffle_tags=shuffle_tags, tag_drop_out=tag_drop_out, latent_sampling_method=latent_sampling_method) latent_sampling_method = ds.latent_sampling_method @@ -295,12 +295,12 @@ def train_embedding(embedding_name, learn_rate, batch_size, gradient_step, data_ loss_step = 0 _loss_step = 0 #internal - + last_saved_file = "" last_saved_image = "" forced_filename = "" embedding_yet_to_be_embedded = False - + pbar = tqdm.tqdm(total=steps - initial_step) try: for i in range((steps-initial_step) * gradient_step): @@ -327,10 +327,10 @@ def train_embedding(embedding_name, learn_rate, batch_size, gradient_step, data_ c = shared.sd_model.cond_stage_model(batch.cond_text) loss = shared.sd_model(x, c)[0] / gradient_step del x - + _loss_step += loss.item() scaler.scale(loss).backward() - + # go back until we reach gradient accumulation steps if (j + 1) % gradient_step != 0: continue diff --git a/scripts/prompt_matrix.py b/scripts/prompt_matrix.py index c53ca28c..4c79eaef 100644 --- a/scripts/prompt_matrix.py +++ b/scripts/prompt_matrix.py @@ -18,7 +18,7 @@ def draw_xy_grid(xs, ys, x_label, y_label, cell): ver_texts = [[images.GridAnnotation(y_label(y))] for y in ys] hor_texts = [[images.GridAnnotation(x_label(x))] for x in xs] - first_pocessed = None + first_processed = None state.job_count = len(xs) * len(ys) @@ -27,17 +27,17 @@ def draw_xy_grid(xs, ys, x_label, y_label, cell): state.job = f"{ix + iy * len(xs) + 1} out of {len(xs) * len(ys)}" processed = cell(x, y) - if first_pocessed is None: - first_pocessed = processed + if first_processed is None: + first_processed = processed res.append(processed.images[0]) grid = images.image_grid(res, rows=len(ys)) grid = images.draw_grid_annotations(grid, res[0].width, res[0].height, hor_texts, ver_texts) - first_pocessed.images = [grid] + first_processed.images = [grid] - return first_pocessed + return first_processed class Script(scripts.Script): diff --git a/webui.py b/webui.py index c2d0c6be..4b32e77d 100644 --- a/webui.py +++ b/webui.py @@ -153,8 +153,8 @@ def webui(): # gradio uses a very open CORS policy via app.user_middleware, which makes it possible for # an attacker to trick the user into opening a malicious HTML page, which makes a request to the - # running web ui and do whatever the attcker wants, including installing an extension and - # runnnig its code. We disable this here. Suggested by RyotaK. + # running web ui and do whatever the attacker wants, including installing an extension and + # running its code. We disable this here. Suggested by RyotaK. app.user_middleware = [x for x in app.user_middleware if x.cls.__name__ != 'CORSMiddleware'] setup_cors(app) -- cgit v1.2.3 From 5f1dfbbc959855fd90ba80c0c76301d2063772fa Mon Sep 17 00:00:00 2001 From: Vladimir Mandic Date: Sat, 24 Dec 2022 18:02:22 -0500 Subject: implement train api --- modules/api/api.py | 94 ++++++++++++++++++++++++++++++++++- modules/api/models.py | 9 ++++ modules/hypernetworks/hypernetwork.py | 26 ++++++++++ modules/hypernetworks/ui.py | 31 ++---------- 4 files changed, 132 insertions(+), 28 deletions(-) (limited to 'modules/api/models.py') diff --git a/modules/api/api.py b/modules/api/api.py index b43dd16b..1ceba75d 100644 --- a/modules/api/api.py +++ b/modules/api/api.py @@ -10,13 +10,17 @@ from fastapi.security import HTTPBasic, HTTPBasicCredentials from secrets import compare_digest import modules.shared as shared -from modules import sd_samplers, deepbooru +from modules import sd_samplers, deepbooru, sd_hijack from modules.api.models import * from modules.processing import StableDiffusionProcessingTxt2Img, StableDiffusionProcessingImg2Img, process_images from modules.extras import run_extras, run_pnginfo +from modules.textual_inversion.textual_inversion import create_embedding, train_embedding +from modules.textual_inversion.preprocess import preprocess +from modules.hypernetworks.hypernetwork import create_hypernetwork, train_hypernetwork from PIL import PngImagePlugin,Image from modules.sd_models import checkpoints_list from modules.realesrgan_model import get_realesrgan_models +from modules import devices from typing import List def upscaler_to_index(name: str): @@ -97,6 +101,11 @@ class Api: self.add_api_route("/sdapi/v1/artist-categories", self.get_artists_categories, methods=["GET"], response_model=List[str]) self.add_api_route("/sdapi/v1/artists", self.get_artists, methods=["GET"], response_model=List[ArtistItem]) self.add_api_route("/sdapi/v1/refresh-checkpoints", self.refresh_checkpoints, methods=["POST"]) + self.add_api_route("/sdapi/v1/create/embedding", self.create_embedding, methods=["POST"], response_model=CreateResponse) + self.add_api_route("/sdapi/v1/create/hypernetwork", self.create_hypernetwork, methods=["POST"], response_model=CreateResponse) + self.add_api_route("/sdapi/v1/preprocess", self.preprocess, methods=["POST"], response_model=PreprocessResponse) + self.add_api_route("/sdapi/v1/train/embedding", self.train_embedding, methods=["POST"], response_model=TrainResponse) + self.add_api_route("/sdapi/v1/train/hypernetwork", self.train_hypernetwork, methods=["POST"], response_model=TrainResponse) def add_api_route(self, path: str, endpoint, **kwargs): if shared.cmd_opts.api_auth: @@ -326,6 +335,89 @@ class Api: def refresh_checkpoints(self): shared.refresh_checkpoints() + def create_embedding(self, args: dict): + try: + shared.state.begin() + filename = create_embedding(**args) # create empty embedding + sd_hijack.model_hijack.embedding_db.load_textual_inversion_embeddings() # reload embeddings so new one can be immediately used + shared.state.end() + return CreateResponse(info = "create embedding filename: {filename}".format(filename = filename)) + except AssertionError as e: + shared.state.end() + return TrainResponse(info = "create embedding error: {error}".format(error = e)) + + def create_hypernetwork(self, args: dict): + try: + shared.state.begin() + filename = create_hypernetwork(**args) # create empty embedding + shared.state.end() + return CreateResponse(info = "create hypernetwork filename: {filename}".format(filename = filename)) + except AssertionError as e: + shared.state.end() + return TrainResponse(info = "create hypernetwork error: {error}".format(error = e)) + + def preprocess(self, args: dict): + try: + shared.state.begin() + preprocess(**args) # quick operation unless blip/booru interrogation is enabled + shared.state.end() + return PreprocessResponse(info = 'preprocess complete') + except KeyError as e: + shared.state.end() + return PreprocessResponse(info = "preprocess error: invalid token: {error}".format(error = e)) + except AssertionError as e: + shared.state.end() + return PreprocessResponse(info = "preprocess error: {error}".format(error = e)) + except FileNotFoundError as e: + shared.state.end() + return PreprocessResponse(info = 'preprocess error: {error}'.format(error = e)) + + def train_embedding(self, args: dict): + try: + shared.state.begin() + apply_optimizations = shared.opts.training_xattention_optimizations + error = None + filename = '' + if not apply_optimizations: + sd_hijack.undo_optimizations() + try: + embedding, filename = train_embedding(**args) # can take a long time to complete + except Exception as e: + error = e + finally: + if not apply_optimizations: + sd_hijack.apply_optimizations() + shared.state.end() + return TrainResponse(info = "train embedding complete: filename: {filename} error: {error}".format(filename = filename, error = error)) + except AssertionError as msg: + shared.state.end() + return TrainResponse(info = "train embedding error: {msg}".format(msg = msg)) + + def train_hypernetwork(self, args: dict): + try: + shared.state.begin() + initial_hypernetwork = shared.loaded_hypernetwork + apply_optimizations = shared.opts.training_xattention_optimizations + error = None + filename = '' + if not apply_optimizations: + sd_hijack.undo_optimizations() + try: + hypernetwork, filename = train_hypernetwork(*args) + except Exception as e: + error = e + finally: + shared.loaded_hypernetwork = initial_hypernetwork + shared.sd_model.cond_stage_model.to(devices.device) + shared.sd_model.first_stage_model.to(devices.device) + if not apply_optimizations: + sd_hijack.apply_optimizations() + shared.state.end() + return TrainResponse(info = "train embedding complete: filename: {filename} error: {error}".format(filename = filename, error = error)) + except AssertionError as msg: + shared.state.end() + return TrainResponse(info = "train embedding error: {error}".format(error = error)) + def launch(self, server_name, port): self.app.include_router(self.router) uvicorn.run(self.app, host=server_name, port=port) diff --git a/modules/api/models.py b/modules/api/models.py index a22bc6b3..c446ce7a 100644 --- a/modules/api/models.py +++ b/modules/api/models.py @@ -175,6 +175,15 @@ class InterrogateRequest(BaseModel): class InterrogateResponse(BaseModel): caption: str = Field(default=None, title="Caption", description="The generated caption for the image.") +class TrainResponse(BaseModel): + info: str = Field(title="Train info", description="Response string from train embedding or hypernetwork task.") + +class CreateResponse(BaseModel): + info: str = Field(title="Create info", description="Response string from create embedding or hypernetwork task.") + +class PreprocessResponse(BaseModel): + info: str = Field(title="Preprocess info", description="Response string from preprocessing task.") + fields = {} for key, metadata in opts.data_labels.items(): value = opts.data.get(key) diff --git a/modules/hypernetworks/hypernetwork.py b/modules/hypernetworks/hypernetwork.py index c406ffb3..3182ff03 100644 --- a/modules/hypernetworks/hypernetwork.py +++ b/modules/hypernetworks/hypernetwork.py @@ -378,6 +378,32 @@ def report_statistics(loss_info:dict): print(e) +def create_hypernetwork(name, enable_sizes, overwrite_old, layer_structure=None, activation_func=None, weight_init=None, add_layer_norm=False, use_dropout=False): + # Remove illegal characters from name. + name = "".join( x for x in name if (x.isalnum() or x in "._- ")) + + fn = os.path.join(shared.cmd_opts.hypernetwork_dir, f"{name}.pt") + if not overwrite_old: + assert not os.path.exists(fn), f"file {fn} already exists" + + if type(layer_structure) == str: + layer_structure = [float(x.strip()) for x in layer_structure.split(",")] + + hypernet = modules.hypernetworks.hypernetwork.Hypernetwork( + name=name, + enable_sizes=[int(x) for x in enable_sizes], + layer_structure=layer_structure, + activation_func=activation_func, + weight_init=weight_init, + add_layer_norm=add_layer_norm, + use_dropout=use_dropout, + ) + hypernet.save(fn) + + shared.reload_hypernetworks() + + return fn + def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, gradient_step, data_root, log_directory, training_width, training_height, steps, shuffle_tags, tag_drop_out, latent_sampling_method, create_image_every, save_hypernetwork_every, template_file, preview_from_txt2img, preview_prompt, preview_negative_prompt, preview_steps, preview_sampler_index, preview_cfg_scale, preview_seed, preview_width, preview_height): # images allows training previews to have infotext. Importing it at the top causes a circular import problem. diff --git a/modules/hypernetworks/ui.py b/modules/hypernetworks/ui.py index c2d4b51c..e7f9e593 100644 --- a/modules/hypernetworks/ui.py +++ b/modules/hypernetworks/ui.py @@ -3,39 +3,16 @@ import os import re import gradio as gr -import modules.textual_inversion.preprocess -import modules.textual_inversion.textual_inversion +import modules.hypernetworks.hypernetwork from modules import devices, sd_hijack, shared -from modules.hypernetworks import hypernetwork not_available = ["hardswish", "multiheadattention"] -keys = list(x for x in hypernetwork.HypernetworkModule.activation_dict.keys() if x not in not_available) +keys = list(x for x in modules.hypernetworks.hypernetwork.HypernetworkModule.activation_dict.keys() if x not in not_available) def create_hypernetwork(name, enable_sizes, overwrite_old, layer_structure=None, activation_func=None, weight_init=None, add_layer_norm=False, use_dropout=False): - # Remove illegal characters from name. - name = "".join( x for x in name if (x.isalnum() or x in "._- ")) + filename = modules.hypernetworks.hypernetwork.create_hypernetwork(name, enable_sizes, overwrite_old, layer_structure, activation_func, weight_init, add_layer_norm, use_dropout) - fn = os.path.join(shared.cmd_opts.hypernetwork_dir, f"{name}.pt") - if not overwrite_old: - assert not os.path.exists(fn), f"file {fn} already exists" - - if type(layer_structure) == str: - layer_structure = [float(x.strip()) for x in layer_structure.split(",")] - - hypernet = modules.hypernetworks.hypernetwork.Hypernetwork( - name=name, - enable_sizes=[int(x) for x in enable_sizes], - layer_structure=layer_structure, - activation_func=activation_func, - weight_init=weight_init, - add_layer_norm=add_layer_norm, - use_dropout=use_dropout, - ) - hypernet.save(fn) - - shared.reload_hypernetworks() - - return gr.Dropdown.update(choices=sorted([x for x in shared.hypernetworks.keys()])), f"Created: {fn}", "" + return gr.Dropdown.update(choices=sorted([x for x in shared.hypernetworks.keys()])), f"Created: {filename}", "" def train_hypernetwork(*args): -- cgit v1.2.3 From b5819d9bf1794071139c640b5f1e72c84a0e051a Mon Sep 17 00:00:00 2001 From: Philpax Date: Mon, 2 Jan 2023 10:17:33 +1100 Subject: feat(api): add /sdapi/v1/embeddings --- modules/api/api.py | 8 ++++++++ modules/api/models.py | 3 +++ 2 files changed, 11 insertions(+) (limited to 'modules/api/models.py') diff --git a/modules/api/api.py b/modules/api/api.py index 11daff0d..30bf3dac 100644 --- a/modules/api/api.py +++ b/modules/api/api.py @@ -100,6 +100,7 @@ class Api: self.add_api_route("/sdapi/v1/prompt-styles", self.get_prompt_styles, methods=["GET"], response_model=List[PromptStyleItem]) self.add_api_route("/sdapi/v1/artist-categories", self.get_artists_categories, methods=["GET"], response_model=List[str]) self.add_api_route("/sdapi/v1/artists", self.get_artists, methods=["GET"], response_model=List[ArtistItem]) + self.add_api_route("/sdapi/v1/embeddings", self.get_embeddings, methods=["GET"], response_model=EmbeddingsResponse) self.add_api_route("/sdapi/v1/refresh-checkpoints", self.refresh_checkpoints, methods=["POST"]) self.add_api_route("/sdapi/v1/create/embedding", self.create_embedding, methods=["POST"], response_model=CreateResponse) self.add_api_route("/sdapi/v1/create/hypernetwork", self.create_hypernetwork, methods=["POST"], response_model=CreateResponse) @@ -327,6 +328,13 @@ class Api: def get_artists(self): return [{"name":x[0], "score":x[1], "category":x[2]} for x in shared.artist_db.artists] + def get_embeddings(self): + db = sd_hijack.model_hijack.embedding_db + return { + "loaded": sorted(db.word_embeddings.keys()), + "skipped": sorted(db.skipped_embeddings), + } + def refresh_checkpoints(self): shared.refresh_checkpoints() diff --git a/modules/api/models.py b/modules/api/models.py index c446ce7a..a8472dc9 100644 --- a/modules/api/models.py +++ b/modules/api/models.py @@ -249,3 +249,6 @@ class ArtistItem(BaseModel): score: float = Field(title="Score") category: str = Field(title="Category") +class EmbeddingsResponse(BaseModel): + loaded: List[str] = Field(title="Loaded", description="Embeddings loaded for the current model") + skipped: List[str] = Field(title="Skipped", description="Embeddings skipped for the current model (likely due to architecture incompatibility)") \ No newline at end of file -- cgit v1.2.3 From c65909ad16a1962129114c6251de092f49479b06 Mon Sep 17 00:00:00 2001 From: Philpax Date: Mon, 2 Jan 2023 12:21:22 +1100 Subject: feat(api): return more data for embeddings --- modules/api/api.py | 17 +++++++++++++++-- modules/api/models.py | 11 +++++++++-- modules/textual_inversion/textual_inversion.py | 8 ++++---- 3 files changed, 28 insertions(+), 8 deletions(-) (limited to 'modules/api/models.py') diff --git a/modules/api/api.py b/modules/api/api.py index 30bf3dac..9c670f00 100644 --- a/modules/api/api.py +++ b/modules/api/api.py @@ -330,9 +330,22 @@ class Api: def get_embeddings(self): db = sd_hijack.model_hijack.embedding_db + + def convert_embedding(embedding): + return { + "step": embedding.step, + "sd_checkpoint": embedding.sd_checkpoint, + "sd_checkpoint_name": embedding.sd_checkpoint_name, + "shape": embedding.shape, + "vectors": embedding.vectors, + } + + def convert_embeddings(embeddings): + return {embedding.name: convert_embedding(embedding) for embedding in embeddings.values()} + return { - "loaded": sorted(db.word_embeddings.keys()), - "skipped": sorted(db.skipped_embeddings), + "loaded": convert_embeddings(db.word_embeddings), + "skipped": convert_embeddings(db.skipped_embeddings), } def refresh_checkpoints(self): diff --git a/modules/api/models.py b/modules/api/models.py index a8472dc9..4a632c68 100644 --- a/modules/api/models.py +++ b/modules/api/models.py @@ -249,6 +249,13 @@ class ArtistItem(BaseModel): score: float = Field(title="Score") category: str = Field(title="Category") +class EmbeddingItem(BaseModel): + step: Optional[int] = Field(title="Step", description="The number of steps that were used to train this embedding, if available") + sd_checkpoint: Optional[str] = Field(title="SD Checkpoint", description="The hash of the checkpoint this embedding was trained on, if available") + sd_checkpoint_name: Optional[str] = Field(title="SD Checkpoint Name", description="The name of the checkpoint this embedding was trained on, if available. Note that this is the name that was used by the trainer; for a stable identifier, use `sd_checkpoint` instead") + shape: int = Field(title="Shape", description="The length of each individual vector in the embedding") + vectors: int = Field(title="Vectors", description="The number of vectors in the embedding") + class EmbeddingsResponse(BaseModel): - loaded: List[str] = Field(title="Loaded", description="Embeddings loaded for the current model") - skipped: List[str] = Field(title="Skipped", description="Embeddings skipped for the current model (likely due to architecture incompatibility)") \ No newline at end of file + loaded: Dict[str, EmbeddingItem] = Field(title="Loaded", description="Embeddings loaded for the current model") + skipped: Dict[str, EmbeddingItem] = Field(title="Skipped", description="Embeddings skipped for the current model (likely due to architecture incompatibility)") \ No newline at end of file diff --git a/modules/textual_inversion/textual_inversion.py b/modules/textual_inversion/textual_inversion.py index 1e5722e7..fd253477 100644 --- a/modules/textual_inversion/textual_inversion.py +++ b/modules/textual_inversion/textual_inversion.py @@ -59,7 +59,7 @@ class EmbeddingDatabase: def __init__(self, embeddings_dir): self.ids_lookup = {} self.word_embeddings = {} - self.skipped_embeddings = [] + self.skipped_embeddings = {} self.dir_mtime = None self.embeddings_dir = embeddings_dir self.expected_shape = -1 @@ -91,7 +91,7 @@ class EmbeddingDatabase: self.dir_mtime = mt self.ids_lookup.clear() self.word_embeddings.clear() - self.skipped_embeddings = [] + self.skipped_embeddings.clear() self.expected_shape = self.get_expected_shape() def process_file(path, filename): @@ -136,7 +136,7 @@ class EmbeddingDatabase: if self.expected_shape == -1 or self.expected_shape == embedding.shape: self.register_embedding(embedding, shared.sd_model) else: - self.skipped_embeddings.append(name) + self.skipped_embeddings[name] = embedding for fn in os.listdir(self.embeddings_dir): try: @@ -153,7 +153,7 @@ class EmbeddingDatabase: print(f"Textual inversion embeddings loaded({len(self.word_embeddings)}): {', '.join(self.word_embeddings.keys())}") if len(self.skipped_embeddings) > 0: - print(f"Textual inversion embeddings skipped({len(self.skipped_embeddings)}): {', '.join(self.skipped_embeddings)}") + print(f"Textual inversion embeddings skipped({len(self.skipped_embeddings)}): {', '.join(self.skipped_embeddings.keys())}") def find_embedding_at_position(self, tokens, offset): token = tokens[offset] -- cgit v1.2.3