From 3369fb27df6c1badd39bcb59b3f71c61a47d3d91 Mon Sep 17 00:00:00 2001 From: SpenserCai Date: Fri, 25 Aug 2023 22:15:35 +0800 Subject: support installed extensions list api --- modules/api/api.py | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'modules/api/api.py') diff --git a/modules/api/api.py b/modules/api/api.py index e6edffe7..0bcf5497 100644 --- a/modules/api/api.py +++ b/modules/api/api.py @@ -243,6 +243,7 @@ class Api: self.add_api_route("/sdapi/v1/reload-checkpoint", self.reloadapi, methods=["POST"]) self.add_api_route("/sdapi/v1/scripts", self.get_scripts_list, methods=["GET"], response_model=models.ScriptsList) self.add_api_route("/sdapi/v1/script-info", self.get_script_info, methods=["GET"], response_model=List[models.ScriptInfo]) + self.add_api_route("/sdapi/v1/extensions", self.get_extensions_list, methods=["GET"], response_model=List[models.ExtensionItem]) if shared.cmd_opts.api_server_stop: self.add_api_route("/sdapi/v1/server-kill", self.kill_webui, methods=["POST"]) @@ -769,6 +770,25 @@ class Api: except Exception as err: cuda = {'error': f'{err}'} return models.MemoryResponse(ram=ram, cuda=cuda) + + def get_extensions_list(self): + from modules import extensions + extensions.list_extensions() + ext_list = [] + for ext in extensions.extensions: + ext: extensions.Extension + ext.read_info_from_repo() + if ext.remote is not None: + ext_list.append({ + "name": ext.name, + "remote": ext.remote, + "branch": ext.branch, + "commit_hash":ext.commit_hash, + "commit_date":ext.commit_date, + "version":ext.version, + "enabled":ext.enabled + }) + return ext_list def launch(self, server_name, port, root_path): self.app.include_router(self.router) -- cgit v1.2.3 From dd07b5193efa547929629b310ef5c9ff0fc83a19 Mon Sep 17 00:00:00 2001 From: SpenserCai Date: Fri, 25 Aug 2023 22:23:17 +0800 Subject: fix format error --- modules/api/api.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'modules/api/api.py') diff --git a/modules/api/api.py b/modules/api/api.py index 0bcf5497..785ee828 100644 --- a/modules/api/api.py +++ b/modules/api/api.py @@ -770,7 +770,7 @@ class Api: except Exception as err: cuda = {'error': f'{err}'} return models.MemoryResponse(ram=ram, cuda=cuda) - + def get_extensions_list(self): from modules import extensions extensions.list_extensions() -- cgit v1.2.3 From 72ee347eabf04d1a238a738a03e7973cc2a46ca3 Mon Sep 17 00:00:00 2001 From: AUTOMATIC1111 <16777216c@gmail.com> Date: Sat, 26 Aug 2023 06:52:18 +0300 Subject: update pnginfo checkpoint to return dict with parsed values --- modules/api/api.py | 10 ++++------ modules/api/models.py | 3 ++- 2 files changed, 6 insertions(+), 7 deletions(-) (limited to 'modules/api/api.py') diff --git a/modules/api/api.py b/modules/api/api.py index 785ee828..844e31ee 100644 --- a/modules/api/api.py +++ b/modules/api/api.py @@ -17,7 +17,7 @@ from fastapi.encoders import jsonable_encoder from secrets import compare_digest import modules.shared as shared -from modules import sd_samplers, deepbooru, sd_hijack, images, scripts, ui, postprocessing, errors, restart, shared_items +from modules import sd_samplers, deepbooru, sd_hijack, images, scripts, ui, postprocessing, errors, restart, shared_items, script_callbacks, generation_parameters_copypaste from modules.api import models from modules.shared import opts from modules.processing import StableDiffusionProcessingTxt2Img, StableDiffusionProcessingImg2Img, process_images @@ -474,9 +474,6 @@ class Api: return models.ExtrasBatchImagesResponse(images=list(map(encode_pil_to_base64, result[0])), html_info=result[1]) def pnginfoapi(self, req: models.PNGInfoRequest): - if(not req.image.strip()): - return models.PNGInfoResponse(info="") - image = decode_base64_to_image(req.image.strip()) if image is None: return models.PNGInfoResponse(info="") @@ -485,9 +482,10 @@ class Api: if geninfo is None: geninfo = "" - items = {**{'parameters': geninfo}, **items} + params = generation_parameters_copypaste.parse_generation_parameters(geninfo) + script_callbacks.infotext_pasted_callback(geninfo, params) - return models.PNGInfoResponse(info=geninfo, items=items) + return models.PNGInfoResponse(info=geninfo, items=items, parameters=params) def progressapi(self, req: models.ProgressRequest = Depends()): # copy from check_progress_call of ui.py diff --git a/modules/api/models.py b/modules/api/models.py index 731ab03d..94eca97d 100644 --- a/modules/api/models.py +++ b/modules/api/models.py @@ -178,7 +178,8 @@ class PNGInfoRequest(BaseModel): class PNGInfoResponse(BaseModel): info: str = Field(title="Image info", description="A string with the parameters used to generate the image") - items: dict = Field(title="Items", description="An object containing all the info the image had") + items: dict = Field(title="Items", description="A dictionary containing all the other fields the image had") + parameters: dict = Field(title="Parameters", description="A dictionary with parsed generation info fields") class ProgressRequest(BaseModel): skip_current_image: bool = Field(default=False, title="Skip current image", description="Skip current image serialization") -- cgit v1.2.3 From b6c1a1bbbf29a3041025aa336f6f843ffd7c7d46 Mon Sep 17 00:00:00 2001 From: a666 <19142162+a666@users.noreply.github.com> Date: Fri, 25 Aug 2023 01:58:19 -0600 Subject: Fix some deprecated types --- modules/api/api.py | 26 +++++++++++++------------- modules/api/models.py | 24 +++++++++++------------- modules/gitpython_hack.py | 2 +- modules/prompt_parser.py | 7 +++---- modules/script_callbacks.py | 6 +++--- modules/sub_quadratic_attention.py | 4 ++-- modules/ui.py | 3 +-- 7 files changed, 34 insertions(+), 38 deletions(-) (limited to 'modules/api/api.py') diff --git a/modules/api/api.py b/modules/api/api.py index 844e31ee..905ef9c9 100644 --- a/modules/api/api.py +++ b/modules/api/api.py @@ -29,7 +29,7 @@ from modules.sd_models import unload_model_weights, reload_model_weights, checkp from modules.sd_models_config import find_checkpoint_config_near_filename from modules.realesrgan_model import get_realesrgan_models from modules import devices -from typing import Dict, List, Any +from typing import Any import piexif import piexif.helper from contextlib import closing @@ -221,15 +221,15 @@ class Api: self.add_api_route("/sdapi/v1/options", self.get_config, methods=["GET"], response_model=models.OptionsModel) self.add_api_route("/sdapi/v1/options", self.set_config, methods=["POST"]) self.add_api_route("/sdapi/v1/cmd-flags", self.get_cmd_flags, methods=["GET"], response_model=models.FlagsModel) - self.add_api_route("/sdapi/v1/samplers", self.get_samplers, methods=["GET"], response_model=List[models.SamplerItem]) - self.add_api_route("/sdapi/v1/upscalers", self.get_upscalers, methods=["GET"], response_model=List[models.UpscalerItem]) - self.add_api_route("/sdapi/v1/latent-upscale-modes", self.get_latent_upscale_modes, methods=["GET"], response_model=List[models.LatentUpscalerModeItem]) - self.add_api_route("/sdapi/v1/sd-models", self.get_sd_models, methods=["GET"], response_model=List[models.SDModelItem]) - self.add_api_route("/sdapi/v1/sd-vae", self.get_sd_vaes, methods=["GET"], response_model=List[models.SDVaeItem]) - self.add_api_route("/sdapi/v1/hypernetworks", self.get_hypernetworks, methods=["GET"], response_model=List[models.HypernetworkItem]) - self.add_api_route("/sdapi/v1/face-restorers", self.get_face_restorers, methods=["GET"], response_model=List[models.FaceRestorerItem]) - self.add_api_route("/sdapi/v1/realesrgan-models", self.get_realesrgan_models, methods=["GET"], response_model=List[models.RealesrganItem]) - self.add_api_route("/sdapi/v1/prompt-styles", self.get_prompt_styles, methods=["GET"], response_model=List[models.PromptStyleItem]) + self.add_api_route("/sdapi/v1/samplers", self.get_samplers, methods=["GET"], response_model=list[models.SamplerItem]) + self.add_api_route("/sdapi/v1/upscalers", self.get_upscalers, methods=["GET"], response_model=list[models.UpscalerItem]) + self.add_api_route("/sdapi/v1/latent-upscale-modes", self.get_latent_upscale_modes, methods=["GET"], response_model=list[models.LatentUpscalerModeItem]) + self.add_api_route("/sdapi/v1/sd-models", self.get_sd_models, methods=["GET"], response_model=list[models.SDModelItem]) + self.add_api_route("/sdapi/v1/sd-vae", self.get_sd_vaes, methods=["GET"], response_model=list[models.SDVaeItem]) + self.add_api_route("/sdapi/v1/hypernetworks", self.get_hypernetworks, methods=["GET"], response_model=list[models.HypernetworkItem]) + self.add_api_route("/sdapi/v1/face-restorers", self.get_face_restorers, methods=["GET"], response_model=list[models.FaceRestorerItem]) + self.add_api_route("/sdapi/v1/realesrgan-models", self.get_realesrgan_models, methods=["GET"], response_model=list[models.RealesrganItem]) + self.add_api_route("/sdapi/v1/prompt-styles", self.get_prompt_styles, methods=["GET"], response_model=list[models.PromptStyleItem]) self.add_api_route("/sdapi/v1/embeddings", self.get_embeddings, methods=["GET"], response_model=models.EmbeddingsResponse) self.add_api_route("/sdapi/v1/refresh-checkpoints", self.refresh_checkpoints, methods=["POST"]) self.add_api_route("/sdapi/v1/refresh-vae", self.refresh_vae, methods=["POST"]) @@ -242,8 +242,8 @@ class Api: self.add_api_route("/sdapi/v1/unload-checkpoint", self.unloadapi, methods=["POST"]) self.add_api_route("/sdapi/v1/reload-checkpoint", self.reloadapi, methods=["POST"]) self.add_api_route("/sdapi/v1/scripts", self.get_scripts_list, methods=["GET"], response_model=models.ScriptsList) - self.add_api_route("/sdapi/v1/script-info", self.get_script_info, methods=["GET"], response_model=List[models.ScriptInfo]) - self.add_api_route("/sdapi/v1/extensions", self.get_extensions_list, methods=["GET"], response_model=List[models.ExtensionItem]) + self.add_api_route("/sdapi/v1/script-info", self.get_script_info, methods=["GET"], response_model=list[models.ScriptInfo]) + self.add_api_route("/sdapi/v1/extensions", self.get_extensions_list, methods=["GET"], response_model=list[models.ExtensionItem]) if shared.cmd_opts.api_server_stop: self.add_api_route("/sdapi/v1/server-kill", self.kill_webui, methods=["POST"]) @@ -563,7 +563,7 @@ class Api: return options - def set_config(self, req: Dict[str, Any]): + def set_config(self, req: dict[str, Any]): checkpoint_name = req.get("sd_model_checkpoint", None) if checkpoint_name is not None and checkpoint_name not in checkpoint_aliases: raise RuntimeError(f"model {checkpoint_name!r} not found") diff --git a/modules/api/models.py b/modules/api/models.py index 94eca97d..a0d80af8 100644 --- a/modules/api/models.py +++ b/modules/api/models.py @@ -1,12 +1,10 @@ import inspect from pydantic import BaseModel, Field, create_model -from typing import Any, Optional -from typing_extensions import Literal +from typing import Any, Optional, Literal from inflection import underscore from modules.processing import StableDiffusionProcessingTxt2Img, StableDiffusionProcessingImg2Img from modules.shared import sd_upscalers, opts, parser -from typing import Dict, List API_NOT_ALLOWED = [ "self", @@ -130,12 +128,12 @@ StableDiffusionImg2ImgProcessingAPI = PydanticModelGenerator( ).generate_model() class TextToImageResponse(BaseModel): - images: List[str] = Field(default=None, title="Image", description="The generated image in base64 format.") + images: list[str] = Field(default=None, title="Image", description="The generated image in base64 format.") parameters: dict info: str class ImageToImageResponse(BaseModel): - images: List[str] = Field(default=None, title="Image", description="The generated image in base64 format.") + images: list[str] = Field(default=None, title="Image", description="The generated image in base64 format.") parameters: dict info: str @@ -168,10 +166,10 @@ class FileData(BaseModel): name: str = Field(title="File name") class ExtrasBatchImagesRequest(ExtrasBaseRequest): - imageList: List[FileData] = Field(title="Images", description="List of images to work on. Must be Base64 strings") + imageList: list[FileData] = Field(title="Images", description="List of images to work on. Must be Base64 strings") class ExtrasBatchImagesResponse(ExtraBaseResponse): - images: List[str] = Field(title="Images", description="The generated images in base64 format.") + images: list[str] = Field(title="Images", description="The generated images in base64 format.") class PNGInfoRequest(BaseModel): image: str = Field(title="Image", description="The base64 encoded PNG image") @@ -233,8 +231,8 @@ FlagsModel = create_model("Flags", **flags) class SamplerItem(BaseModel): name: str = Field(title="Name") - aliases: List[str] = Field(title="Aliases") - options: Dict[str, str] = Field(title="Options") + aliases: list[str] = Field(title="Aliases") + options: dict[str, str] = Field(title="Options") class UpscalerItem(BaseModel): name: str = Field(title="Name") @@ -285,8 +283,8 @@ class EmbeddingItem(BaseModel): vectors: int = Field(title="Vectors", description="The number of vectors in the embedding") class EmbeddingsResponse(BaseModel): - 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)") + 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)") class MemoryResponse(BaseModel): ram: dict = Field(title="RAM", description="System memory stats") @@ -304,14 +302,14 @@ class ScriptArg(BaseModel): minimum: Optional[Any] = Field(default=None, title="Minimum", description="Minimum allowed value for the argumentin UI") maximum: Optional[Any] = Field(default=None, title="Minimum", description="Maximum allowed value for the argumentin UI") step: Optional[Any] = Field(default=None, title="Minimum", description="Step for changing value of the argumentin UI") - choices: Optional[List[str]] = Field(default=None, title="Choices", description="Possible values for the argument") + choices: Optional[list[str]] = Field(default=None, title="Choices", description="Possible values for the argument") class ScriptInfo(BaseModel): name: str = Field(default=None, title="Name", description="Script name") is_alwayson: bool = Field(default=None, title="IsAlwayson", description="Flag specifying whether this script is an alwayson script") is_img2img: bool = Field(default=None, title="IsImg2img", description="Flag specifying whether this script is an img2img script") - args: List[ScriptArg] = Field(title="Arguments", description="List of script's arguments") + args: list[ScriptArg] = Field(title="Arguments", description="List of script's arguments") class ExtensionItem(BaseModel): name: str = Field(title="Name", description="Extension name") diff --git a/modules/gitpython_hack.py b/modules/gitpython_hack.py index e537c1df..b55f0640 100644 --- a/modules/gitpython_hack.py +++ b/modules/gitpython_hack.py @@ -23,7 +23,7 @@ class Git(git.Git): ) return self._parse_object_header(ret) - def stream_object_data(self, ref: str) -> tuple[str, str, int, "Git.CatFileContentStream"]: + def stream_object_data(self, ref: str) -> tuple[str, str, int, Git.CatFileContentStream]: # Not really streaming, per se; this buffers the entire object in memory. # Shouldn't be a problem for our use case, since we're only using this for # object headers (commit objects). diff --git a/modules/prompt_parser.py b/modules/prompt_parser.py index 334efeef..ddf4d2dd 100644 --- a/modules/prompt_parser.py +++ b/modules/prompt_parser.py @@ -2,7 +2,6 @@ from __future__ import annotations import re from collections import namedtuple -from typing import List import lark # a prompt like this: "fantasy landscape with a [mountain:lake:0.25] and [an oak:a christmas tree:0.75][ in foreground::0.6][ in background:0.25] [shoddy:masterful:0.5]" @@ -240,14 +239,14 @@ def get_multicond_prompt_list(prompts: SdConditioning | list[str]): class ComposableScheduledPromptConditioning: def __init__(self, schedules, weight=1.0): - self.schedules: List[ScheduledPromptConditioning] = schedules + self.schedules: list[ScheduledPromptConditioning] = schedules self.weight: float = weight class MulticondLearnedConditioning: def __init__(self, shape, batch): self.shape: tuple = shape # the shape field is needed to send this object to DDIM/PLMS - self.batch: List[List[ComposableScheduledPromptConditioning]] = batch + self.batch: list[list[ComposableScheduledPromptConditioning]] = batch def get_multicond_learned_conditioning(model, prompts, steps, hires_steps=None, use_old_scheduling=False) -> MulticondLearnedConditioning: @@ -278,7 +277,7 @@ class DictWithShape(dict): return self["crossattn"].shape -def reconstruct_cond_batch(c: List[List[ScheduledPromptConditioning]], current_step): +def reconstruct_cond_batch(c: list[list[ScheduledPromptConditioning]], current_step): param = c[0][0].cond is_dict = isinstance(param, dict) diff --git a/modules/script_callbacks.py b/modules/script_callbacks.py index fab23551..9c2a6541 100644 --- a/modules/script_callbacks.py +++ b/modules/script_callbacks.py @@ -1,7 +1,7 @@ import inspect import os from collections import namedtuple -from typing import Optional, Dict, Any +from typing import Optional, Any from fastapi import FastAPI from gradio import Blocks @@ -255,7 +255,7 @@ def image_grid_callback(params: ImageGridLoopParams): report_exception(c, 'image_grid') -def infotext_pasted_callback(infotext: str, params: Dict[str, Any]): +def infotext_pasted_callback(infotext: str, params: dict[str, Any]): for c in callback_map['callbacks_infotext_pasted']: try: c.callback(infotext, params) @@ -446,7 +446,7 @@ def on_infotext_pasted(callback): """register a function to be called before applying an infotext. The callback is called with two arguments: - infotext: str - raw infotext. - - result: Dict[str, any] - parsed infotext parameters. + - result: dict[str, any] - parsed infotext parameters. """ add_callback(callback_map['callbacks_infotext_pasted'], callback) diff --git a/modules/sub_quadratic_attention.py b/modules/sub_quadratic_attention.py index ae4ee4bb..4cb561ef 100644 --- a/modules/sub_quadratic_attention.py +++ b/modules/sub_quadratic_attention.py @@ -15,7 +15,7 @@ import torch from torch import Tensor from torch.utils.checkpoint import checkpoint import math -from typing import Optional, NamedTuple, List +from typing import Optional, NamedTuple def narrow_trunc( @@ -97,7 +97,7 @@ def _query_chunk_attention( ) return summarize_chunk(query, key_chunk, value_chunk) - chunks: List[AttnChunk] = [ + chunks: list[AttnChunk] = [ chunk_scanner(chunk) for chunk in torch.arange(0, k_tokens, kv_chunk_size) ] acc_chunk = AttnChunk(*map(torch.stack, zip(*chunks))) diff --git a/modules/ui.py b/modules/ui.py index f4028475..9a569182 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -1338,7 +1338,6 @@ checkpoint: N/A def setup_ui_api(app): from pydantic import BaseModel, Field - from typing import List class QuicksettingsHint(BaseModel): name: str = Field(title="Name of the quicksettings field") @@ -1347,7 +1346,7 @@ def setup_ui_api(app): def quicksettings_hint(): return [QuicksettingsHint(name=k, label=v.label) for k, v in opts.data_labels.items()] - app.add_api_route("/internal/quicksettings-hint", quicksettings_hint, methods=["GET"], response_model=List[QuicksettingsHint]) + app.add_api_route("/internal/quicksettings-hint", quicksettings_hint, methods=["GET"], response_model=list[QuicksettingsHint]) app.add_api_route("/internal/ping", lambda: {}, methods=["GET"]) -- cgit v1.2.3 From f71e919ecb001c4d191b76a87477d6118de7be12 Mon Sep 17 00:00:00 2001 From: FluttyProger Date: Sun, 1 Oct 2023 18:06:48 +0300 Subject: Ability for extensions to return custom data via api in response.images --- modules/api/api.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'modules/api/api.py') diff --git a/modules/api/api.py b/modules/api/api.py index 905ef9c9..efedafa4 100644 --- a/modules/api/api.py +++ b/modules/api/api.py @@ -103,7 +103,8 @@ def decode_base64_to_image(encoding): def encode_pil_to_base64(image): with io.BytesIO() as output_bytes: - + if isinstance(image, str): + return image if opts.samples_format.lower() == 'png': use_metadata = False metadata = PngImagePlugin.PngInfo() -- cgit v1.2.3 From 282903bb6798f49af66f6935ee4dc0015895cf7c Mon Sep 17 00:00:00 2001 From: AUTOMATIC1111 <16777216c@gmail.com> Date: Sun, 15 Oct 2023 09:41:02 +0300 Subject: repair unload sd checkpoint button --- modules/api/api.py | 11 +++++------ modules/sd_models.py | 13 +------------ modules/ui_settings.py | 24 +++++++++++++++++------- 3 files changed, 23 insertions(+), 25 deletions(-) (limited to 'modules/api/api.py') diff --git a/modules/api/api.py b/modules/api/api.py index efedafa4..09083874 100644 --- a/modules/api/api.py +++ b/modules/api/api.py @@ -17,15 +17,14 @@ from fastapi.encoders import jsonable_encoder from secrets import compare_digest import modules.shared as shared -from modules import sd_samplers, deepbooru, sd_hijack, images, scripts, ui, postprocessing, errors, restart, shared_items, script_callbacks, generation_parameters_copypaste +from modules import sd_samplers, deepbooru, sd_hijack, images, scripts, ui, postprocessing, errors, restart, shared_items, script_callbacks, generation_parameters_copypaste, sd_models from modules.api import models from modules.shared import opts from modules.processing import StableDiffusionProcessingTxt2Img, StableDiffusionProcessingImg2Img, process_images 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 unload_model_weights, reload_model_weights, checkpoint_aliases +from PIL import PngImagePlugin, Image from modules.sd_models_config import find_checkpoint_config_near_filename from modules.realesrgan_model import get_realesrgan_models from modules import devices @@ -541,12 +540,12 @@ class Api: return {} def unloadapi(self): - unload_model_weights() + sd_models.unload_model_weights() return {} def reloadapi(self): - reload_model_weights() + sd_models.send_model_to_device(shared.sd_model) return {} @@ -566,7 +565,7 @@ class Api: def set_config(self, req: dict[str, Any]): checkpoint_name = req.get("sd_model_checkpoint", None) - if checkpoint_name is not None and checkpoint_name not in checkpoint_aliases: + if checkpoint_name is not None and checkpoint_name not in sd_models.checkpoint_aliases: raise RuntimeError(f"model {checkpoint_name!r} not found") for k, v in req.items(): diff --git a/modules/sd_models.py b/modules/sd_models.py index c8efeedc..3b6cdea1 100644 --- a/modules/sd_models.py +++ b/modules/sd_models.py @@ -1,7 +1,6 @@ import collections import os.path import sys -import gc import threading import torch @@ -798,17 +797,7 @@ def reload_model_weights(sd_model=None, info=None): def unload_model_weights(sd_model=None, info=None): - timer = Timer() - - if model_data.sd_model: - model_data.sd_model.to(devices.cpu) - sd_hijack.model_hijack.undo_hijack(model_data.sd_model) - model_data.sd_model = None - sd_model = None - gc.collect() - devices.torch_gc() - - print(f"Unloaded weights {timer.summary()}.") + send_model_to_cpu(sd_model or shared.sd_model) return sd_model diff --git a/modules/ui_settings.py b/modules/ui_settings.py index 74a3aef3..e054d00a 100644 --- a/modules/ui_settings.py +++ b/modules/ui_settings.py @@ -1,6 +1,6 @@ import gradio as gr -from modules import ui_common, shared, script_callbacks, scripts, sd_models, sysinfo +from modules import ui_common, shared, script_callbacks, scripts, sd_models, sysinfo, timer from modules.call_queue import wrap_gradio_call from modules.shared import opts from modules.ui_components import FormRow @@ -177,8 +177,8 @@ class UiSettings: download_localization = gr.Button(value='Download localization template', elem_id="download_localization") reload_script_bodies = gr.Button(value='Reload custom script bodies (No ui updates, No restart)', variant='secondary', elem_id="settings_reload_script_bodies") with gr.Row(): - unload_sd_model = gr.Button(value='Unload SD checkpoint to free VRAM', elem_id="sett_unload_sd_model") - reload_sd_model = gr.Button(value='Reload the last SD checkpoint back into VRAM', elem_id="sett_reload_sd_model") + unload_sd_model = gr.Button(value='Unload SD checkpoint to RAM', elem_id="sett_unload_sd_model") + reload_sd_model = gr.Button(value='Load SD checkpoint to VRAM from RAM', elem_id="sett_reload_sd_model") with gr.Row(): calculate_all_checkpoint_hash = gr.Button(value='Calculate hash for all checkpoint', elem_id="calculate_all_checkpoint_hash") calculate_all_checkpoint_hash_threads = gr.Number(value=1, label="Number of parallel calculations", elem_id="calculate_all_checkpoint_hash_threads", precision=0, minimum=1) @@ -194,16 +194,26 @@ class UiSettings: self.text_settings = gr.Textbox(elem_id="settings_json", value=lambda: opts.dumpjson(), visible=False) + def call_func_and_return_text(func, text): + def handler(): + t = timer.Timer() + func() + t.record(text) + + return f'{text} in {t.total:.1f}s' + + return handler + unload_sd_model.click( - fn=sd_models.unload_model_weights, + fn=call_func_and_return_text(sd_models.unload_model_weights, 'Unloaded the checkpoint'), inputs=[], - outputs=[] + outputs=[self.result] ) reload_sd_model.click( - fn=sd_models.reload_model_weights, + fn=call_func_and_return_text(lambda: sd_models.send_model_to_device(shared.sd_model), 'Loaded the checkpoint'), inputs=[], - outputs=[] + outputs=[self.result] ) request_notifications.click( -- cgit v1.2.3 From 11d23e8ca55c097ecfa255a05b63f194e25f08be Mon Sep 17 00:00:00 2001 From: AUTOMATIC1111 <16777216c@gmail.com> Date: Sat, 2 Dec 2023 18:01:11 +0300 Subject: remove Train/Preprocessing tab and put all its functionality into extras batch images mode --- javascript/ui.js | 17 ++ modules/api/api.py | 15 -- modules/api/models.py | 3 - modules/postprocessing.py | 92 +++++++--- modules/scripts_postprocessing.py | 86 ++++++++- modules/shared_options.py | 1 + modules/textual_inversion/preprocess.py | 232 ------------------------ modules/textual_inversion/ui.py | 7 - modules/ui.py | 107 ----------- modules/ui_postprocessing.py | 16 +- modules/ui_toprow.py | 6 +- scripts/postprocessing_caption.py | 30 +++ scripts/postprocessing_codeformer.py | 16 +- scripts/postprocessing_create_flipped_copies.py | 32 ++++ scripts/postprocessing_focal_crop.py | 54 ++++++ scripts/postprocessing_gfpgan.py | 13 +- scripts/postprocessing_split_oversized.py | 71 ++++++++ scripts/postprocessing_upscale.py | 12 ++ scripts/processing_autosized_crop.py | 64 +++++++ 19 files changed, 460 insertions(+), 414 deletions(-) delete mode 100644 modules/textual_inversion/preprocess.py create mode 100644 scripts/postprocessing_caption.py create mode 100644 scripts/postprocessing_create_flipped_copies.py create mode 100644 scripts/postprocessing_focal_crop.py create mode 100644 scripts/postprocessing_split_oversized.py create mode 100644 scripts/processing_autosized_crop.py (limited to 'modules/api/api.py') diff --git a/javascript/ui.js b/javascript/ui.js index 2e262602..410fc44e 100644 --- a/javascript/ui.js +++ b/javascript/ui.js @@ -170,6 +170,23 @@ function submit_img2img() { return res; } +function submit_extras() { + showSubmitButtons('extras', false); + + var id = randomId(); + + requestProgress(id, gradioApp().getElementById('extras_gallery_container'), gradioApp().getElementById('extras_gallery'), function() { + showSubmitButtons('extras', true); + }); + + var res = create_submit_args(arguments); + + res[0] = id; + + console.log(res); + return res; +} + function restoreProgressTxt2img() { showRestoreProgressButton("txt2img", false); var id = localGet("txt2img_task_id"); diff --git a/modules/api/api.py b/modules/api/api.py index 09083874..b3d74e51 100644 --- a/modules/api/api.py +++ b/modules/api/api.py @@ -22,7 +22,6 @@ from modules.api import models from modules.shared import opts from modules.processing import StableDiffusionProcessingTxt2Img, StableDiffusionProcessingImg2Img, process_images 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_config import find_checkpoint_config_near_filename @@ -235,7 +234,6 @@ class Api: self.add_api_route("/sdapi/v1/refresh-vae", self.refresh_vae, methods=["POST"]) self.add_api_route("/sdapi/v1/create/embedding", self.create_embedding, methods=["POST"], response_model=models.CreateResponse) self.add_api_route("/sdapi/v1/create/hypernetwork", self.create_hypernetwork, methods=["POST"], response_model=models.CreateResponse) - self.add_api_route("/sdapi/v1/preprocess", self.preprocess, methods=["POST"], response_model=models.PreprocessResponse) self.add_api_route("/sdapi/v1/train/embedding", self.train_embedding, methods=["POST"], response_model=models.TrainResponse) self.add_api_route("/sdapi/v1/train/hypernetwork", self.train_hypernetwork, methods=["POST"], response_model=models.TrainResponse) self.add_api_route("/sdapi/v1/memory", self.get_memory, methods=["GET"], response_model=models.MemoryResponse) @@ -675,19 +673,6 @@ class Api: finally: shared.state.end() - def preprocess(self, args: dict): - try: - shared.state.begin(job="preprocess") - preprocess(**args) # quick operation unless blip/booru interrogation is enabled - shared.state.end() - return models.PreprocessResponse(info='preprocess complete') - except KeyError as e: - return models.PreprocessResponse(info=f"preprocess error: invalid token: {e}") - except Exception as e: - return models.PreprocessResponse(info=f"preprocess error: {e}") - finally: - shared.state.end() - def train_embedding(self, args: dict): try: shared.state.begin(job="train_embedding") diff --git a/modules/api/models.py b/modules/api/models.py index a0d80af8..33894b3e 100644 --- a/modules/api/models.py +++ b/modules/api/models.py @@ -202,9 +202,6 @@ class TrainResponse(BaseModel): 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/postprocessing.py b/modules/postprocessing.py index 0a134ee4..3c85a74c 100644 --- a/modules/postprocessing.py +++ b/modules/postprocessing.py @@ -6,7 +6,7 @@ from modules import shared, images, devices, scripts, scripts_postprocessing, ui from modules.shared import opts -def run_postprocessing(extras_mode, image, image_folder, input_dir, output_dir, show_extras_results, *args, save_output: bool = True): +def run_postprocessing(id_task, extras_mode, image, image_folder, input_dir, output_dir, show_extras_results, *args, save_output: bool = True): devices.torch_gc() shared.state.begin(job="extras") @@ -29,11 +29,7 @@ def run_postprocessing(extras_mode, image, image_folder, input_dir, output_dir, image_list = shared.listfiles(input_dir) for filename in image_list: - try: - image = Image.open(filename) - except Exception: - continue - yield image, filename + yield filename, filename else: assert image, 'image not selected' yield image, None @@ -45,37 +41,85 @@ def run_postprocessing(extras_mode, image, image_folder, input_dir, output_dir, infotext = '' - for image_data, name in get_images(extras_mode, image, image_folder, input_dir): + data_to_process = list(get_images(extras_mode, image, image_folder, input_dir)) + shared.state.job_count = len(data_to_process) + + for image_placeholder, name in data_to_process: image_data: Image.Image + shared.state.nextjob() shared.state.textinfo = name + shared.state.skipped = False + + if shared.state.interrupted: + break + + if isinstance(image_placeholder, str): + try: + image_data = Image.open(image_placeholder) + except Exception: + continue + else: + image_data = image_placeholder + + shared.state.assign_current_image(image_data) parameters, existing_pnginfo = images.read_info_from_image(image_data) if parameters: existing_pnginfo["parameters"] = parameters - pp = scripts_postprocessing.PostprocessedImage(image_data.convert("RGB")) + initial_pp = scripts_postprocessing.PostprocessedImage(image_data.convert("RGB")) - scripts.scripts_postproc.run(pp, args) + scripts.scripts_postproc.run(initial_pp, args) - if opts.use_original_name_batch and name is not None: - basename = os.path.splitext(os.path.basename(name))[0] - forced_filename = basename - else: - basename = '' - forced_filename = None + if shared.state.skipped: + continue + + used_suffixes = {} + for pp in [initial_pp, *initial_pp.extra_images]: + suffix = pp.get_suffix(used_suffixes) + + if opts.use_original_name_batch and name is not None: + basename = os.path.splitext(os.path.basename(name))[0] + forced_filename = basename + suffix + else: + basename = '' + forced_filename = None + + infotext = ", ".join([k if k == v else f'{k}: {generation_parameters_copypaste.quote(v)}' for k, v in pp.info.items() if v is not None]) + + if opts.enable_pnginfo: + pp.image.info = existing_pnginfo + pp.image.info["postprocessing"] = infotext + + if save_output: + fullfn, _ = images.save_image(pp.image, path=outpath, basename=basename, extension=opts.samples_format, info=infotext, short_filename=True, no_prompt=True, grid=False, pnginfo_section_name="extras", existing_info=existing_pnginfo, forced_filename=forced_filename, suffix=suffix) - infotext = ", ".join([k if k == v else f'{k}: {generation_parameters_copypaste.quote(v)}' for k, v in pp.info.items() if v is not None]) + if pp.caption: + caption_filename = os.path.splitext(fullfn)[0] + ".txt" + if os.path.isfile(caption_filename): + with open(caption_filename, encoding="utf8") as file: + existing_caption = file.read().strip() + else: + existing_caption = "" - if opts.enable_pnginfo: - pp.image.info = existing_pnginfo - pp.image.info["postprocessing"] = infotext + action = shared.opts.postprocessing_existing_caption_action + if action == 'Prepend' and existing_caption: + caption = f"{existing_caption} {pp.caption}" + elif action == 'Append' and existing_caption: + caption = f"{pp.caption} {existing_caption}" + elif action == 'Keep' and existing_caption: + caption = existing_caption + else: + caption = pp.caption - if save_output: - images.save_image(pp.image, path=outpath, basename=basename, extension=opts.samples_format, info=infotext, short_filename=True, no_prompt=True, grid=False, pnginfo_section_name="extras", existing_info=existing_pnginfo, forced_filename=forced_filename) + caption = caption.strip() + if caption: + with open(caption_filename, "w", encoding="utf8") as file: + file.write(caption) - if extras_mode != 2 or show_extras_results: - outputs.append(pp.image) + if extras_mode != 2 or show_extras_results: + outputs.append(pp.image) image_data.close() @@ -99,9 +143,11 @@ def run_extras(extras_mode, resize_mode, image, image_folder, input_dir, output_ "upscaler_2_visibility": extras_upscaler_2_visibility, }, "GFPGAN": { + "enable": True, "gfpgan_visibility": gfpgan_visibility, }, "CodeFormer": { + "enable": True, "codeformer_visibility": codeformer_visibility, "codeformer_weight": codeformer_weight, }, diff --git a/modules/scripts_postprocessing.py b/modules/scripts_postprocessing.py index bac1335d..901cad08 100644 --- a/modules/scripts_postprocessing.py +++ b/modules/scripts_postprocessing.py @@ -1,13 +1,56 @@ +import dataclasses import os import gradio as gr from modules import errors, shared +@dataclasses.dataclass +class PostprocessedImageSharedInfo: + target_width: int = None + target_height: int = None + + class PostprocessedImage: def __init__(self, image): self.image = image self.info = {} + self.shared = PostprocessedImageSharedInfo() + self.extra_images = [] + self.nametags = [] + self.disable_processing = False + self.caption = None + + def get_suffix(self, used_suffixes=None): + used_suffixes = {} if used_suffixes is None else used_suffixes + suffix = "-".join(self.nametags) + if suffix: + suffix = "-" + suffix + + if suffix not in used_suffixes: + used_suffixes[suffix] = 1 + return suffix + + for i in range(1, 100): + proposed_suffix = suffix + "-" + str(i) + + if proposed_suffix not in used_suffixes: + used_suffixes[proposed_suffix] = 1 + return proposed_suffix + + return suffix + + def create_copy(self, new_image, *, nametags=None, disable_processing=False): + pp = PostprocessedImage(new_image) + pp.shared = self.shared + pp.nametags = self.nametags.copy() + pp.info = self.info.copy() + pp.disable_processing = disable_processing + + if nametags is not None: + pp.nametags += nametags + + return pp class ScriptPostprocessing: @@ -42,10 +85,17 @@ class ScriptPostprocessing: pass - def image_changed(self): - pass + def process_firstpass(self, pp: PostprocessedImage, **args): + """ + Called for all scripts before calling process(). Scripts can examine the image here and set fields + of the pp object to communicate things to other scripts. + args contains a dictionary with all values returned by components from ui() + """ + pass + def image_changed(self): + pass def wrap_call(func, filename, funcname, *args, default=None, **kwargs): @@ -118,16 +168,42 @@ class ScriptPostprocessingRunner: return inputs def run(self, pp: PostprocessedImage, args): - for script in self.scripts_in_preferred_order(): - shared.state.job = script.name + scripts = [] + for script in self.scripts_in_preferred_order(): script_args = args[script.args_from:script.args_to] process_args = {} for (name, _component), value in zip(script.controls.items(), script_args): process_args[name] = value - script.process(pp, **process_args) + scripts.append((script, process_args)) + + for script, process_args in scripts: + script.process_firstpass(pp, **process_args) + + all_images = [pp] + + for script, process_args in scripts: + if shared.state.skipped: + break + + shared.state.job = script.name + + for single_image in all_images.copy(): + + if not single_image.disable_processing: + script.process(single_image, **process_args) + + for extra_image in single_image.extra_images: + if not isinstance(extra_image, PostprocessedImage): + extra_image = single_image.create_copy(extra_image) + + all_images.append(extra_image) + + single_image.extra_images.clear() + + pp.extra_images = all_images[1:] def create_args_for_run(self, scripts_args): if not self.ui_created: diff --git a/modules/shared_options.py b/modules/shared_options.py index d8a27180..859dee40 100644 --- a/modules/shared_options.py +++ b/modules/shared_options.py @@ -357,6 +357,7 @@ options_templates.update(options_section(('postprocessing', "Postprocessing", "p 'postprocessing_enable_in_main_ui': OptionInfo([], "Enable postprocessing operations in txt2img and img2img tabs", ui_components.DropdownMulti, lambda: {"choices": [x.name for x in shared_items.postprocessing_scripts()]}), 'postprocessing_operation_order': OptionInfo([], "Postprocessing operation order", ui_components.DropdownMulti, lambda: {"choices": [x.name for x in shared_items.postprocessing_scripts()]}), 'upscaling_max_images_in_cache': OptionInfo(5, "Maximum number of images in upscaling cache", gr.Slider, {"minimum": 0, "maximum": 10, "step": 1}), + 'postprocessing_existing_caption_action': OptionInfo("Ignore", "Action for existing captions", gr.Radio, {"choices": ["Ignore", "Keep", "Prepend", "Append"]}).info("when generating captions using postprocessing; Ignore = use generated; Keep = use original; Prepend/Append = combine both"), })) options_templates.update(options_section((None, "Hidden options"), { diff --git a/modules/textual_inversion/preprocess.py b/modules/textual_inversion/preprocess.py deleted file mode 100644 index 789fa083..00000000 --- a/modules/textual_inversion/preprocess.py +++ /dev/null @@ -1,232 +0,0 @@ -import os -from PIL import Image, ImageOps -import math -import tqdm - -from modules import shared, images, deepbooru -from modules.textual_inversion import autocrop - - -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=0.15, 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): - try: - if process_caption: - shared.interrogator.load() - - if process_caption_deepbooru: - deepbooru.model.start() - - 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: - - if process_caption: - shared.interrogator.send_blip_to_ram() - - if process_caption_deepbooru: - deepbooru.model.stop() - - -def listfiles(dirname): - return os.listdir(dirname) - - -class PreprocessParams: - src = None - dstdir = None - subindex = 0 - flip = False - process_caption = False - process_caption_deepbooru = False - preprocess_txt_action = None - - -def save_pic_with_caption(image, index, params: PreprocessParams, existing_caption=None): - caption = "" - - if params.process_caption: - caption += shared.interrogator.generate_caption(image) - - if params.process_caption_deepbooru: - if caption: - caption += ", " - caption += deepbooru.model.tag_multi(image) - - filename_part = params.src - filename_part = os.path.splitext(filename_part)[0] - filename_part = os.path.basename(filename_part) - - basename = f"{index:05}-{params.subindex}-{filename_part}" - image.save(os.path.join(params.dstdir, f"{basename}.png")) - - if params.preprocess_txt_action == 'prepend' and existing_caption: - caption = f"{existing_caption} {caption}" - elif params.preprocess_txt_action == 'append' and existing_caption: - caption = f"{caption} {existing_caption}" - elif params.preprocess_txt_action == 'copy' and existing_caption: - caption = existing_caption - - caption = caption.strip() - - if caption: - with open(os.path.join(params.dstdir, f"{basename}.txt"), "w", encoding="utf8") as file: - file.write(caption) - - params.subindex += 1 - - -def save_pic(image, index, params, existing_caption=None): - save_pic_with_caption(image, index, params, existing_caption=existing_caption) - - if params.flip: - save_pic_with_caption(ImageOps.mirror(image), index, params, existing_caption=existing_caption) - - -def split_pic(image, inverse_xy, width, height, overlap_ratio): - if inverse_xy: - from_w, from_h = image.height, image.width - to_w, to_h = height, width - else: - from_w, from_h = image.width, image.height - to_w, to_h = width, height - h = from_h * to_w // from_w - if inverse_xy: - image = image.resize((h, to_w)) - else: - image = image.resize((to_w, h)) - - split_count = math.ceil((h - to_h * overlap_ratio) / (to_h * (1.0 - overlap_ratio))) - y_step = (h - to_h) / (split_count - 1) - for i in range(split_count): - y = int(y_step * i) - if inverse_xy: - splitted = image.crop((y, 0, y + to_h, to_w)) - else: - splitted = image.crop((0, y, to_w, y + to_h)) - yield splitted - -# not using torchvision.transforms.CenterCrop because it doesn't allow float regions -def center_crop(image: Image, w: int, h: int): - iw, ih = image.size - if ih / h < iw / w: - sw = w * ih / h - box = (iw - sw) / 2, 0, iw - (iw - sw) / 2, ih - else: - sh = h * iw / w - box = 0, (ih - sh) / 2, iw, ih - (ih - sh) / 2 - return image.resize((w, h), Image.Resampling.LANCZOS, box) - - -def multicrop_pic(image: Image, mindim, maxdim, minarea, maxarea, objective, threshold): - iw, ih = image.size - err = lambda w, h: 1-(lambda x: x if x < 1 else 1/x)(iw/ih/(w/h)) - wh = max(((w, h) for w in range(mindim, maxdim+1, 64) for h in range(mindim, maxdim+1, 64) - if minarea <= w * h <= maxarea and err(w, h) <= threshold), - key= lambda wh: (wh[0]*wh[1], -err(*wh))[::1 if objective=='Maximize area' else -1], - default=None - ) - return wh and center_crop(image, *wh) - - -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) - dst = os.path.abspath(process_dst) - split_threshold = max(0.0, min(1.0, split_threshold)) - overlap_ratio = max(0.0, min(0.9, overlap_ratio)) - - assert src != dst, 'same directory specified as source and destination' - - os.makedirs(dst, exist_ok=True) - - files = listfiles(src) - - shared.state.job = "preprocess" - shared.state.textinfo = "Preprocessing..." - shared.state.job_count = len(files) - - params = PreprocessParams() - params.dstdir = dst - params.flip = process_flip - params.process_caption = process_caption - params.process_caption_deepbooru = process_caption_deepbooru - params.preprocess_txt_action = preprocess_txt_action - - pbar = tqdm.tqdm(files) - for index, imagefile in enumerate(pbar): - params.subindex = 0 - filename = os.path.join(src, imagefile) - try: - img = Image.open(filename) - img = ImageOps.exif_transpose(img) - img = img.convert("RGB") - except Exception: - continue - - description = f"Preprocessing [Image {index}/{len(files)}]" - pbar.set_description(description) - shared.state.textinfo = description - - params.src = filename - - existing_caption = None - existing_caption_filename = f"{os.path.splitext(filename)[0]}.txt" - if os.path.exists(existing_caption_filename): - with open(existing_caption_filename, 'r', encoding="utf8") as file: - existing_caption = file.read() - - if shared.state.interrupted: - break - - if img.height > img.width: - ratio = (img.width * height) / (img.height * width) - inverse_xy = False - else: - ratio = (img.height * width) / (img.width * height) - inverse_xy = True - - process_default_resize = True - - if process_split and ratio < 1.0 and ratio <= split_threshold: - for splitted in split_pic(img, inverse_xy, width, height, overlap_ratio): - save_pic(splitted, index, params, existing_caption=existing_caption) - process_default_resize = False - - if process_focal_crop and img.height != img.width: - - dnn_model_path = None - try: - dnn_model_path = autocrop.download_and_cache_models() - except Exception as e: - print("Unable to load face detection model for auto crop selection. Falling back to lower quality haar method.", e) - - autocrop_settings = autocrop.Settings( - crop_width = width, - crop_height = height, - face_points_weight = process_focal_crop_face_weight, - entropy_points_weight = process_focal_crop_entropy_weight, - corner_points_weight = process_focal_crop_edges_weight, - annotate_image = process_focal_crop_debug, - dnn_model_path = dnn_model_path, - ) - for focal in autocrop.crop_image(img, autocrop_settings): - save_pic(focal, index, params, existing_caption=existing_caption) - process_default_resize = False - - if process_multicrop: - cropped = multicrop_pic(img, process_multicrop_mindim, process_multicrop_maxdim, process_multicrop_minarea, process_multicrop_maxarea, process_multicrop_objective, process_multicrop_threshold) - if cropped is not None: - save_pic(cropped, index, params, existing_caption=existing_caption) - else: - 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) - - shared.state.nextjob() diff --git a/modules/textual_inversion/ui.py b/modules/textual_inversion/ui.py index 35c4feef..f149ad1f 100644 --- a/modules/textual_inversion/ui.py +++ b/modules/textual_inversion/ui.py @@ -3,7 +3,6 @@ import html import gradio as gr import modules.textual_inversion.textual_inversion -import modules.textual_inversion.preprocess from modules import sd_hijack, shared @@ -15,12 +14,6 @@ def create_embedding(name, initialization_text, nvpt, overwrite_old): return gr.Dropdown.update(choices=sorted(sd_hijack.model_hijack.embedding_db.word_embeddings.keys())), f"Created: {filename}", "" -def preprocess(*args): - modules.textual_inversion.preprocess.preprocess(*args) - - return f"Preprocessing {'interrupted' if shared.state.interrupted else 'finished'}.", "" - - def train_embedding(*args): assert not shared.cmd_opts.lowvram, 'Training models with lowvram not possible' diff --git a/modules/ui.py b/modules/ui.py index 08e0ad77..d80486dd 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -912,71 +912,6 @@ def create_ui(): with gr.Column(): create_hypernetwork = gr.Button(value="Create hypernetwork", variant='primary', elem_id="train_create_hypernetwork") - with gr.Tab(label="Preprocess images", id="preprocess_images"): - process_src = gr.Textbox(label='Source directory', elem_id="train_process_src") - process_dst = gr.Textbox(label='Destination directory', elem_id="train_process_dst") - process_width = gr.Slider(minimum=64, maximum=2048, step=8, label="Width", value=512, elem_id="train_process_width") - process_height = gr.Slider(minimum=64, maximum=2048, step=8, label="Height", value=512, elem_id="train_process_height") - preprocess_txt_action = gr.Dropdown(label='Existing Caption txt Action', value="ignore", choices=["ignore", "copy", "prepend", "append"], elem_id="train_preprocess_txt_action") - - with gr.Row(): - process_keep_original_size = gr.Checkbox(label='Keep original size', elem_id="train_process_keep_original_size") - process_flip = gr.Checkbox(label='Create flipped copies', elem_id="train_process_flip") - process_split = gr.Checkbox(label='Split oversized images', elem_id="train_process_split") - process_focal_crop = gr.Checkbox(label='Auto focal point crop', elem_id="train_process_focal_crop") - process_multicrop = gr.Checkbox(label='Auto-sized crop', elem_id="train_process_multicrop") - process_caption = gr.Checkbox(label='Use BLIP for caption', elem_id="train_process_caption") - process_caption_deepbooru = gr.Checkbox(label='Use deepbooru for caption', visible=True, elem_id="train_process_caption_deepbooru") - - with gr.Row(visible=False) as process_split_extra_row: - process_split_threshold = gr.Slider(label='Split image threshold', value=0.5, minimum=0.0, maximum=1.0, step=0.05, elem_id="train_process_split_threshold") - process_overlap_ratio = gr.Slider(label='Split image overlap ratio', value=0.2, minimum=0.0, maximum=0.9, step=0.05, elem_id="train_process_overlap_ratio") - - with gr.Row(visible=False) as process_focal_crop_row: - process_focal_crop_face_weight = gr.Slider(label='Focal point face weight', value=0.9, minimum=0.0, maximum=1.0, step=0.05, elem_id="train_process_focal_crop_face_weight") - process_focal_crop_entropy_weight = gr.Slider(label='Focal point entropy weight', value=0.15, minimum=0.0, maximum=1.0, step=0.05, elem_id="train_process_focal_crop_entropy_weight") - process_focal_crop_edges_weight = gr.Slider(label='Focal point edges weight', value=0.5, minimum=0.0, maximum=1.0, step=0.05, elem_id="train_process_focal_crop_edges_weight") - process_focal_crop_debug = gr.Checkbox(label='Create debug image', elem_id="train_process_focal_crop_debug") - - with gr.Column(visible=False) as process_multicrop_col: - gr.Markdown('Each image is center-cropped with an automatically chosen width and height.') - with gr.Row(): - process_multicrop_mindim = gr.Slider(minimum=64, maximum=2048, step=8, label="Dimension lower bound", value=384, elem_id="train_process_multicrop_mindim") - process_multicrop_maxdim = gr.Slider(minimum=64, maximum=2048, step=8, label="Dimension upper bound", value=768, elem_id="train_process_multicrop_maxdim") - with gr.Row(): - process_multicrop_minarea = gr.Slider(minimum=64*64, maximum=2048*2048, step=1, label="Area lower bound", value=64*64, elem_id="train_process_multicrop_minarea") - process_multicrop_maxarea = gr.Slider(minimum=64*64, maximum=2048*2048, step=1, label="Area upper bound", value=640*640, elem_id="train_process_multicrop_maxarea") - with gr.Row(): - process_multicrop_objective = gr.Radio(["Maximize area", "Minimize error"], value="Maximize area", label="Resizing objective", elem_id="train_process_multicrop_objective") - process_multicrop_threshold = gr.Slider(minimum=0, maximum=1, step=0.01, label="Error threshold", value=0.1, elem_id="train_process_multicrop_threshold") - - with gr.Row(): - with gr.Column(scale=3): - gr.HTML(value="") - - with gr.Column(): - with gr.Row(): - interrupt_preprocessing = gr.Button("Interrupt", elem_id="train_interrupt_preprocessing") - run_preprocess = gr.Button(value="Preprocess", variant='primary', elem_id="train_run_preprocess") - - process_split.change( - fn=lambda show: gr_show(show), - inputs=[process_split], - outputs=[process_split_extra_row], - ) - - process_focal_crop.change( - fn=lambda show: gr_show(show), - inputs=[process_focal_crop], - outputs=[process_focal_crop_row], - ) - - process_multicrop.change( - fn=lambda show: gr_show(show), - inputs=[process_multicrop], - outputs=[process_multicrop_col], - ) - def get_textual_inversion_template_names(): return sorted(textual_inversion.textual_inversion_templates) @@ -1077,42 +1012,6 @@ def create_ui(): ] ) - run_preprocess.click( - fn=wrap_gradio_gpu_call(textual_inversion_ui.preprocess, extra_outputs=[gr.update()]), - _js="start_training_textual_inversion", - inputs=[ - dummy_component, - process_src, - process_dst, - process_width, - process_height, - preprocess_txt_action, - process_keep_original_size, - process_flip, - process_split, - process_caption, - process_caption_deepbooru, - process_split_threshold, - process_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, - ], - outputs=[ - ti_output, - ti_outcome, - ], - ) - train_embedding.click( fn=wrap_gradio_gpu_call(textual_inversion_ui.train_embedding, extra_outputs=[gr.update()]), _js="start_training_textual_inversion", @@ -1186,12 +1085,6 @@ def create_ui(): outputs=[], ) - interrupt_preprocessing.click( - fn=lambda: shared.state.interrupt(), - inputs=[], - outputs=[], - ) - loadsave = ui_loadsave.UiLoadsave(cmd_opts.ui_config_file) settings = ui_settings.UiSettings() diff --git a/modules/ui_postprocessing.py b/modules/ui_postprocessing.py index 802e1ce7..fbad0800 100644 --- a/modules/ui_postprocessing.py +++ b/modules/ui_postprocessing.py @@ -1,9 +1,10 @@ import gradio as gr -from modules import scripts, shared, ui_common, postprocessing, call_queue +from modules import scripts, shared, ui_common, postprocessing, call_queue, ui_toprow import modules.generation_parameters_copypaste as parameters_copypaste def create_ui(): + dummy_component = gr.Label(visible=False) tab_index = gr.State(value=0) with gr.Row(equal_height=False, variant='compact'): @@ -20,11 +21,13 @@ def create_ui(): extras_batch_output_dir = gr.Textbox(label="Output directory", **shared.hide_dirs, placeholder="Leave blank to save images to the default path.", elem_id="extras_batch_output_dir") show_extras_results = gr.Checkbox(label='Show result images', value=True, elem_id="extras_show_extras_results") - submit = gr.Button('Generate', elem_id="extras_generate", variant='primary') - script_inputs = scripts.scripts_postproc.setup_ui() with gr.Column(): + toprow = ui_toprow.Toprow(is_compact=True, is_img2img=False, id_part="extras") + toprow.create_inline_toprow_image() + submit = toprow.submit + result_images, html_info_x, html_info, html_log = ui_common.create_output_panel("extras", shared.opts.outdir_extras_samples) tab_single.select(fn=lambda: 0, inputs=[], outputs=[tab_index]) @@ -33,7 +36,9 @@ def create_ui(): submit.click( fn=call_queue.wrap_gradio_gpu_call(postprocessing.run_postprocessing, extra_outputs=[None, '']), + _js="submit_extras", inputs=[ + dummy_component, tab_index, extras_image, image_batch, @@ -45,8 +50,9 @@ def create_ui(): outputs=[ result_images, html_info_x, - html_info, - ] + html_log, + ], + show_progress=False, ) parameters_copypaste.add_paste_fields("extras", extras_image, None) diff --git a/modules/ui_toprow.py b/modules/ui_toprow.py index 985b5a2d..88838f97 100644 --- a/modules/ui_toprow.py +++ b/modules/ui_toprow.py @@ -34,8 +34,10 @@ class Toprow: submit_box = None - def __init__(self, is_img2img, is_compact=False): - id_part = "img2img" if is_img2img else "txt2img" + def __init__(self, is_img2img, is_compact=False, id_part=None): + if id_part is None: + id_part = "img2img" if is_img2img else "txt2img" + self.id_part = id_part self.is_img2img = is_img2img self.is_compact = is_compact diff --git a/scripts/postprocessing_caption.py b/scripts/postprocessing_caption.py new file mode 100644 index 00000000..243e3ad9 --- /dev/null +++ b/scripts/postprocessing_caption.py @@ -0,0 +1,30 @@ +from modules import scripts_postprocessing, ui_components, deepbooru, shared +import gradio as gr + + +class ScriptPostprocessingCeption(scripts_postprocessing.ScriptPostprocessing): + name = "Caption" + order = 4000 + + def ui(self): + with ui_components.InputAccordion(False, label="Caption") as enable: + option = gr.CheckboxGroup(value=["Deepbooru"], choices=["Deepbooru", "BLIP"], show_label=False) + + return { + "enable": enable, + "option": option, + } + + def process(self, pp: scripts_postprocessing.PostprocessedImage, enable, option): + if not enable: + return + + captions = [pp.caption] + + if "Deepbooru" in option: + captions.append(deepbooru.model.tag(pp.image)) + + if "BLIP" in option: + captions.append(shared.interrogator.generate_caption(pp.image)) + + pp.caption = ", ".join([x for x in captions if x]) diff --git a/scripts/postprocessing_codeformer.py b/scripts/postprocessing_codeformer.py index a7d80d40..e1e156dd 100644 --- a/scripts/postprocessing_codeformer.py +++ b/scripts/postprocessing_codeformer.py @@ -1,28 +1,28 @@ from PIL import Image import numpy as np -from modules import scripts_postprocessing, codeformer_model +from modules import scripts_postprocessing, codeformer_model, ui_components import gradio as gr -from modules.ui_components import FormRow - class ScriptPostprocessingCodeFormer(scripts_postprocessing.ScriptPostprocessing): name = "CodeFormer" order = 3000 def ui(self): - with FormRow(): - codeformer_visibility = gr.Slider(minimum=0.0, maximum=1.0, step=0.001, label="CodeFormer visibility", value=0, elem_id="extras_codeformer_visibility") - codeformer_weight = gr.Slider(minimum=0.0, maximum=1.0, step=0.001, label="CodeFormer weight (0 = maximum effect, 1 = minimum effect)", value=0, elem_id="extras_codeformer_weight") + with ui_components.InputAccordion(False, label="CodeFormer") as enable: + with gr.Row(): + codeformer_visibility = gr.Slider(minimum=0.0, maximum=1.0, step=0.001, label="Visibility", value=1.0, elem_id="extras_codeformer_visibility") + codeformer_weight = gr.Slider(minimum=0.0, maximum=1.0, step=0.001, label="Weight (0 = maximum effect, 1 = minimum effect)", value=0, elem_id="extras_codeformer_weight") return { + "enable": enable, "codeformer_visibility": codeformer_visibility, "codeformer_weight": codeformer_weight, } - def process(self, pp: scripts_postprocessing.PostprocessedImage, codeformer_visibility, codeformer_weight): - if codeformer_visibility == 0: + def process(self, pp: scripts_postprocessing.PostprocessedImage, enable, codeformer_visibility, codeformer_weight): + if codeformer_visibility == 0 or not enable: return restored_img = codeformer_model.codeformer.restore(np.array(pp.image, dtype=np.uint8), w=codeformer_weight) diff --git a/scripts/postprocessing_create_flipped_copies.py b/scripts/postprocessing_create_flipped_copies.py new file mode 100644 index 00000000..3425571d --- /dev/null +++ b/scripts/postprocessing_create_flipped_copies.py @@ -0,0 +1,32 @@ +from PIL import ImageOps, Image + +from modules import scripts_postprocessing, ui_components +import gradio as gr + + +class ScriptPostprocessingCreateFlippedCopies(scripts_postprocessing.ScriptPostprocessing): + name = "Create flipped copies" + order = 4000 + + def ui(self): + with ui_components.InputAccordion(False, label="Create flipped copies") as enable: + with gr.Row(): + option = gr.CheckboxGroup(value=["Horizontal"], choices=["Horizontal", "Vertical", "Both"], show_label=False) + + return { + "enable": enable, + "option": option, + } + + def process(self, pp: scripts_postprocessing.PostprocessedImage, enable, option): + if not enable: + return + + if "Horizontal" in option: + pp.extra_images.append(ImageOps.mirror(pp.image)) + + if "Vertical" in option: + pp.extra_images.append(pp.image.transpose(Image.Transpose.FLIP_TOP_BOTTOM)) + + if "Both" in option: + pp.extra_images.append(pp.image.transpose(Image.Transpose.FLIP_TOP_BOTTOM).transpose(Image.Transpose.FLIP_LEFT_RIGHT)) diff --git a/scripts/postprocessing_focal_crop.py b/scripts/postprocessing_focal_crop.py new file mode 100644 index 00000000..d3baf298 --- /dev/null +++ b/scripts/postprocessing_focal_crop.py @@ -0,0 +1,54 @@ + +from modules import scripts_postprocessing, ui_components, errors +import gradio as gr + +from modules.textual_inversion import autocrop + + +class ScriptPostprocessingFocalCrop(scripts_postprocessing.ScriptPostprocessing): + name = "Auto focal point crop" + order = 4000 + + def ui(self): + with ui_components.InputAccordion(False, label="Auto focal point crop") as enable: + face_weight = gr.Slider(label='Focal point face weight', value=0.9, minimum=0.0, maximum=1.0, step=0.05, elem_id="postprocess_focal_crop_face_weight") + entropy_weight = gr.Slider(label='Focal point entropy weight', value=0.15, minimum=0.0, maximum=1.0, step=0.05, elem_id="postprocess_focal_crop_entropy_weight") + edges_weight = gr.Slider(label='Focal point edges weight', value=0.5, minimum=0.0, maximum=1.0, step=0.05, elem_id="postprocess_focal_crop_edges_weight") + debug = gr.Checkbox(label='Create debug image', elem_id="train_process_focal_crop_debug") + + return { + "enable": enable, + "face_weight": face_weight, + "entropy_weight": entropy_weight, + "edges_weight": edges_weight, + "debug": debug, + } + + def process(self, pp: scripts_postprocessing.PostprocessedImage, enable, face_weight, entropy_weight, edges_weight, debug): + if not enable: + return + + if not pp.shared.target_width or not pp.shared.target_height: + return + + dnn_model_path = None + try: + dnn_model_path = autocrop.download_and_cache_models() + except Exception: + errors.report("Unable to load face detection model for auto crop selection. Falling back to lower quality haar method.", exc_info=True) + + autocrop_settings = autocrop.Settings( + crop_width=pp.shared.target_width, + crop_height=pp.shared.target_height, + face_points_weight=face_weight, + entropy_points_weight=entropy_weight, + corner_points_weight=edges_weight, + annotate_image=debug, + dnn_model_path=dnn_model_path, + ) + + result, *others = autocrop.crop_image(pp.image, autocrop_settings) + + pp.image = result + pp.extra_images = [pp.create_copy(x, nametags=["focal-crop-debug"], disable_processing=True) for x in others] + diff --git a/scripts/postprocessing_gfpgan.py b/scripts/postprocessing_gfpgan.py index d854f3f7..6e756605 100644 --- a/scripts/postprocessing_gfpgan.py +++ b/scripts/postprocessing_gfpgan.py @@ -1,26 +1,25 @@ from PIL import Image import numpy as np -from modules import scripts_postprocessing, gfpgan_model +from modules import scripts_postprocessing, gfpgan_model, ui_components import gradio as gr -from modules.ui_components import FormRow - class ScriptPostprocessingGfpGan(scripts_postprocessing.ScriptPostprocessing): name = "GFPGAN" order = 2000 def ui(self): - with FormRow(): - gfpgan_visibility = gr.Slider(minimum=0.0, maximum=1.0, step=0.001, label="GFPGAN visibility", value=0, elem_id="extras_gfpgan_visibility") + with ui_components.InputAccordion(False, label="GFPGAN") as enable: + gfpgan_visibility = gr.Slider(minimum=0.0, maximum=1.0, step=0.001, label="Visibility", value=1.0, elem_id="extras_gfpgan_visibility") return { + "enable": enable, "gfpgan_visibility": gfpgan_visibility, } - def process(self, pp: scripts_postprocessing.PostprocessedImage, gfpgan_visibility): - if gfpgan_visibility == 0: + def process(self, pp: scripts_postprocessing.PostprocessedImage, enable, gfpgan_visibility): + if gfpgan_visibility == 0 or not enable: return restored_img = gfpgan_model.gfpgan_fix_faces(np.array(pp.image, dtype=np.uint8)) diff --git a/scripts/postprocessing_split_oversized.py b/scripts/postprocessing_split_oversized.py new file mode 100644 index 00000000..c4a03160 --- /dev/null +++ b/scripts/postprocessing_split_oversized.py @@ -0,0 +1,71 @@ +import math + +from modules import scripts_postprocessing, ui_components +import gradio as gr + + +def split_pic(image, inverse_xy, width, height, overlap_ratio): + if inverse_xy: + from_w, from_h = image.height, image.width + to_w, to_h = height, width + else: + from_w, from_h = image.width, image.height + to_w, to_h = width, height + h = from_h * to_w // from_w + if inverse_xy: + image = image.resize((h, to_w)) + else: + image = image.resize((to_w, h)) + + split_count = math.ceil((h - to_h * overlap_ratio) / (to_h * (1.0 - overlap_ratio))) + y_step = (h - to_h) / (split_count - 1) + for i in range(split_count): + y = int(y_step * i) + if inverse_xy: + splitted = image.crop((y, 0, y + to_h, to_w)) + else: + splitted = image.crop((0, y, to_w, y + to_h)) + yield splitted + + +class ScriptPostprocessingSplitOversized(scripts_postprocessing.ScriptPostprocessing): + name = "Split oversized images" + order = 4000 + + def ui(self): + with ui_components.InputAccordion(False, label="Split oversized images") as enable: + with gr.Row(): + split_threshold = gr.Slider(label='Threshold', value=0.5, minimum=0.0, maximum=1.0, step=0.05, elem_id="postprocess_split_threshold") + overlap_ratio = gr.Slider(label='Overlap ratio', value=0.2, minimum=0.0, maximum=0.9, step=0.05, elem_id="postprocess_overlap_ratio") + + return { + "enable": enable, + "split_threshold": split_threshold, + "overlap_ratio": overlap_ratio, + } + + def process(self, pp: scripts_postprocessing.PostprocessedImage, enable, split_threshold, overlap_ratio): + if not enable: + return + + width = pp.shared.target_width + height = pp.shared.target_height + + if not width or not height: + return + + if pp.image.height > pp.image.width: + ratio = (pp.image.width * height) / (pp.image.height * width) + inverse_xy = False + else: + ratio = (pp.image.height * width) / (pp.image.width * height) + inverse_xy = True + + if ratio >= 1.0 and ratio > split_threshold: + return + + result, *others = split_pic(pp.image, inverse_xy, width, height, overlap_ratio) + + pp.image = result + pp.extra_images = [pp.create_copy(x) for x in others] + diff --git a/scripts/postprocessing_upscale.py b/scripts/postprocessing_upscale.py index eb42a29e..ed709688 100644 --- a/scripts/postprocessing_upscale.py +++ b/scripts/postprocessing_upscale.py @@ -81,6 +81,14 @@ class ScriptPostprocessingUpscale(scripts_postprocessing.ScriptPostprocessing): return image + def process_firstpass(self, pp: scripts_postprocessing.PostprocessedImage, upscale_mode=1, upscale_by=2.0, upscale_to_width=None, upscale_to_height=None, upscale_crop=False, upscaler_1_name=None, upscaler_2_name=None, upscaler_2_visibility=0.0): + if upscale_mode == 1: + pp.shared.target_width = upscale_to_width + pp.shared.target_height = upscale_to_height + else: + pp.shared.target_width = int(pp.image.width * upscale_by) + pp.shared.target_height = int(pp.image.height * upscale_by) + def process(self, pp: scripts_postprocessing.PostprocessedImage, upscale_mode=1, upscale_by=2.0, upscale_to_width=None, upscale_to_height=None, upscale_crop=False, upscaler_1_name=None, upscaler_2_name=None, upscaler_2_visibility=0.0): if upscaler_1_name == "None": upscaler_1_name = None @@ -126,6 +134,10 @@ class ScriptPostprocessingUpscaleSimple(ScriptPostprocessingUpscale): "upscaler_name": upscaler_name, } + def process_firstpass(self, pp: scripts_postprocessing.PostprocessedImage, upscale_by=2.0, upscaler_name=None): + pp.shared.target_width = int(pp.image.width * upscale_by) + pp.shared.target_height = int(pp.image.height * upscale_by) + def process(self, pp: scripts_postprocessing.PostprocessedImage, upscale_by=2.0, upscaler_name=None): if upscaler_name is None or upscaler_name == "None": return diff --git a/scripts/processing_autosized_crop.py b/scripts/processing_autosized_crop.py new file mode 100644 index 00000000..c0980226 --- /dev/null +++ b/scripts/processing_autosized_crop.py @@ -0,0 +1,64 @@ +from PIL import Image + +from modules import scripts_postprocessing, ui_components +import gradio as gr + + +def center_crop(image: Image, w: int, h: int): + iw, ih = image.size + if ih / h < iw / w: + sw = w * ih / h + box = (iw - sw) / 2, 0, iw - (iw - sw) / 2, ih + else: + sh = h * iw / w + box = 0, (ih - sh) / 2, iw, ih - (ih - sh) / 2 + return image.resize((w, h), Image.Resampling.LANCZOS, box) + + +def multicrop_pic(image: Image, mindim, maxdim, minarea, maxarea, objective, threshold): + iw, ih = image.size + err = lambda w, h: 1 - (lambda x: x if x < 1 else 1 / x)(iw / ih / (w / h)) + wh = max(((w, h) for w in range(mindim, maxdim + 1, 64) for h in range(mindim, maxdim + 1, 64) + if minarea <= w * h <= maxarea and err(w, h) <= threshold), + key=lambda wh: (wh[0] * wh[1], -err(*wh))[::1 if objective == 'Maximize area' else -1], + default=None + ) + return wh and center_crop(image, *wh) + + +class ScriptPostprocessingAutosizedCrop(scripts_postprocessing.ScriptPostprocessing): + name = "Auto-sized crop" + order = 4000 + + def ui(self): + with ui_components.InputAccordion(False, label="Auto-sized crop") as enable: + gr.Markdown('Each image is center-cropped with an automatically chosen width and height.') + with gr.Row(): + mindim = gr.Slider(minimum=64, maximum=2048, step=8, label="Dimension lower bound", value=384, elem_id="postprocess_multicrop_mindim") + maxdim = gr.Slider(minimum=64, maximum=2048, step=8, label="Dimension upper bound", value=768, elem_id="postprocess_multicrop_maxdim") + with gr.Row(): + minarea = gr.Slider(minimum=64 * 64, maximum=2048 * 2048, step=1, label="Area lower bound", value=64 * 64, elem_id="postprocess_multicrop_minarea") + maxarea = gr.Slider(minimum=64 * 64, maximum=2048 * 2048, step=1, label="Area upper bound", value=640 * 640, elem_id="postprocess_multicrop_maxarea") + with gr.Row(): + objective = gr.Radio(["Maximize area", "Minimize error"], value="Maximize area", label="Resizing objective", elem_id="postprocess_multicrop_objective") + threshold = gr.Slider(minimum=0, maximum=1, step=0.01, label="Error threshold", value=0.1, elem_id="postprocess_multicrop_threshold") + + return { + "enable": enable, + "mindim": mindim, + "maxdim": maxdim, + "minarea": minarea, + "maxarea": maxarea, + "objective": objective, + "threshold": threshold, + } + + def process(self, pp: scripts_postprocessing.PostprocessedImage, enable, mindim, maxdim, minarea, maxarea, objective, threshold): + if not enable: + return + + cropped = multicrop_pic(pp.image, mindim, maxdim, minarea, maxarea, objective, threshold) + if cropped is not None: + pp.image = cropped + else: + print(f"skipped {pp.image.width}x{pp.image.height} image (can't find suitable size within error threshold)") -- cgit v1.2.3