Löschen sie App.py

.gitignore

@@ -1,207 +0,0 @@
-# Byte-compiled / optimized / DLL files
-__pycache__/
-*.py[codz]
-*$py.class
-
-# C extensions
-*.so
-
-# Distribution / packaging
-.Python
-build/
-develop-eggs/
-dist/
-downloads/
-eggs/
-.eggs/
-lib/
-lib64/
-parts/
-sdist/
-var/
-wheels/
-share/python-wheels/
-*.egg-info/
-.installed.cfg
-*.egg
-MANIFEST
-
-# PyInstaller
-#  Usually these files are written by a python script from a template
-#  before PyInstaller builds the exe, so as to inject date/other infos into it.
-*.manifest
-*.spec
-
-# Installer logs
-pip-log.txt
-pip-delete-this-directory.txt
-
-# Unit test / coverage reports
-htmlcov/
-.tox/
-.nox/
-.coverage
-.coverage.*
-.cache
-nosetests.xml
-coverage.xml
-*.cover
-*.py.cover
-.hypothesis/
-.pytest_cache/
-cover/
-
-# Translations
-*.mo
-*.pot
-
-# Django stuff:
-*.log
-local_settings.py
-db.sqlite3
-db.sqlite3-journal
-
-# Flask stuff:
-instance/
-.webassets-cache
-
-# Scrapy stuff:
-.scrapy
-
-# Sphinx documentation
-docs/_build/
-
-# PyBuilder
-.pybuilder/
-target/
-
-# Jupyter Notebook
-.ipynb_checkpoints
-
-# IPython
-profile_default/
-ipython_config.py
-
-# pyenv
-#   For a library or package, you might want to ignore these files since the code is
-#   intended to run in multiple environments; otherwise, check them in:
-# .python-version
-
-# pipenv
-#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
-#   However, in case of collaboration, if having platform-specific dependencies or dependencies
-#   having no cross-platform support, pipenv may install dependencies that don't work, or not
-#   install all needed dependencies.
-#Pipfile.lock
-
-# UV
-#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
-#   This is especially recommended for binary packages to ensure reproducibility, and is more
-#   commonly ignored for libraries.
-#uv.lock
-
-# poetry
-#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
-#   This is especially recommended for binary packages to ensure reproducibility, and is more
-#   commonly ignored for libraries.
-#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
-#poetry.lock
-#poetry.toml
-
-# pdm
-#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
-#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
-#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
-#pdm.lock
-#pdm.toml
-.pdm-python
-.pdm-build/
-
-# pixi
-#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
-#pixi.lock
-#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
-#   in the .venv directory. It is recommended not to include this directory in version control.
-.pixi
-
-# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
-__pypackages__/
-
-# Celery stuff
-celerybeat-schedule
-celerybeat.pid
-
-# SageMath parsed files
-*.sage.py
-
-# Environments
-.env
-.envrc
-.venv
-env/
-venv/
-ENV/
-env.bak/
-venv.bak/
-
-# Spyder project settings
-.spyderproject
-.spyproject
-
-# Rope project settings
-.ropeproject
-
-# mkdocs documentation
-/site
-
-# mypy
-.mypy_cache/
-.dmypy.json
-dmypy.json
-
-# Pyre type checker
-.pyre/
-
-# pytype static type analyzer
-.pytype/
-
-# Cython debug symbols
-cython_debug/
-
-# PyCharm
-#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
-#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
-#  and can be added to the global gitignore or merged into this file.  For a more nuclear
-#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
-#.idea/
-
-# Abstra
-# Abstra is an AI-powered process automation framework.
-# Ignore directories containing user credentials, local state, and settings.
-# Learn more at https://abstra.io/docs
-.abstra/
-
-# Visual Studio Code
-#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
-#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
-#  and can be added to the global gitignore or merged into this file. However, if you prefer, 
-#  you could uncomment the following to ignore the entire vscode folder
-# .vscode/
-
-# Ruff stuff:
-.ruff_cache/
-
-# PyPI configuration file
-.pypirc
-
-# Cursor
-#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
-#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
-#  refer to https://docs.cursor.com/context/ignore-files
-.cursorignore
-.cursorindexingignore
-
-# Marimo
-marimo/_static/
-marimo/_lsp/
-__marimo__/

README.md

@@ -4,13 +4,11 @@ emoji: 🧩🖼️
 colorFrom: red
 colorTo: pink
 sdk: gradio
-sdk_version: 5.44.1
+sdk_version: 4.31.3
 app_file: app.py
 pinned: true
 license: mit
 short_description: Stunning images using stable diffusion.
-preload_from_hub:
-  - madebyollin/sdxl-vae-fp16-fix config.json,diffusion_pytorch_model.safetensors
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -1,1506 +0,0 @@
-import spaces
-import os
-from argparse import ArgumentParser
-from stablepy import (
-    Model_Diffusers,
-    SCHEDULE_TYPE_OPTIONS,
-    SCHEDULE_PREDICTION_TYPE_OPTIONS,
-    check_scheduler_compatibility,
-    TASK_AND_PREPROCESSORS,
-    FACE_RESTORATION_MODELS,
-    scheduler_names,
-)
-from constants import (
-    DIRECTORY_MODELS,
-    DIRECTORY_LORAS,
-    DIRECTORY_VAES,
-    DIRECTORY_EMBEDS,
-    DIRECTORY_UPSCALERS,
-    DOWNLOAD_MODEL,
-    DOWNLOAD_VAE,
-    DOWNLOAD_LORA,
-    LOAD_DIFFUSERS_FORMAT_MODEL,
-    DIFFUSERS_FORMAT_LORAS,
-    DOWNLOAD_EMBEDS,
-    CIVITAI_API_KEY,
-    HF_TOKEN,
-    TASK_STABLEPY,
-    TASK_MODEL_LIST,
-    UPSCALER_DICT_GUI,
-    UPSCALER_KEYS,
-    PROMPT_W_OPTIONS,
-    WARNING_MSG_VAE,
-    SDXL_TASK,
-    MODEL_TYPE_TASK,
-    POST_PROCESSING_SAMPLER,
-    SUBTITLE_GUI,
-    HELP_GUI,
-    EXAMPLES_GUI_HELP,
-    EXAMPLES_GUI,
-    RESOURCES,
-    DIFFUSERS_CONTROLNET_MODEL,
-    IP_MODELS,
-    MODE_IP_OPTIONS,
-    CACHE_HF_ROOT,
-    CACHE_HF,
-)
-from stablepy.diffusers_vanilla.style_prompt_config import STYLE_NAMES
-import torch
-import re
-import time
-from PIL import ImageFile
-from utils import (
-    download_things,
-    get_model_list,
-    extract_parameters,
-    get_my_lora,
-    get_model_type,
-    extract_exif_data,
-    create_mask_now,
-    download_diffuser_repo,
-    get_used_storage_gb,
-    delete_model,
-    progress_step_bar,
-    html_template_message,
-    escape_html,
-    clear_hf_cache,
-)
-from image_processor import preprocessor_tab
-from datetime import datetime
-import gradio as gr
-import logging
-import diffusers
-import warnings
-from stablepy import logger
-from diffusers import FluxPipeline
-# import urllib.parse
-import subprocess
-
-IS_ZERO_GPU = bool(os.getenv("SPACES_ZERO_GPU"))
-HIDE_API = bool(os.getenv("HIDE_API"))
-if IS_ZERO_GPU:
-    subprocess.run("rm -rf /data-nvme/zerogpu-offload/*", env={}, shell=True)
-IS_GPU_MODE = True if IS_ZERO_GPU else (True if torch.cuda.is_available() else False)
-img_path = "./images/"
-allowed_path = os.path.abspath(img_path)
-delete_cache_time = (9600, 9600) if IS_ZERO_GPU else (86400, 86400)
-
-ImageFile.LOAD_TRUNCATED_IMAGES = True
-torch.backends.cuda.matmul.allow_tf32 = True
-# os.environ["PYTORCH_NO_CUDA_MEMORY_CACHING"] = "1"
-
-directories = [DIRECTORY_MODELS, DIRECTORY_LORAS, DIRECTORY_VAES, DIRECTORY_EMBEDS, DIRECTORY_UPSCALERS]
-for directory in directories:
-    os.makedirs(directory, exist_ok=True)
-
-# Download stuffs
-for url in [url.strip() for url in DOWNLOAD_MODEL.split(',')]:
-    download_things(DIRECTORY_MODELS, url, HF_TOKEN, CIVITAI_API_KEY)
-for url in [url.strip() for url in DOWNLOAD_VAE.split(',')]:
-    download_things(DIRECTORY_VAES, url, HF_TOKEN, CIVITAI_API_KEY)
-for url in [url.strip() for url in DOWNLOAD_LORA.split(',')]:
-    download_things(DIRECTORY_LORAS, url, HF_TOKEN, CIVITAI_API_KEY)
-
-# Download Embeddings
-for url_embed in DOWNLOAD_EMBEDS:
-    download_things(DIRECTORY_EMBEDS, url_embed, HF_TOKEN, CIVITAI_API_KEY)
-
-# Build list models
-embed_list = get_model_list(DIRECTORY_EMBEDS)
-embed_list = [
-    (os.path.splitext(os.path.basename(emb))[0], emb) for emb in embed_list
-]
-single_file_model_list = get_model_list(DIRECTORY_MODELS)
-model_list = LOAD_DIFFUSERS_FORMAT_MODEL + single_file_model_list
-lora_model_list = get_model_list(DIRECTORY_LORAS)
-lora_model_list.insert(0, "None")
-lora_model_list = lora_model_list + DIFFUSERS_FORMAT_LORAS
-vae_model_list = get_model_list(DIRECTORY_VAES)
-vae_model_list.insert(0, "BakedVAE")
-vae_model_list.insert(0, "None")
-
-print('\033[33m🏁 Download and listing of valid models completed.\033[0m')
-
-components = None
-if IS_ZERO_GPU:
-    flux_repo = "camenduru/FLUX.1-dev-diffusers"
-    flux_pipe = FluxPipeline.from_pretrained(
-        flux_repo,
-        transformer=None,
-        torch_dtype=torch.bfloat16,
-    ).to("cuda")
-    components = flux_pipe.components
-    delete_model(flux_repo)
-
-#######################
-# GUI
-#######################
-logging.getLogger("diffusers").setLevel(logging.ERROR)
-diffusers.utils.logging.set_verbosity(40)
-warnings.filterwarnings(action="ignore", category=FutureWarning, module="diffusers")
-warnings.filterwarnings(action="ignore", category=UserWarning, module="diffusers")
-warnings.filterwarnings(action="ignore", category=FutureWarning, module="transformers")
-
-parser = ArgumentParser(description='DiffuseCraft: Create images from text prompts.', add_help=True)
-parser.add_argument("--share", action="store_true", dest="share_enabled", default=False, help="Enable sharing")
-parser.add_argument('--theme', type=str, default="NoCrypt/miku", help='Set the theme (default: NoCrypt/miku)')
-parser.add_argument("--ssr", action="store_true", help="Enable SSR (Server-Side Rendering)")
-parser.add_argument("--log-level", type=str, default="INFO", choices=["DEBUG", "INFO", "WARNING", "ERROR", "CRITICAL"], help="Set logging level (default: INFO)")
-args = parser.parse_args()
-
-logger.setLevel(
-    "INFO" if IS_ZERO_GPU else getattr(logging, args.log_level.upper())
-)
-
-CSS = """
-.contain { display: flex; flex-direction: column; }
-#component-0 { height: 100%; }
-#gallery { flex-grow: 1; }
-#load_model { height: 50px; }
-"""
-
-
-def lora_chk(lora_):
-    if isinstance(lora_, str) and lora_.strip() not in ["", "None"]:
-        return lora_
-    return None
-
-
-class GuiSD:
-    def __init__(self, stream=True):
-        self.model = None
-        self.status_loading = False
-        self.sleep_loading = 4
-        self.last_load = datetime.now()
-        self.inventory = []
-
-    def update_storage_models(self, storage_floor_gb=30, required_inventory_for_purge=3):
-        while get_used_storage_gb() > storage_floor_gb:
-            if len(self.inventory) < required_inventory_for_purge:
-                break
-            removal_candidate = self.inventory.pop(0)
-            delete_model(removal_candidate)
-
-        # Cleanup after 60 seconds of inactivity
-        lowPrioCleanup = max((datetime.now() - self.last_load).total_seconds(), 0) > 60
-        if lowPrioCleanup and (len(self.inventory) >= required_inventory_for_purge - 1) and not self.status_loading and get_used_storage_gb(CACHE_HF_ROOT) > (storage_floor_gb * 2):
-            print("Cleaning up Hugging Face cache...")
-            clear_hf_cache()
-            self.inventory = [
-                m for m in self.inventory if os.path.exists(m)
-            ]
-
-    def update_inventory(self, model_name):
-        if model_name not in single_file_model_list:
-            self.inventory = [
-                m for m in self.inventory if m != model_name
-            ] + [model_name]
-        print(self.inventory)
-
-    def load_new_model(self, model_name, vae_model, task, controlnet_model, progress=gr.Progress(track_tqdm=True)):
-
-        # download link model > model_name
-        if model_name.startswith("http"):
-            yield f"Downloading model: {model_name}"
-            model_name = download_things(DIRECTORY_MODELS, model_name, HF_TOKEN, CIVITAI_API_KEY)
-            if not model_name:
-                raise ValueError("Error retrieving model information from URL")
-
-        if IS_ZERO_GPU:
-            self.update_storage_models()
-
-        vae_model = vae_model if vae_model != "None" else None
-        model_type = get_model_type(model_name)
-        dtype_model = torch.bfloat16 if model_type == "FLUX" else torch.float16
-
-        if not os.path.exists(model_name):
-            logger.debug(f"model_name={model_name}, vae_model={vae_model}, task={task}, controlnet_model={controlnet_model}")
-            _ = download_diffuser_repo(
-                repo_name=model_name,
-                model_type=model_type,
-                revision="main",
-                token=True,
-            )
-
-        self.update_inventory(model_name)
-
-        for i in range(68):
-            if not self.status_loading:
-                self.status_loading = True
-                if i > 0:
-                    time.sleep(self.sleep_loading)
-                    print("Previous model ops...")
-                break
-            time.sleep(0.5)
-            print(f"Waiting queue {i}")
-            yield "Waiting queue"
-
-        self.status_loading = True
-
-        yield f"Loading model: {model_name}"
-
-        if vae_model == "BakedVAE":
-            vae_model = model_name
-        elif vae_model:
-            vae_type = "SDXL" if "sdxl" in vae_model.lower() else "SD 1.5"
-            if model_type != vae_type:
-                gr.Warning(WARNING_MSG_VAE)
-
-        print("Loading model...")
-
-        try:
-            start_time = time.time()
-
-            if self.model is None:
-                self.model = Model_Diffusers(
-                    base_model_id=model_name,
-                    task_name=TASK_STABLEPY[task],
-                    vae_model=vae_model,
-                    type_model_precision=dtype_model,
-                    retain_task_model_in_cache=False,
-                    controlnet_model=controlnet_model,
-                    device="cpu" if IS_ZERO_GPU else None,
-                    env_components=components,
-                )
-                self.model.advanced_params(image_preprocessor_cuda_active=IS_GPU_MODE)
-            else:
-                if self.model.base_model_id != model_name:
-                    load_now_time = datetime.now()
-                    elapsed_time = max((load_now_time - self.last_load).total_seconds(), 0)
-
-                    if elapsed_time <= 9:
-                        print("Waiting for the previous model's time ops...")
-                        time.sleep(9 - elapsed_time)
-
-                if IS_ZERO_GPU:
-                    self.model.device = torch.device("cpu")
-                self.model.load_pipe(
-                    model_name,
-                    task_name=TASK_STABLEPY[task],
-                    vae_model=vae_model,
-                    type_model_precision=dtype_model,
-                    retain_task_model_in_cache=False,
-                    controlnet_model=controlnet_model,
-                )
-
-            end_time = time.time()
-            self.sleep_loading = max(min(int(end_time - start_time), 10), 4)
-        except Exception as e:
-            self.last_load = datetime.now()
-            self.status_loading = False
-            self.sleep_loading = 4
-            raise e
-
-        self.last_load = datetime.now()
-        self.status_loading = False
-
-        yield f"Model loaded: {model_name}"
-
-    # @spaces.GPU(duration=59)
-    @torch.inference_mode()
-    def generate_pipeline(
-        self,
-        prompt,
-        neg_prompt,
-        num_images,
-        steps,
-        cfg,
-        clip_skip,
-        seed,
-        lora1,
-        lora_scale1,
-        lora2,
-        lora_scale2,
-        lora3,
-        lora_scale3,
-        lora4,
-        lora_scale4,
-        lora5,
-        lora_scale5,
-        lora6,
-        lora_scale6,
-        lora7,
-        lora_scale7,
-        sampler,
-        schedule_type,
-        schedule_prediction_type,
-        img_height,
-        img_width,
-        model_name,
-        vae_model,
-        task,
-        image_control,
-        preprocessor_name,
-        preprocess_resolution,
-        image_resolution,
-        style_prompt,  # list []
-        style_json_file,
-        image_mask,
-        strength,
-        low_threshold,
-        high_threshold,
-        value_threshold,
-        distance_threshold,
-        recolor_gamma_correction,
-        tile_blur_sigma,
-        controlnet_output_scaling_in_unet,
-        controlnet_start_threshold,
-        controlnet_stop_threshold,
-        textual_inversion,
-        syntax_weights,
-        upscaler_model_path,
-        upscaler_increases_size,
-        upscaler_tile_size,
-        upscaler_tile_overlap,
-        hires_steps,
-        hires_denoising_strength,
-        hires_sampler,
-        hires_prompt,
-        hires_negative_prompt,
-        hires_before_adetailer,
-        hires_after_adetailer,
-        hires_schedule_type,
-        hires_guidance_scale,
-        controlnet_model,
-        loop_generation,
-        leave_progress_bar,
-        disable_progress_bar,
-        image_previews,
-        display_images,
-        save_generated_images,
-        filename_pattern,
-        image_storage_location,
-        retain_compel_previous_load,
-        retain_detailfix_model_previous_load,
-        retain_hires_model_previous_load,
-        t2i_adapter_preprocessor,
-        t2i_adapter_conditioning_scale,
-        t2i_adapter_conditioning_factor,
-        xformers_memory_efficient_attention,
-        freeu,
-        generator_in_cpu,
-        adetailer_inpaint_only,
-        adetailer_verbose,
-        adetailer_sampler,
-        adetailer_active_a,
-        prompt_ad_a,
-        negative_prompt_ad_a,
-        strength_ad_a,
-        face_detector_ad_a,
-        person_detector_ad_a,
-        hand_detector_ad_a,
-        mask_dilation_a,
-        mask_blur_a,
-        mask_padding_a,
-        adetailer_active_b,
-        prompt_ad_b,
-        negative_prompt_ad_b,
-        strength_ad_b,
-        face_detector_ad_b,
-        person_detector_ad_b,
-        hand_detector_ad_b,
-        mask_dilation_b,
-        mask_blur_b,
-        mask_padding_b,
-        retain_task_cache_gui,
-        guidance_rescale,
-        image_ip1,
-        mask_ip1,
-        model_ip1,
-        mode_ip1,
-        scale_ip1,
-        image_ip2,
-        mask_ip2,
-        model_ip2,
-        mode_ip2,
-        scale_ip2,
-        pag_scale,
-        face_restoration_model,
-        face_restoration_visibility,
-        face_restoration_weight,
-    ):
-        info_state = html_template_message("Navigating latent space...")
-        yield info_state, gr.update(), gr.update()
-
-        vae_model = vae_model if vae_model != "None" else None
-        loras_list = [lora1, lora2, lora3, lora4, lora5, lora6, lora7]
-        vae_msg = f"VAE: {vae_model}" if vae_model else ""
-        msg_lora = ""
-
-        logger.debug(f"Config model: {model_name}, {vae_model}, {loras_list}")
-
-        task = TASK_STABLEPY[task]
-
-        params_ip_img = []
-        params_ip_msk = []
-        params_ip_model = []
-        params_ip_mode = []
-        params_ip_scale = []
-
-        all_adapters = [
-            (image_ip1, mask_ip1, model_ip1, mode_ip1, scale_ip1),
-            (image_ip2, mask_ip2, model_ip2, mode_ip2, scale_ip2),
-        ]
-
-        if not hasattr(self.model.pipe, "transformer"):
-            for imgip, mskip, modelip, modeip, scaleip in all_adapters:
-                if imgip:
-                    params_ip_img.append(imgip)
-                    if mskip:
-                        params_ip_msk.append(mskip)
-                    params_ip_model.append(modelip)
-                    params_ip_mode.append(modeip)
-                    params_ip_scale.append(scaleip)
-
-        concurrency = 5
-        self.model.stream_config(concurrency=concurrency, latent_resize_by=1, vae_decoding=False)
-
-        if task != "txt2img" and not image_control:
-            raise ValueError("Reference image is required. Please upload one in 'Image ControlNet/Inpaint/Img2img'.")
-
-        if task in ["inpaint", "repaint"] and not image_mask:
-            raise ValueError("Mask image not found. Upload one in 'Image Mask' to proceed.")
-
-        if "https://" not in str(UPSCALER_DICT_GUI[upscaler_model_path]):
-            upscaler_model = upscaler_model_path
-        else:
-            url_upscaler = UPSCALER_DICT_GUI[upscaler_model_path]
-
-            if not os.path.exists(f"./{DIRECTORY_UPSCALERS}/{url_upscaler.split('/')[-1]}"):
-                download_things(DIRECTORY_UPSCALERS, url_upscaler, HF_TOKEN)
-
-            upscaler_model = f"./{DIRECTORY_UPSCALERS}/{url_upscaler.split('/')[-1]}"
-
-        logging.getLogger("ultralytics").setLevel(logging.INFO if adetailer_verbose else logging.ERROR)
-
-        adetailer_params_A = {
-            "face_detector_ad": face_detector_ad_a,
-            "person_detector_ad": person_detector_ad_a,
-            "hand_detector_ad": hand_detector_ad_a,
-            "prompt": prompt_ad_a,
-            "negative_prompt": negative_prompt_ad_a,
-            "strength": strength_ad_a,
-            # "image_list_task" : None,
-            "mask_dilation": mask_dilation_a,
-            "mask_blur": mask_blur_a,
-            "mask_padding": mask_padding_a,
-            "inpaint_only": adetailer_inpaint_only,
-            "sampler": adetailer_sampler,
-        }
-
-        adetailer_params_B = {
-            "face_detector_ad": face_detector_ad_b,
-            "person_detector_ad": person_detector_ad_b,
-            "hand_detector_ad": hand_detector_ad_b,
-            "prompt": prompt_ad_b,
-            "negative_prompt": negative_prompt_ad_b,
-            "strength": strength_ad_b,
-            # "image_list_task" : None,
-            "mask_dilation": mask_dilation_b,
-            "mask_blur": mask_blur_b,
-            "mask_padding": mask_padding_b,
-        }
-        pipe_params = {
-            "prompt": prompt,
-            "negative_prompt": neg_prompt,
-            "img_height": img_height,
-            "img_width": img_width,
-            "num_images": num_images,
-            "num_steps": steps,
-            "guidance_scale": cfg,
-            "clip_skip": clip_skip,
-            "pag_scale": float(pag_scale),
-            "seed": seed,
-            "image": image_control,
-            "preprocessor_name": preprocessor_name,
-            "preprocess_resolution": preprocess_resolution,
-            "image_resolution": image_resolution,
-            "style_prompt": style_prompt if style_prompt else "",
-            "style_json_file": "",
-            "image_mask": image_mask,  # only for Inpaint
-            "strength": strength,  # only for Inpaint or ...
-            "low_threshold": low_threshold,
-            "high_threshold": high_threshold,
-            "value_threshold": value_threshold,
-            "distance_threshold": distance_threshold,
-            "recolor_gamma_correction": float(recolor_gamma_correction),
-            "tile_blur_sigma": int(tile_blur_sigma),
-            "lora_A": lora_chk(lora1),
-            "lora_scale_A": lora_scale1,
-            "lora_B": lora_chk(lora2),
-            "lora_scale_B": lora_scale2,
-            "lora_C": lora_chk(lora3),
-            "lora_scale_C": lora_scale3,
-            "lora_D": lora_chk(lora4),
-            "lora_scale_D": lora_scale4,
-            "lora_E": lora_chk(lora5),
-            "lora_scale_E": lora_scale5,
-            "lora_F": lora_chk(lora6),
-            "lora_scale_F": lora_scale6,
-            "lora_G": lora_chk(lora7),
-            "lora_scale_G": lora_scale7,
-            "textual_inversion": embed_list if textual_inversion else [],
-            "syntax_weights": syntax_weights,  # "Classic"
-            "sampler": sampler,
-            "schedule_type": schedule_type,
-            "schedule_prediction_type": schedule_prediction_type,
-            "xformers_memory_efficient_attention": xformers_memory_efficient_attention,
-            "gui_active": True,
-            "loop_generation": loop_generation,
-            "controlnet_conditioning_scale": float(controlnet_output_scaling_in_unet),
-            "control_guidance_start": float(controlnet_start_threshold),
-            "control_guidance_end": float(controlnet_stop_threshold),
-            "generator_in_cpu": generator_in_cpu,
-            "FreeU": freeu,
-            "adetailer_A": adetailer_active_a,
-            "adetailer_A_params": adetailer_params_A,
-            "adetailer_B": adetailer_active_b,
-            "adetailer_B_params": adetailer_params_B,
-            "leave_progress_bar": leave_progress_bar,
-            "disable_progress_bar": disable_progress_bar,
-            "image_previews": image_previews,
-            "display_images": display_images,
-            "save_generated_images": save_generated_images,
-            "filename_pattern": filename_pattern,
-            "image_storage_location": image_storage_location,
-            "retain_compel_previous_load": retain_compel_previous_load,
-            "retain_detailfix_model_previous_load": retain_detailfix_model_previous_load,
-            "retain_hires_model_previous_load": retain_hires_model_previous_load,
-            "t2i_adapter_preprocessor": t2i_adapter_preprocessor,
-            "t2i_adapter_conditioning_scale": float(t2i_adapter_conditioning_scale),
-            "t2i_adapter_conditioning_factor": float(t2i_adapter_conditioning_factor),
-            "upscaler_model_path": upscaler_model,
-            "upscaler_increases_size": upscaler_increases_size,
-            "upscaler_tile_size": upscaler_tile_size,
-            "upscaler_tile_overlap": upscaler_tile_overlap,
-            "hires_steps": hires_steps,
-            "hires_denoising_strength": hires_denoising_strength,
-            "hires_prompt": hires_prompt,
-            "hires_negative_prompt": hires_negative_prompt,
-            "hires_sampler": hires_sampler,
-            "hires_before_adetailer": hires_before_adetailer,
-            "hires_after_adetailer": hires_after_adetailer,
-            "hires_schedule_type": hires_schedule_type,
-            "hires_guidance_scale": hires_guidance_scale,
-            "ip_adapter_image": params_ip_img,
-            "ip_adapter_mask": params_ip_msk,
-            "ip_adapter_model": params_ip_model,
-            "ip_adapter_mode": params_ip_mode,
-            "ip_adapter_scale": params_ip_scale,
-            "face_restoration_model": face_restoration_model,
-            "face_restoration_visibility": face_restoration_visibility,
-            "face_restoration_weight": face_restoration_weight,
-        }
-
-        # kwargs for diffusers pipeline
-        if guidance_rescale:
-            pipe_params["guidance_rescale"] = guidance_rescale
-        if IS_ZERO_GPU:
-            self.model.device = torch.device("cuda:0")
-            if hasattr(self.model.pipe, "transformer") and loras_list != ["None"] * self.model.num_loras:
-                self.model.pipe.transformer.to(self.model.device)
-                logger.debug("transformer to cuda")
-
-        actual_progress = 0
-        info_images = gr.update()
-        for img, [seed, image_path, metadata] in self.model(**pipe_params):
-            info_state = progress_step_bar(actual_progress, steps)
-            actual_progress += concurrency
-            if image_path:
-                info_images = f"Seeds: {str(seed)}"
-                if vae_msg:
-                    info_images = info_images + "<br>" + vae_msg
-
-                if "Cannot copy out of meta tensor; no data!" in self.model.last_lora_error:
-                    msg_ram = "Unable to process the LoRAs due to high RAM usage; please try again later."
-                    print(msg_ram)
-                    msg_lora += f"<br>{msg_ram}"
-
-                for status, lora in zip(self.model.lora_status, self.model.lora_memory):
-                    if status:
-                        msg_lora += f"<br>Loaded: {lora}"
-                    elif status is not None:
-                        msg_lora += f"<br>Error with: {lora}"
-
-                if msg_lora:
-                    info_images += msg_lora
-
-                info_images = info_images + "<br>" + "GENERATION DATA:<br>" + escape_html(metadata[-1]) + "<br>-------<br>"
-
-                download_links = "<br>".join(
-                    [
-                        f'<a href="{path.replace("/images/", f"/gradio_api/file={allowed_path}/")}" download="{os.path.basename(path)}">Download Image {i + 1}</a>'
-                        for i, path in enumerate(image_path)
-                    ]
-                )
-                if save_generated_images:
-                    info_images += f"<br>{download_links}"
-
-                info_state = "COMPLETE"
-
-            yield info_state, img, info_images
-
-
-def dynamic_gpu_duration(func, duration, *args):
-
-    # @torch.inference_mode()
-    @spaces.GPU(duration=duration)
-    def wrapped_func():
-        yield from func(*args)
-
-    return wrapped_func()
-
-
-@spaces.GPU
-def dummy_gpu():
-    return None
-
-
-def sd_gen_generate_pipeline(*args):
-    gpu_duration_arg = int(args[-1]) if args[-1] else 59
-    verbose_arg = int(args[-2])
-    load_lora_cpu = args[-3]
-    generation_args = args[:-3]
-    lora_list = [
-        None if item == "None" else item
-        for item in [args[7], args[9], args[11], args[13], args[15], args[17], args[19]]
-    ]
-    lora_status = [None] * sd_gen.model.num_loras
-
-    msg_load_lora = "Updating LoRAs in GPU..."
-    if load_lora_cpu:
-        msg_load_lora = "Updating LoRAs in CPU..."
-
-    if lora_list != sd_gen.model.lora_memory and lora_list != [None] * sd_gen.model.num_loras:
-        yield msg_load_lora, gr.update(), gr.update()
-
-    # Load lora in CPU
-    if load_lora_cpu:
-        lora_status = sd_gen.model.load_lora_on_the_fly(
-            lora_A=lora_list[0], lora_scale_A=args[8],
-            lora_B=lora_list[1], lora_scale_B=args[10],
-            lora_C=lora_list[2], lora_scale_C=args[12],
-            lora_D=lora_list[3], lora_scale_D=args[14],
-            lora_E=lora_list[4], lora_scale_E=args[16],
-            lora_F=lora_list[5], lora_scale_F=args[18],
-            lora_G=lora_list[6], lora_scale_G=args[20],
-        )
-        print(lora_status)
-
-    sampler_name = args[21]
-    schedule_type_name = args[22]
-    _, _, msg_sampler = check_scheduler_compatibility(
-        sd_gen.model.class_name, sampler_name, schedule_type_name
-    )
-    if msg_sampler:
-        gr.Warning(msg_sampler)
-
-    if verbose_arg:
-        for status, lora in zip(lora_status, lora_list):
-            if status:
-                gr.Info(f"LoRA loaded in CPU: {lora}")
-            elif status is not None:
-                gr.Warning(f"Failed to load LoRA: {lora}")
-
-        if lora_status == [None] * sd_gen.model.num_loras and sd_gen.model.lora_memory != [None] * sd_gen.model.num_loras and load_lora_cpu:
-            lora_cache_msg = ", ".join(
-                str(x) for x in sd_gen.model.lora_memory if x is not None
-            )
-            gr.Info(f"LoRAs in cache: {lora_cache_msg}")
-
-    msg_request = f"Requesting {gpu_duration_arg}s. of GPU time.\nModel: {sd_gen.model.base_model_id}"
-    if verbose_arg:
-        gr.Info(msg_request)
-        print(msg_request)
-    yield msg_request.replace("\n", "<br>"), gr.update(), gr.update()
-
-    start_time = time.time()
-
-    # yield from sd_gen.generate_pipeline(*generation_args)
-    yield from dynamic_gpu_duration(
-        sd_gen.generate_pipeline,
-        gpu_duration_arg,
-        *generation_args,
-    )
-
-    end_time = time.time()
-    execution_time = end_time - start_time
-    msg_task_complete = (
-        f"GPU task complete in: {int(round(execution_time, 0) + 1)} seconds"
-    )
-
-    if verbose_arg:
-        gr.Info(msg_task_complete)
-        print(msg_task_complete)
-
-    yield msg_task_complete, gr.update(), gr.update()
-
-
-@spaces.GPU(duration=15)
-def process_upscale(image, upscaler_name, upscaler_size):
-    if image is None:
-        return None
-
-    from stablepy.diffusers_vanilla.utils import save_pil_image_with_metadata
-    from stablepy import load_upscaler_model
-
-    image = image.convert("RGB")
-    exif_image = extract_exif_data(image)
-
-    name_upscaler = UPSCALER_DICT_GUI[upscaler_name]
-
-    if "https://" in str(name_upscaler):
-
-        if not os.path.exists(f"./{DIRECTORY_UPSCALERS}/{name_upscaler.split('/')[-1]}"):
-            download_things(DIRECTORY_UPSCALERS, name_upscaler, HF_TOKEN)
-
-        name_upscaler = f"./{DIRECTORY_UPSCALERS}/{name_upscaler.split('/')[-1]}"
-
-    scaler_beta = load_upscaler_model(model=name_upscaler, tile=(0 if IS_ZERO_GPU else 192), tile_overlap=8, device=("cuda" if IS_GPU_MODE else "cpu"), half=IS_GPU_MODE)
-    image_up = scaler_beta.upscale(image, upscaler_size, True)
-
-    image_path = save_pil_image_with_metadata(image_up, f'{os.getcwd()}/up_images', exif_image)
-
-    return image_path
-
-
-# https://huggingface.co/spaces/BestWishYsh/ConsisID-preview-Space/discussions/1#674969a022b99c122af5d407
-# dynamic_gpu_duration.zerogpu = True
-# sd_gen_generate_pipeline.zerogpu = True
-sd_gen = GuiSD()
-
-with gr.Blocks(theme=args.theme, css=CSS, fill_width=True, fill_height=False) as app:
-    gr.Markdown("# 🧩 DiffuseCraft")
-    gr.Markdown(SUBTITLE_GUI)
-    with gr.Tab("Generation"):
-        with gr.Row():
-
-            with gr.Column(scale=2):
-
-                def update_task_options(model_name, task_name):
-                    new_choices = MODEL_TYPE_TASK[get_model_type(model_name)]
-
-                    if task_name not in new_choices:
-                        task_name = "txt2img"
-
-                    return gr.update(value=task_name, choices=new_choices)
-
-                task_gui = gr.Dropdown(label="Task", choices=SDXL_TASK, value=TASK_MODEL_LIST[0])
-                model_name_gui = gr.Dropdown(label="Model", choices=model_list, value=model_list[0], allow_custom_value=True)
-                prompt_gui = gr.Textbox(lines=5, placeholder="Enter prompt", label="Prompt")
-                neg_prompt_gui = gr.Textbox(lines=3, placeholder="Enter Neg prompt", label="Negative prompt", value="lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, worst quality, low quality, very displeasing, (bad)")
-                with gr.Row(equal_height=False):
-                    set_params_gui = gr.Button(value="↙️", variant="secondary", size="sm")
-                    clear_prompt_gui = gr.Button(value="🗑️", variant="secondary", size="sm")
-                    set_random_seed = gr.Button(value="🎲", variant="secondary", size="sm")
-                generate_button = gr.Button(value="GENERATE IMAGE", variant="primary")
-
-                model_name_gui.change(
-                    update_task_options,
-                    [model_name_gui, task_gui],
-                    [task_gui],
-                )
-
-                load_model_gui = gr.HTML(elem_id="load_model", elem_classes="contain")
-
-                result_images = gr.Gallery(
-                    label="Generated images",
-                    show_label=False,
-                    elem_id="gallery",
-                    columns=[2],
-                    rows=[2],
-                    object_fit="contain",
-                    # height="auto",
-                    interactive=False,
-                    preview=False,
-                    selected_index=50,
-                )
-
-                actual_task_info = gr.HTML()
-
-                with gr.Row(equal_height=False, variant="default", visible=IS_ZERO_GPU):
-                    gpu_duration_gui = gr.Number(minimum=5, maximum=240, value=59, show_label=False, container=False, info="GPU time duration (seconds)")
-                    with gr.Column():
-                        verbose_info_gui = gr.Checkbox(value=False, container=False, label="Status info")
-                        load_lora_cpu_gui = gr.Checkbox(value=False, container=False, label="Load LoRAs on CPU")
-
-            with gr.Column(scale=1):
-                steps_gui = gr.Slider(minimum=1, maximum=100, step=1, value=28, label="Steps")
-                cfg_gui = gr.Slider(minimum=0, maximum=30, step=0.5, value=7., label="CFG")
-                sampler_gui = gr.Dropdown(label="Sampler", choices=scheduler_names, value="Euler")
-                schedule_type_gui = gr.Dropdown(label="Schedule type", choices=SCHEDULE_TYPE_OPTIONS, value=SCHEDULE_TYPE_OPTIONS[0])
-                img_width_gui = gr.Slider(minimum=64, maximum=4096, step=8, value=1024, label="Img Width")
-                img_height_gui = gr.Slider(minimum=64, maximum=4096, step=8, value=1024, label="Img Height")
-                seed_gui = gr.Number(minimum=-1, maximum=9999999999, value=-1, label="Seed")
-                pag_scale_gui = gr.Slider(minimum=0.0, maximum=10.0, step=0.1, value=0.0, label="PAG Scale")
-                with gr.Row():
-                    clip_skip_gui = gr.Checkbox(value=True, label="Layer 2 Clip Skip")
-                    free_u_gui = gr.Checkbox(value=False, label="FreeU")
-
-                with gr.Row(equal_height=False):
-
-                    def run_set_params_gui(base_prompt, name_model):
-                        valid_receptors = {  # default values
-                            "prompt": gr.update(value=base_prompt),
-                            "neg_prompt": gr.update(value=""),
-                            "Steps": gr.update(value=30),
-                            "width": gr.update(value=1024),
-                            "height": gr.update(value=1024),
-                            "Seed": gr.update(value=-1),
-                            "Sampler": gr.update(value="Euler"),
-                            "CFG scale": gr.update(value=7.),  # cfg
-                            "Clip skip": gr.update(value=True),
-                            "Model": gr.update(value=name_model),
-                            "Schedule type": gr.update(value="Automatic"),
-                            "PAG": gr.update(value=.0),
-                            "FreeU": gr.update(value=False),
-                            "Hires upscaler": gr.update(),
-                            "Hires upscale": gr.update(),
-                            "Hires steps": gr.update(),
-                            "Hires denoising strength": gr.update(),
-                            "Hires CFG": gr.update(),
-                            "Hires sampler": gr.update(),
-                            "Hires schedule type": gr.update(),
-                            "Image resolution": gr.update(value=1024),
-                            "Strength": gr.update(),
-                        }
-
-                        # Generate up to 7 LoRAs
-                        for i in range(1, 8):
-                            valid_receptors[f"Lora_{i}"] = gr.update()
-                            valid_receptors[f"Lora_scale_{i}"] = gr.update()
-
-                        valid_keys = list(valid_receptors.keys())
-
-                        parameters = extract_parameters(base_prompt)
-                        # print(parameters)
-
-                        if "Sampler" in parameters:
-                            value_sampler = parameters["Sampler"]
-                            for s_type in SCHEDULE_TYPE_OPTIONS:
-                                if s_type in value_sampler:
-                                    value_sampler = value_sampler.replace(s_type, "").strip()
-                                    parameters["Sampler"] = value_sampler
-                                    parameters["Schedule type"] = s_type
-
-                        params_lora = []
-                        if ">" in parameters["prompt"] and "<" in parameters["prompt"]:
-                            params_lora = re.findall(r'<lora:[^>]+>', parameters["prompt"])
-                        if "Loras" in parameters:
-                            params_lora += re.findall(r'<lora:[^>]+>', parameters["Loras"])
-
-                        if params_lora:
-                            parsed_params = []
-                            for tag_l in params_lora:
-                                try:
-                                    inner = tag_l.strip("<>")        # remove < >
-                                    _, data_l = inner.split(":", 1)  # remove the "lora:" part
-                                    parts_l = data_l.split(":")
-
-                                    name_l = parts_l[0]
-                                    weight_l = float(parts_l[1]) if len(parts_l) > 1 else 1.0  # default weight = 1.0
-
-                                    parsed_params.append((name_l, weight_l))
-                                except Exception as e:
-                                    print(f"Error parsing LoRA tag {tag_l}: {e}")
-
-                            num_lora = 1
-                            for parsed_l, parsed_s in parsed_params:
-                                filtered_loras = [m for m in lora_model_list if parsed_l in m]
-                                if filtered_loras:
-                                    parameters[f"Lora_{num_lora}"] = filtered_loras[0]
-                                    parameters[f"Lora_scale_{num_lora}"] = parsed_s
-                                    num_lora += 1
-
-                        # continue = discard new value
-                        for key, val in parameters.items():
-                            # print(val)
-                            if key in valid_keys:
-                                try:
-                                    if key == "Sampler":
-                                        if val not in scheduler_names:
-                                            continue
-                                    if key in ["Schedule type", "Hires schedule type"]:
-                                        if val not in SCHEDULE_TYPE_OPTIONS:
-                                            continue
-                                    if key == "Hires sampler":
-                                        if val not in POST_PROCESSING_SAMPLER:
-                                            continue
-                                    elif key == "Clip skip":
-                                        if "," in str(val):
-                                            val = val.replace(",", "")
-                                        if int(val) >= 2:
-                                            val = True
-                                    if key == "prompt":
-                                        if ">" in val and "<" in val:
-                                            val = re.sub(r'<[^>]+>', '', val)  # Delete html and loras
-                                            print("Removed LoRA written in the prompt")
-                                    if key in ["prompt", "neg_prompt"]:
-                                        val = re.sub(r'\s+', ' ', re.sub(r',+', ',', val)).strip()
-                                    if key in ["Steps", "width", "height", "Seed", "Hires steps", "Image resolution"]:
-                                        val = int(val)
-                                    if key == "FreeU":
-                                        val = True
-                                    if key in ["CFG scale", "PAG", "Hires upscale", "Hires denoising strength", "Hires CFG", "Strength"]:
-                                        val = float(val)
-                                    if key == "Model":
-                                        filtered_models = [m for m in model_list if val in m]
-                                        if filtered_models:
-                                            val = filtered_models[0]
-                                        else:
-                                            val = name_model
-                                    if key == "Hires upscaler":
-                                        if val not in UPSCALER_KEYS:
-                                            continue
-                                    if key == "Seed":
-                                        continue
-
-                                    valid_receptors[key] = gr.update(value=val)
-                                    # print(val, type(val))
-                                    # print(valid_receptors)
-                                except Exception as e:
-                                    print(str(e))
-                        return [value for value in valid_receptors.values()]
-
-                    def run_clear_prompt_gui():
-                        return gr.update(value=""), gr.update(value="")
-                    clear_prompt_gui.click(
-                        run_clear_prompt_gui, [], [prompt_gui, neg_prompt_gui]
-                    )
-
-                    def run_set_random_seed():
-                        return -1
-                    set_random_seed.click(
-                        run_set_random_seed, [], seed_gui
-                    )
-
-                num_images_gui = gr.Slider(minimum=1, maximum=(8 if IS_ZERO_GPU else 20), step=1, value=1, label="Images")
-                prompt_syntax_gui = gr.Dropdown(label="Prompt Syntax", choices=PROMPT_W_OPTIONS, value=PROMPT_W_OPTIONS[1][1])
-                vae_model_gui = gr.Dropdown(label="VAE Model", choices=vae_model_list, value=vae_model_list[0])
-
-                with gr.Accordion("Hires fix", open=False, visible=True):
-
-                    upscaler_model_path_gui = gr.Dropdown(label="Upscaler", choices=UPSCALER_KEYS, value=UPSCALER_KEYS[0])
-                    upscaler_increases_size_gui = gr.Slider(minimum=1.1, maximum=4., step=0.1, value=1.2, label="Upscale by")
-                    upscaler_tile_size_gui = gr.Slider(minimum=0, maximum=512, step=16, value=(0 if IS_ZERO_GPU else 192), label="Upscaler Tile Size", info="0 = no tiling")
-                    upscaler_tile_overlap_gui = gr.Slider(minimum=0, maximum=48, step=1, value=8, label="Upscaler Tile Overlap")
-                    hires_steps_gui = gr.Slider(minimum=0, value=30, maximum=100, step=1, label="Hires Steps")
-                    hires_denoising_strength_gui = gr.Slider(minimum=0.1, maximum=1.0, step=0.01, value=0.55, label="Hires Denoising Strength")
-                    hires_sampler_gui = gr.Dropdown(label="Hires Sampler", choices=POST_PROCESSING_SAMPLER, value=POST_PROCESSING_SAMPLER[0])
-                    hires_schedule_list = ["Use same schedule type"] + SCHEDULE_TYPE_OPTIONS
-                    hires_schedule_type_gui = gr.Dropdown(label="Hires Schedule type", choices=hires_schedule_list, value=hires_schedule_list[0])
-                    hires_guidance_scale_gui = gr.Slider(minimum=-1., maximum=30., step=0.5, value=-1., label="Hires CFG", info="If the value is -1, the main CFG will be used")
-                    hires_prompt_gui = gr.Textbox(label="Hires Prompt", placeholder="Main prompt will be use", lines=3)
-                    hires_negative_prompt_gui = gr.Textbox(label="Hires Negative Prompt", placeholder="Main negative prompt will be use", lines=3)
-
-                with gr.Accordion("LoRA", open=False, visible=True):
-
-                    def lora_dropdown(label, visible=True):
-                        return gr.Dropdown(label=label, choices=lora_model_list, value="None", allow_custom_value=True, visible=visible)
-
-                    def lora_scale_slider(label, visible=True):
-                        val_lora = 8 if IS_ZERO_GPU else 10
-                        return gr.Slider(minimum=-val_lora, maximum=val_lora, step=0.01, value=0.33, label=label, visible=visible)
-
-                    lora1_gui = lora_dropdown("Lora1")
-                    lora_scale_1_gui = lora_scale_slider("Lora Scale 1")
-                    lora2_gui = lora_dropdown("Lora2")
-                    lora_scale_2_gui = lora_scale_slider("Lora Scale 2")
-                    lora3_gui = lora_dropdown("Lora3")
-                    lora_scale_3_gui = lora_scale_slider("Lora Scale 3")
-                    lora4_gui = lora_dropdown("Lora4")
-                    lora_scale_4_gui = lora_scale_slider("Lora Scale 4")
-                    lora5_gui = lora_dropdown("Lora5")
-                    lora_scale_5_gui = lora_scale_slider("Lora Scale 5")
-                    lora6_gui = lora_dropdown("Lora6", visible=(not IS_ZERO_GPU))
-                    lora_scale_6_gui = lora_scale_slider("Lora Scale 6", visible=(not IS_ZERO_GPU))
-                    lora7_gui = lora_dropdown("Lora7", visible=(not IS_ZERO_GPU))
-                    lora_scale_7_gui = lora_scale_slider("Lora Scale 7", visible=(not IS_ZERO_GPU))
-
-                    with gr.Accordion("From URL", open=False, visible=True):
-                        text_lora = gr.Textbox(
-                            label="LoRA's download URL",
-                            placeholder="https://civitai.com/api/download/models/28907",
-                            lines=1,
-                            info="It has to be .safetensors files, and you can also download them from Hugging Face.",
-                        )
-                        romanize_text = gr.Checkbox(value=False, label="Transliterate name", visible=(not IS_ZERO_GPU))
-                        button_lora = gr.Button("Get and Refresh the LoRA Lists")
-                        new_lora_status = gr.HTML()
-                        button_lora.click(
-                            get_my_lora,
-                            [text_lora, romanize_text],
-                            [lora1_gui, lora2_gui, lora3_gui, lora4_gui, lora5_gui, lora6_gui, lora7_gui, new_lora_status]
-                        )
-
-                with gr.Accordion("Face restoration", open=False, visible=True):
-
-                    face_rest_options = [None] + FACE_RESTORATION_MODELS
-
-                    face_restoration_model_gui = gr.Dropdown(label="Face restoration model", choices=face_rest_options, value=face_rest_options[0])
-                    face_restoration_visibility_gui = gr.Slider(minimum=0., maximum=1., step=0.001, value=1., label="Visibility")
-                    face_restoration_weight_gui = gr.Slider(minimum=0., maximum=1., step=0.001, value=.5, label="Weight", info="(0 = maximum effect, 1 = minimum effect)")
-
-                with gr.Accordion("IP-Adapter", open=False, visible=True):
-
-                    with gr.Accordion("IP-Adapter 1", open=False, visible=True):
-                        image_ip1 = gr.Image(label="IP Image", type="filepath")
-                        mask_ip1 = gr.Image(label="IP Mask", type="filepath")
-                        model_ip1 = gr.Dropdown(value="plus_face", label="Model", choices=IP_MODELS)
-                        mode_ip1 = gr.Dropdown(value="original", label="Mode", choices=MODE_IP_OPTIONS)
-                        scale_ip1 = gr.Slider(minimum=0., maximum=2., step=0.01, value=0.7, label="Scale")
-                    with gr.Accordion("IP-Adapter 2", open=False, visible=True):
-                        image_ip2 = gr.Image(label="IP Image", type="filepath")
-                        mask_ip2 = gr.Image(label="IP Mask (optional)", type="filepath")
-                        model_ip2 = gr.Dropdown(value="base", label="Model", choices=IP_MODELS)
-                        mode_ip2 = gr.Dropdown(value="style", label="Mode", choices=MODE_IP_OPTIONS)
-                        scale_ip2 = gr.Slider(minimum=0., maximum=2., step=0.01, value=0.7, label="Scale")
-
-                with gr.Accordion("ControlNet / Img2img / Inpaint", open=False, visible=True):
-                    image_control = gr.Image(label="Image ControlNet/Inpaint/Img2img", type="filepath")
-                    image_mask_gui = gr.Image(label="Image Mask", type="filepath")
-                    strength_gui = gr.Slider(
-                        minimum=0.01, maximum=1.0, step=0.01, value=0.55, label="Strength",
-                        info="This option adjusts the level of changes for img2img, repaint and inpaint."
-                    )
-                    image_resolution_gui = gr.Slider(
-                        minimum=64, maximum=2048, step=64, value=1024, label="Image Resolution",
-                        info="The maximum proportional size of the generated image based on the uploaded image."
-                    )
-                    controlnet_model_gui = gr.Dropdown(label="ControlNet model", choices=DIFFUSERS_CONTROLNET_MODEL, value=DIFFUSERS_CONTROLNET_MODEL[0], allow_custom_value=True)
-                    control_net_output_scaling_gui = gr.Slider(minimum=0, maximum=5.0, step=0.1, value=1, label="ControlNet Output Scaling in UNet")
-                    control_net_start_threshold_gui = gr.Slider(minimum=0, maximum=1, step=0.01, value=0, label="ControlNet Start Threshold (%)")
-                    control_net_stop_threshold_gui = gr.Slider(minimum=0, maximum=1, step=0.01, value=1, label="ControlNet Stop Threshold (%)")
-                    preprocessor_name_gui = gr.Dropdown(label="Preprocessor Name", choices=TASK_AND_PREPROCESSORS["canny"])
-
-                    def change_preprocessor_choices(task):
-                        task = TASK_STABLEPY[task]
-                        if task in TASK_AND_PREPROCESSORS.keys():
-                            choices_task = TASK_AND_PREPROCESSORS[task]
-                        else:
-                            choices_task = TASK_AND_PREPROCESSORS["canny"]
-                        return gr.update(choices=choices_task, value=choices_task[0])
-                    task_gui.change(
-                        change_preprocessor_choices,
-                        [task_gui],
-                        [preprocessor_name_gui],
-                    )
-
-                    preprocess_resolution_gui = gr.Slider(minimum=64, maximum=2048, step=64, value=512, label="Preprocessor Resolution")
-                    low_threshold_gui = gr.Slider(minimum=1, maximum=255, step=1, value=100, label="'CANNY' low threshold")
-                    high_threshold_gui = gr.Slider(minimum=1, maximum=255, step=1, value=200, label="'CANNY' high threshold")
-                    value_threshold_gui = gr.Slider(minimum=0.0, maximum=2.0, step=0.01, value=0.1, label="'MLSD' Hough value threshold")
-                    distance_threshold_gui = gr.Slider(minimum=0.0, maximum=20.0, step=0.01, value=0.1, label="'MLSD' Hough distance threshold")
-                    recolor_gamma_correction_gui = gr.Number(minimum=0., maximum=25., value=1., step=0.001, label="'RECOLOR' gamma correction")
-                    tile_blur_sigma_gui = gr.Number(minimum=0, maximum=100, value=9, step=1, label="'TILE' blur sigma")
-
-                with gr.Accordion("T2I adapter", open=False, visible=False):
-                    t2i_adapter_preprocessor_gui = gr.Checkbox(value=True, label="T2i Adapter Preprocessor")
-                    adapter_conditioning_scale_gui = gr.Slider(minimum=0, maximum=5., step=0.1, value=1, label="Adapter Conditioning Scale")
-                    adapter_conditioning_factor_gui = gr.Slider(minimum=0, maximum=1., step=0.01, value=0.55, label="Adapter Conditioning Factor (%)")
-
-                with gr.Accordion("Styles", open=False, visible=True):
-
-                    try:
-                        style_names_found = sd_gen.model.STYLE_NAMES
-                    except Exception:
-                        style_names_found = STYLE_NAMES
-
-                    style_prompt_gui = gr.Dropdown(
-                        style_names_found,
-                        multiselect=True,
-                        value=None,
-                        label="Style Prompt",
-                        interactive=True,
-                    )
-                    style_json_gui = gr.File(label="Style JSON File")
-                    style_button = gr.Button("Load styles")
-
-                    def load_json_style_file(json):
-                        if not sd_gen.model:
-                            gr.Info("First load the model")
-                            return gr.update(value=None, choices=STYLE_NAMES)
-
-                        sd_gen.model.load_style_file(json)
-                        gr.Info(f"{len(sd_gen.model.STYLE_NAMES)} styles loaded")
-                        return gr.update(value=None, choices=sd_gen.model.STYLE_NAMES)
-
-                    style_button.click(load_json_style_file, [style_json_gui], [style_prompt_gui])
-
-                with gr.Accordion("Textual inversion", open=False, visible=False):
-                    active_textual_inversion_gui = gr.Checkbox(value=False, label="Active Textual Inversion in prompt")
-
-                with gr.Accordion("Detailfix", open=False, visible=True):
-
-                    # Adetailer Inpaint Only
-                    adetailer_inpaint_only_gui = gr.Checkbox(label="Inpaint only", value=True)
-
-                    # Adetailer Verbose
-                    adetailer_verbose_gui = gr.Checkbox(label="Verbose", value=False)
-
-                    # Adetailer Sampler
-                    adetailer_sampler_gui = gr.Dropdown(label="Adetailer sampler:", choices=POST_PROCESSING_SAMPLER, value=POST_PROCESSING_SAMPLER[0])
-
-                    with gr.Accordion("Detailfix A", open=False, visible=True):
-                        # Adetailer A
-                        adetailer_active_a_gui = gr.Checkbox(label="Enable Adetailer A", value=False)
-                        prompt_ad_a_gui = gr.Textbox(label="Main prompt", placeholder="Main prompt will be use", lines=3)
-                        negative_prompt_ad_a_gui = gr.Textbox(label="Negative prompt", placeholder="Main negative prompt will be use", lines=3)
-                        strength_ad_a_gui = gr.Number(label="Strength:", value=0.35, step=0.01, minimum=0.01, maximum=1.0)
-                        face_detector_ad_a_gui = gr.Checkbox(label="Face detector", value=True)
-                        person_detector_ad_a_gui = gr.Checkbox(label="Person detector", value=False)
-                        hand_detector_ad_a_gui = gr.Checkbox(label="Hand detector", value=False)
-                        mask_dilation_a_gui = gr.Number(label="Mask dilation:", value=4, minimum=1)
-                        mask_blur_a_gui = gr.Number(label="Mask blur:", value=4, minimum=1)
-                        mask_padding_a_gui = gr.Number(label="Mask padding:", value=32, minimum=1)
-
-                    with gr.Accordion("Detailfix B", open=False, visible=True):
-                        # Adetailer B
-                        adetailer_active_b_gui = gr.Checkbox(label="Enable Adetailer B", value=False)
-                        prompt_ad_b_gui = gr.Textbox(label="Main prompt", placeholder="Main prompt will be use", lines=3)
-                        negative_prompt_ad_b_gui = gr.Textbox(label="Negative prompt", placeholder="Main negative prompt will be use", lines=3)
-                        strength_ad_b_gui = gr.Number(label="Strength:", value=0.35, step=0.01, minimum=0.01, maximum=1.0)
-                        face_detector_ad_b_gui = gr.Checkbox(label="Face detector", value=False)
-                        person_detector_ad_b_gui = gr.Checkbox(label="Person detector", value=True)
-                        hand_detector_ad_b_gui = gr.Checkbox(label="Hand detector", value=False)
-                        mask_dilation_b_gui = gr.Number(label="Mask dilation:", value=4, minimum=1)
-                        mask_blur_b_gui = gr.Number(label="Mask blur:", value=4, minimum=1)
-                        mask_padding_b_gui = gr.Number(label="Mask padding:", value=32, minimum=1)
-
-                with gr.Accordion("Other settings", open=False, visible=True):
-                    schedule_prediction_type_gui = gr.Dropdown(label="Discrete Sampling Type", choices=SCHEDULE_PREDICTION_TYPE_OPTIONS, value=SCHEDULE_PREDICTION_TYPE_OPTIONS[0])
-                    guidance_rescale_gui = gr.Number(label="CFG rescale:", value=0., step=0.01, minimum=0., maximum=1.5)
-                    save_generated_images_gui = gr.Checkbox(value=True, label="Create a download link for the images")
-                    filename_pattern_gui = gr.Textbox(label="Filename pattern", value="model,seed", placeholder="model,seed,sampler,schedule_type,img_width,img_height,guidance_scale,num_steps,vae,prompt_section,neg_prompt_section", lines=1)
-                    hires_before_adetailer_gui = gr.Checkbox(value=False, label="Hires Before Adetailer")
-                    hires_after_adetailer_gui = gr.Checkbox(value=True, label="Hires After Adetailer")
-                    generator_in_cpu_gui = gr.Checkbox(value=False, label="Generator in CPU")
-                    with gr.Column(visible=(not IS_ZERO_GPU)):
-                        image_storage_location_gui = gr.Textbox(value=img_path, label="Image Storage Location")
-                        disable_progress_bar_gui = gr.Checkbox(value=False, label="Disable Progress Bar")
-                        leave_progress_bar_gui = gr.Checkbox(value=True, label="Leave Progress Bar")
-
-                with gr.Accordion("More settings", open=False, visible=False):
-                    loop_generation_gui = gr.Slider(minimum=1, value=1, label="Loop Generation")
-                    retain_task_cache_gui = gr.Checkbox(value=False, label="Retain task model in cache")
-                    display_images_gui = gr.Checkbox(value=False, label="Display Images")
-                    image_previews_gui = gr.Checkbox(value=True, label="Image Previews")
-                    retain_compel_previous_load_gui = gr.Checkbox(value=False, label="Retain Compel Previous Load")
-                    retain_detailfix_model_previous_load_gui = gr.Checkbox(value=False, label="Retain Detailfix Model Previous Load")
-                    retain_hires_model_previous_load_gui = gr.Checkbox(value=False, label="Retain Hires Model Previous Load")
-                    xformers_memory_efficient_attention_gui = gr.Checkbox(value=False, label="Xformers Memory Efficient Attention")
-
-                set_params_gui.click(
-                    run_set_params_gui, [prompt_gui, model_name_gui], [
-                        prompt_gui,
-                        neg_prompt_gui,
-                        steps_gui,
-                        img_width_gui,
-                        img_height_gui,
-                        seed_gui,
-                        sampler_gui,
-                        cfg_gui,
-                        clip_skip_gui,
-                        model_name_gui,
-                        schedule_type_gui,
-                        pag_scale_gui,
-                        free_u_gui,
-                        upscaler_model_path_gui,
-                        upscaler_increases_size_gui,
-                        hires_steps_gui,
-                        hires_denoising_strength_gui,
-                        hires_guidance_scale_gui,
-                        hires_sampler_gui,
-                        hires_schedule_type_gui,
-                        image_resolution_gui,
-                        strength_gui,
-                        lora1_gui,
-                        lora_scale_1_gui,
-                        lora2_gui,
-                        lora_scale_2_gui,
-                        lora3_gui,
-                        lora_scale_3_gui,
-                        lora4_gui,
-                        lora_scale_4_gui,
-                        lora5_gui,
-                        lora_scale_5_gui,
-                        lora6_gui,
-                        lora_scale_6_gui,
-                        lora7_gui,
-                        lora_scale_7_gui,
-                    ],
-                )
-
-        with gr.Accordion("Examples and help", open=False, visible=True):
-            gr.Markdown(HELP_GUI)
-            gr.Markdown(EXAMPLES_GUI_HELP)
-            gr.Examples(
-                examples=EXAMPLES_GUI,
-                fn=sd_gen.generate_pipeline,
-                inputs=[
-                    prompt_gui,
-                    neg_prompt_gui,
-                    steps_gui,
-                    cfg_gui,
-                    seed_gui,
-                    lora1_gui,
-                    lora_scale_1_gui,
-                    sampler_gui,
-                    img_height_gui,
-                    img_width_gui,
-                    model_name_gui,
-                    task_gui,
-                    image_control,
-                    image_resolution_gui,
-                    strength_gui,
-                    control_net_output_scaling_gui,
-                    control_net_start_threshold_gui,
-                    control_net_stop_threshold_gui,
-                    prompt_syntax_gui,
-                    upscaler_model_path_gui,
-                    gpu_duration_gui,
-                    load_lora_cpu_gui,
-                ],
-                outputs=[load_model_gui, result_images, actual_task_info],
-                cache_examples=False,
-            )
-            gr.Markdown(RESOURCES)
-
-    with gr.Tab("Inpaint mask maker", render=True):
-
-        with gr.Row():
-            with gr.Column(scale=2):
-                image_base = gr.ImageEditor(
-                    sources=["upload", "clipboard"],
-                    # crop_size="1:1",
-                    # enable crop (or disable it)
-                    # transforms=["crop"],
-                    brush=gr.Brush(
-                        default_size="16",  # or leave it as 'auto'
-                        color_mode="fixed",  # 'fixed' hides the user swatches and colorpicker, 'defaults' shows it
-                        # default_color="black", # html names are supported
-                        colors=[
-                            "rgba(0, 0, 0, 1)",  # rgb(a)
-                            "rgba(0, 0, 0, 0.1)",
-                            "rgba(255, 255, 255, 0.1)",
-                            # "hsl(360, 120, 120)" # in fact any valid colorstring
-                        ]
-                    ),
-                    eraser=gr.Eraser(default_size="16"),
-                    render=True,
-                    visible=False,
-                    interactive=False,
-                )
-
-                show_canvas = gr.Button("SHOW INPAINT CANVAS")
-
-                def change_visibility_canvas():
-                    return gr.update(visible=True, interactive=True), gr.update(visible=False)
-                show_canvas.click(change_visibility_canvas, [], [image_base, show_canvas])
-
-                invert_mask = gr.Checkbox(value=False, label="Invert mask")
-                btn = gr.Button("Create mask")
-
-            with gr.Column(scale=1):
-                img_source = gr.Image(interactive=False)
-                img_result = gr.Image(label="Mask image", show_label=True, interactive=False)
-                btn_send = gr.Button("Send to the first tab")
-
-            btn.click(create_mask_now, [image_base, invert_mask], [img_source, img_result])
-
-            def send_img(img_source, img_result):
-                return img_source, img_result
-            btn_send.click(send_img, [img_source, img_result], [image_control, image_mask_gui])
-
-    with gr.Tab("PNG Info"):
-
-        with gr.Row():
-            with gr.Column():
-                image_metadata = gr.Image(label="Image with metadata", type="pil", sources=["upload"])
-
-            with gr.Column():
-                result_metadata = gr.Textbox(label="Metadata", show_label=True, show_copy_button=True, interactive=False, container=True, max_lines=99)
-
-                image_metadata.change(
-                    fn=extract_exif_data,
-                    inputs=[image_metadata],
-                    outputs=[result_metadata],
-                )
-
-    with gr.Tab("Upscaler"):
-
-        with gr.Row():
-            with gr.Column():
-
-                USCALER_TAB_KEYS = [name for name in UPSCALER_KEYS[9:]]
-
-                image_up_tab = gr.Image(label="Image", type="pil", sources=["upload"])
-                upscaler_tab = gr.Dropdown(label="Upscaler", choices=USCALER_TAB_KEYS, value=USCALER_TAB_KEYS[5])
-                upscaler_size_tab = gr.Slider(minimum=1., maximum=4., step=0.1, value=1.1, label="Upscale by")
-                generate_button_up_tab = gr.Button(value="START UPSCALE", variant="primary")
-
-            with gr.Column():
-                result_up_tab = gr.Image(label="Result", type="pil", interactive=False, format="png")
-
-                generate_button_up_tab.click(
-                    fn=process_upscale,
-                    inputs=[image_up_tab, upscaler_tab, upscaler_size_tab],
-                    outputs=[result_up_tab],
-                )
-
-    with gr.Tab("Preprocessor", render=True):
-        preprocessor_tab()
-
-    generate_button.click(
-        fn=sd_gen.load_new_model,
-        inputs=[
-            model_name_gui,
-            vae_model_gui,
-            task_gui,
-            controlnet_model_gui,
-        ],
-        outputs=[load_model_gui],
-        queue=True,
-        show_progress="minimal",
-        api_name=(False if HIDE_API else None),
-    ).success(
-        fn=sd_gen_generate_pipeline,  # fn=sd_gen.generate_pipeline,
-        inputs=[
-            prompt_gui,
-            neg_prompt_gui,
-            num_images_gui,
-            steps_gui,
-            cfg_gui,
-            clip_skip_gui,
-            seed_gui,
-            lora1_gui,
-            lora_scale_1_gui,
-            lora2_gui,
-            lora_scale_2_gui,
-            lora3_gui,
-            lora_scale_3_gui,
-            lora4_gui,
-            lora_scale_4_gui,
-            lora5_gui,
-            lora_scale_5_gui,
-            lora6_gui,
-            lora_scale_6_gui,
-            lora7_gui,
-            lora_scale_7_gui,
-            sampler_gui,
-            schedule_type_gui,
-            schedule_prediction_type_gui,
-            img_height_gui,
-            img_width_gui,
-            model_name_gui,
-            vae_model_gui,
-            task_gui,
-            image_control,
-            preprocessor_name_gui,
-            preprocess_resolution_gui,
-            image_resolution_gui,
-            style_prompt_gui,
-            style_json_gui,
-            image_mask_gui,
-            strength_gui,
-            low_threshold_gui,
-            high_threshold_gui,
-            value_threshold_gui,
-            distance_threshold_gui,
-            recolor_gamma_correction_gui,
-            tile_blur_sigma_gui,
-            control_net_output_scaling_gui,
-            control_net_start_threshold_gui,
-            control_net_stop_threshold_gui,
-            active_textual_inversion_gui,
-            prompt_syntax_gui,
-            upscaler_model_path_gui,
-            upscaler_increases_size_gui,
-            upscaler_tile_size_gui,
-            upscaler_tile_overlap_gui,
-            hires_steps_gui,
-            hires_denoising_strength_gui,
-            hires_sampler_gui,
-            hires_prompt_gui,
-            hires_negative_prompt_gui,
-            hires_before_adetailer_gui,
-            hires_after_adetailer_gui,
-            hires_schedule_type_gui,
-            hires_guidance_scale_gui,
-            controlnet_model_gui,
-            loop_generation_gui,
-            leave_progress_bar_gui,
-            disable_progress_bar_gui,
-            image_previews_gui,
-            display_images_gui,
-            save_generated_images_gui,
-            filename_pattern_gui,
-            image_storage_location_gui,
-            retain_compel_previous_load_gui,
-            retain_detailfix_model_previous_load_gui,
-            retain_hires_model_previous_load_gui,
-            t2i_adapter_preprocessor_gui,
-            adapter_conditioning_scale_gui,
-            adapter_conditioning_factor_gui,
-            xformers_memory_efficient_attention_gui,
-            free_u_gui,
-            generator_in_cpu_gui,
-            adetailer_inpaint_only_gui,
-            adetailer_verbose_gui,
-            adetailer_sampler_gui,
-            adetailer_active_a_gui,
-            prompt_ad_a_gui,
-            negative_prompt_ad_a_gui,
-            strength_ad_a_gui,
-            face_detector_ad_a_gui,
-            person_detector_ad_a_gui,
-            hand_detector_ad_a_gui,
-            mask_dilation_a_gui,
-            mask_blur_a_gui,
-            mask_padding_a_gui,
-            adetailer_active_b_gui,
-            prompt_ad_b_gui,
-            negative_prompt_ad_b_gui,
-            strength_ad_b_gui,
-            face_detector_ad_b_gui,
-            person_detector_ad_b_gui,
-            hand_detector_ad_b_gui,
-            mask_dilation_b_gui,
-            mask_blur_b_gui,
-            mask_padding_b_gui,
-            retain_task_cache_gui,
-            guidance_rescale_gui,
-            image_ip1,
-            mask_ip1,
-            model_ip1,
-            mode_ip1,
-            scale_ip1,
-            image_ip2,
-            mask_ip2,
-            model_ip2,
-            mode_ip2,
-            scale_ip2,
-            pag_scale_gui,
-            face_restoration_model_gui,
-            face_restoration_visibility_gui,
-            face_restoration_weight_gui,
-            load_lora_cpu_gui,
-            verbose_info_gui,
-            gpu_duration_gui,
-        ],
-        outputs=[load_model_gui, result_images, actual_task_info],
-        queue=True,
-        show_progress="minimal",
-        # api_name=(False if HIDE_API else None),
-    )
-
-if __name__ == "__main__":
-    app.queue()
-    app.launch(
-        show_error=True,
-        share=args.share_enabled,
-        debug=True,
-        ssr_mode=args.ssr,
-        allowed_paths=[allowed_path],
-        show_api=(not HIDE_API),
-    )

constants.py

@@ -1,611 +0,0 @@
-import os
-from stablepy.diffusers_vanilla.constants import FLUX_CN_UNION_MODES
-from stablepy import (
-    scheduler_names,
-    SD15_TASKS,
-    SDXL_TASKS,
-    ALL_BUILTIN_UPSCALERS,
-    IP_ADAPTERS_SD,
-    IP_ADAPTERS_SDXL,
-)
-
-IS_ZERO_GPU = bool(os.getenv("SPACES_ZERO_GPU"))
-
-# - **Download Models**
-DOWNLOAD_MODEL = "https://huggingface.co/TechnoByte/MilkyWonderland/resolve/main/milkyWonderland_v40.safetensors"
-
-# - **Download VAEs**
-DOWNLOAD_VAE = "https://huggingface.co/fp16-guy/anything_kl-f8-anime2_vae-ft-mse-840000-ema-pruned_blessed_clearvae_fp16_cleaned/resolve/main/vae-ft-mse-840000-ema-pruned_fp16.safetensors?download=true"
-
-# - **Download LoRAs**
-DOWNLOAD_LORA = "https://huggingface.co/Leopain/color/resolve/main/Coloring_book_-_LineArt.safetensors, https://civitai.com/api/download/models/135867, https://huggingface.co/Linaqruf/anime-detailer-xl-lora/resolve/main/anime-detailer-xl.safetensors?download=true, https://huggingface.co/Linaqruf/style-enhancer-xl-lora/resolve/main/style-enhancer-xl.safetensors?download=true, https://huggingface.co/ByteDance/Hyper-SD/resolve/main/Hyper-SD15-8steps-CFG-lora.safetensors?download=true, https://huggingface.co/ByteDance/Hyper-SD/resolve/main/Hyper-SDXL-8steps-CFG-lora.safetensors?download=true"
-
-LOAD_DIFFUSERS_FORMAT_MODEL = [
-    'stabilityai/stable-diffusion-xl-base-1.0',
-    'Laxhar/noobai-XL-1.1',
-    'Laxhar/noobai-XL-Vpred-1.0',
-    'black-forest-labs/FLUX.1-dev',
-    'black-forest-labs/FLUX.1-Krea-dev',
-    'John6666/blue-pencil-flux1-v021-fp8-flux',
-    'John6666/wai-ani-flux-v10forfp8-fp8-flux',
-    'John6666/xe-anime-flux-v04-fp8-flux',
-    'John6666/lyh-anime-flux-v2a1-fp8-flux',
-    'John6666/carnival-unchained-v10-fp8-flux',
-    'Freepik/flux.1-lite-8B-alpha',
-    'shauray/FluxDev-HyperSD-merged',
-    'mikeyandfriends/PixelWave_FLUX.1-dev_03',
-    'terminusresearch/FluxBooru-v0.3',
-    'black-forest-labs/FLUX.1-schnell',
-    # 'ostris/OpenFLUX.1',
-    'shuttleai/shuttle-3-diffusion',
-    'Laxhar/noobai-XL-1.0',
-    'Laxhar/noobai-XL-0.77',
-    'John6666/noobai-xl-nai-xl-epsilonpred075version-sdxl',
-    'Laxhar/noobai-XL-0.6',
-    'John6666/noobai-xl-nai-xl-epsilonpred05version-sdxl',
-    'John6666/noobai-cyberfix-v10-sdxl',
-    'John6666/noobaiiter-xl-vpred-v075-sdxl',
-    'John6666/ripplemix-noob-vpred10-illustrious01-v14-sdxl',
-    'John6666/sigmaih-15-sdxl',
-    'John6666/ntr-mix-illustrious-xl-noob-xl-xi-sdxl',
-    'John6666/ntr-mix-illustrious-xl-noob-xl-xii-sdxl',
-    'John6666/ntr-mix-illustrious-xl-noob-xl-xiii-sdxl',
-    'John6666/mistoon-anime-v10illustrious-sdxl',
-    'John6666/hassaku-xl-illustrious-v22-sdxl',
-    'John6666/haruki-mix-illustrious-v10-sdxl',
-    'John6666/noobreal-v10-sdxl',
-    'John6666/complicated-noobai-merge-vprediction-sdxl',
-    'Laxhar/noobai-XL-Vpred-0.9r',
-    'Laxhar/noobai-XL-Vpred-0.75s',
-    'Laxhar/noobai-XL-Vpred-0.75',
-    'Laxhar/noobai-XL-Vpred-0.65s',
-    'Laxhar/noobai-XL-Vpred-0.65',
-    'Laxhar/noobai-XL-Vpred-0.6',
-    'John6666/cat-tower-noobai-xl-checkpoint-v14vpred-sdxl',
-    'John6666/cat-tower-noobai-xl-checkpoint-v15vpred-sdxl',
-    'John6666/noobai-xl-nai-xl-vpred05version-sdxl',
-    'John6666/noobai-fusion2-vpred-itercomp-v1-sdxl',
-    'John6666/noobai-xl-nai-xl-vpredtestversion-sdxl',
-    'John6666/chadmix-noobai075-illustrious01-v10-sdxl',
-    'OnomaAIResearch/Illustrious-xl-early-release-v0',
-    'John6666/illustriousxl-mmmix-v50-sdxl',
-    'John6666/illustrious-pencil-xl-v200-sdxl',
-    'John6666/obsession-illustriousxl-v21-sdxl',
-    'John6666/obsession-illustriousxl-v30-sdxl',
-    'John6666/obsession-illustriousxl-v31-sdxl',
-    'John6666/one-obsession-13-sdxl',
-    'John6666/one-obsession-14-24d-sdxl',
-    'John6666/one-obsession-15-noobai-sdxl',
-    'John6666/one-obsession-v16-noobai-sdxl',
-    'John6666/prefect-illustrious-xl-v3-sdxl',
-    'John6666/wai-nsfw-illustrious-v70-sdxl',
-    'John6666/wai-nsfw-illustrious-sdxl-v140-sdxl',
-    'John6666/illustrious-pony-mix-v3-sdxl',
-    'John6666/nova-anime-xl-il-v90-sdxl',
-    'John6666/nova-anime-xl-il-v110-sdxl',
-    'John6666/nova-orange-xl-re-v10-sdxl',
-    'John6666/nova-orange-xl-v110-sdxl',
-    'John6666/nova-orange-xl-re-v20-sdxl',
-    'John6666/nova-unreal-xl-v60-sdxl',
-    'John6666/nova-unreal-xl-v70-sdxl',
-    'John6666/nova-unreal-xl-v80-sdxl',
-    'John6666/nova-cartoon-xl-v40-sdxl',
-    'John6666/silvermoon-mix03-illustrious-v10-sdxl',
-    'eienmojiki/Anything-XL',
-    'eienmojiki/Starry-XL-v5.2',
-    'votepurchase/plantMilkModelSuite_walnut',
-    'John6666/meinaxl-v2-sdxl',
-    'Eugeoter/artiwaifu-diffusion-2.0',
-    'comin/IterComp',
-    'John6666/epicrealism-xl-v8kiss-sdxl',
-    'John6666/epicrealism-xl-v10kiss2-sdxl',
-    'John6666/epicrealism-xl-vxiabeast-sdxl',
-    'John6666/epicrealism-xl-vxvii-crystal-clear-realism-sdxl',
-    'misri/zavychromaxl_v80',
-    'SG161222/RealVisXL_V4.0',
-    'SG161222/RealVisXL_V5.0',
-    'misri/newrealityxlAllInOne_Newreality40',
-    'gsdf/CounterfeitXL',
-    'WhiteAiZ/autismmixSDXL_autismmixConfetti_diffusers',
-    'kitty7779/ponyDiffusionV6XL',
-    'GraydientPlatformAPI/aniverse-pony',
-    'John6666/ras-real-anime-screencap-v1-sdxl',
-    'John6666/duchaiten-pony-xl-no-score-v60-sdxl',
-    'John6666/mistoon-anime-ponyalpha-sdxl',
-    'John6666/mistoon-xl-copper-v20fast-sdxl',
-    'John6666/ebara-mfcg-pony-mix-v12-sdxl',
-    'John6666/t-ponynai3-v51-sdxl',
-    'John6666/t-ponynai3-v65-sdxl',
-    'John6666/t-ponynai3-v7-sdxl',
-    'John6666/prefect-pony-xl-v3-sdxl',
-    'John6666/prefect-pony-xl-v4-sdxl',
-    'John6666/prefect-pony-xl-v50-sdxl',
-    'John6666/mala-anime-mix-nsfw-pony-xl-v5-sdxl',
-    'John6666/wai-ani-nsfw-ponyxl-v10-sdxl',
-    'John6666/wai-real-mix-v11-sdxl',
-    'John6666/wai-shuffle-pdxl-v2-sdxl',
-    'John6666/wai-c-v6-sdxl',
-    'John6666/iniverse-mix-xl-sfwnsfw-pony-guofeng-v43-sdxl',
-    'John6666/sifw-annihilation-xl-v2-sdxl',
-    'John6666/sifw-annihilation-xl-v305illustrious-beta-sdxl',
-    'John6666/photo-realistic-pony-v5-sdxl',
-    'John6666/pony-realism-v21main-sdxl',
-    'John6666/pony-realism-v22main-sdxl',
-    'John6666/pony-realism-v23-ultra-sdxl',
-    'John6666/cyberrealistic-pony-v65-sdxl',
-    'John6666/cyberrealistic-pony-v7-sdxl',
-    'John6666/cyberrealistic-pony-v127-alternative-sdxl',
-    'GraydientPlatformAPI/realcartoon-pony-diffusion',
-    'John6666/nova-anime-xl-pony-v5-sdxl',
-    'John6666/autismmix-sdxl-autismmix-pony-sdxl',
-    'John6666/aimz-dream-real-pony-mix-v3-sdxl',
-    'John6666/prefectious-xl-nsfw-v10-sdxl',
-    'GraydientPlatformAPI/iniverseponyRealGuofeng49',
-    'John6666/duchaiten-pony-real-v11fix-sdxl',
-    'John6666/duchaiten-pony-real-v20-sdxl',
-    'John6666/duchaiten-pony-xl-no-score-v70-sdxl',
-    'KBlueLeaf/Kohaku-XL-Zeta',
-    'cagliostrolab/animagine-xl-3.1',
-    'cagliostrolab/animagine-xl-4.0',
-    'yodayo-ai/kivotos-xl-2.0',
-    'yodayo-ai/holodayo-xl-2.1',
-    'yodayo-ai/clandestine-xl-1.0',
-    'https://huggingface.co/chemwolf/Karmix-XL-v0/resolve/main/Karmix-XL-v0.safetensors?download=true',
-    'https://civitai.com/api/download/models/128713?type=Model&format=SafeTensor&size=pruned&fp=fp16',
-    'https://civitai.com/models/30240?modelVersionId=125771',
-    'digiplay/majicMIX_sombre_v2',
-    'digiplay/majicMIX_realistic_v6',
-    'digiplay/majicMIX_realistic_v7',
-    'digiplay/DreamShaper_8',
-    'digiplay/BeautifulArt_v1',
-    'digiplay/DarkSushi2.5D_v1',
-    'digiplay/darkphoenix3D_v1.1',
-    'digiplay/BeenYouLiteL11_diffusers',
-    'GraydientPlatformAPI/rev-animated2',
-    'myxlmynx/cyberrealistic_classic40',
-    'GraydientPlatformAPI/cyberreal6',
-    'GraydientPlatformAPI/cyberreal5',
-    'youknownothing/deliberate-v6',
-    'GraydientPlatformAPI/deliberate-cyber3',
-    'GraydientPlatformAPI/picx-real',
-    'GraydientPlatformAPI/perfectworld6',
-    'emilianJR/epiCRealism',
-    'votepurchase/counterfeitV30_v30',
-    'votepurchase/ChilloutMix',
-    'Meina/MeinaMix_V11',
-    'Meina/MeinaUnreal_V5',
-    'Meina/MeinaPastel_V7',
-    'GraydientPlatformAPI/realcartoon3d-17',
-    'GraydientPlatformAPI/realcartoon-pixar11',
-    'GraydientPlatformAPI/realcartoon-real17',
-]
-
-
-DIFFUSERS_FORMAT_LORAS = [
-    "nerijs/animation2k-flux",
-    "XLabs-AI/flux-RealismLora",
-    "Shakker-Labs/FLUX.1-dev-LoRA-Logo-Design",
-]
-
-DOWNLOAD_EMBEDS = [
-    'https://huggingface.co/datasets/Nerfgun3/bad_prompt/blob/main/bad_prompt_version2.pt',
-    # 'https://huggingface.co/embed/negative/resolve/main/EasyNegativeV2.safetensors',
-    # 'https://huggingface.co/embed/negative/resolve/main/bad-hands-5.pt',
-]
-
-CIVITAI_API_KEY = os.environ.get("CIVITAI_API_KEY")
-HF_TOKEN = os.environ.get("HF_READ_TOKEN")
-
-DIRECTORY_MODELS = 'models'
-DIRECTORY_LORAS = 'loras'
-DIRECTORY_VAES = 'vaes'
-DIRECTORY_EMBEDS = 'embedings'
-DIRECTORY_UPSCALERS = 'upscalers'
-
-STORAGE_ROOT = "/home/user/"
-CACHE_HF_ROOT = os.path.expanduser("~/.cache/huggingface")
-CACHE_HF = os.path.join(CACHE_HF_ROOT, "hub")
-if IS_ZERO_GPU:
-    os.environ["HF_HOME"] = CACHE_HF
-
-TASK_STABLEPY = {
-    'txt2img': 'txt2img',
-    'img2img': 'img2img',
-    'inpaint': 'inpaint',
-    # 'canny T2I Adapter': 'sdxl_canny_t2i',  # NO HAVE STEP CALLBACK PARAMETERS SO NOT WORKS WITH DIFFUSERS 0.29.0
-    # 'sketch  T2I Adapter': 'sdxl_sketch_t2i',
-    # 'lineart  T2I Adapter': 'sdxl_lineart_t2i',
-    # 'depth-midas  T2I Adapter': 'sdxl_depth-midas_t2i',
-    # 'openpose  T2I Adapter': 'sdxl_openpose_t2i',
-    'openpose ControlNet': 'openpose',
-    'canny ControlNet': 'canny',
-    'mlsd ControlNet': 'mlsd',
-    'scribble ControlNet': 'scribble',
-    'softedge ControlNet': 'softedge',
-    'segmentation ControlNet': 'segmentation',
-    'depth ControlNet': 'depth',
-    'normalbae ControlNet': 'normalbae',
-    'lineart ControlNet': 'lineart',
-    'lineart_anime ControlNet': 'lineart_anime',
-    'shuffle ControlNet': 'shuffle',
-    'ip2p ControlNet': 'ip2p',
-    'optical pattern ControlNet': 'pattern',
-    'recolor ControlNet': 'recolor',
-    'tile ControlNet': 'tile',
-    'repaint ControlNet': 'repaint',
-}
-
-TASK_MODEL_LIST = list(TASK_STABLEPY.keys())
-
-UPSCALER_DICT_GUI = {
-    None: None,
-    **{bu: bu for bu in ALL_BUILTIN_UPSCALERS if bu not in ["HAT x4", "DAT x4", "DAT x3", "DAT x2", "SwinIR 4x"]},
-    # "RealESRGAN_x4plus": "https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth",
-    "RealESRNet_x4plus": "https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.1/RealESRNet_x4plus.pth",
-    # "RealESRGAN_x4plus_anime_6B": "https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth",
-    # "RealESRGAN_x2plus": "https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.1/RealESRGAN_x2plus.pth",
-    # "realesr-animevideov3": "https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-animevideov3.pth",
-    # "realesr-general-x4v3": "https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-general-x4v3.pth",
-    # "realesr-general-wdn-x4v3": "https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-general-wdn-x4v3.pth",
-    "4x-UltraSharp": "https://huggingface.co/Shandypur/ESRGAN-4x-UltraSharp/resolve/main/4x-UltraSharp.pth",
-    "Real-ESRGAN-Anime-finetuning": "https://huggingface.co/danhtran2mind/Real-ESRGAN-Anime-finetuning/resolve/main/Real-ESRGAN-Anime-finetuning.pth",
-    "4x_foolhardy_Remacri": "https://huggingface.co/FacehugmanIII/4x_foolhardy_Remacri/resolve/main/4x_foolhardy_Remacri.pth",
-    "Remacri4xExtraSmoother": "https://huggingface.co/hollowstrawberry/upscalers-backup/resolve/main/ESRGAN/Remacri%204x%20ExtraSmoother.pth",
-    "AnimeSharp4x": "https://huggingface.co/hollowstrawberry/upscalers-backup/resolve/main/ESRGAN/AnimeSharp%204x.pth",
-    "lollypop": "https://huggingface.co/hollowstrawberry/upscalers-backup/resolve/main/ESRGAN/lollypop.pth",
-    "RealisticRescaler4x": "https://huggingface.co/hollowstrawberry/upscalers-backup/resolve/main/ESRGAN/RealisticRescaler%204x.pth",
-    "NickelbackFS4x": "https://huggingface.co/hollowstrawberry/upscalers-backup/resolve/main/ESRGAN/NickelbackFS%204x.pth"
-}
-
-UPSCALER_KEYS = list(UPSCALER_DICT_GUI.keys())
-
-DIFFUSERS_CONTROLNET_MODEL = [
-    "Automatic",
-
-    "brad-twinkl/controlnet-union-sdxl-1.0-promax",
-    "xinsir/controlnet-union-sdxl-1.0",
-    "xinsir/anime-painter",
-    "Eugeoter/noob-sdxl-controlnet-canny",
-    "Eugeoter/noob-sdxl-controlnet-lineart_anime",
-    "Eugeoter/noob-sdxl-controlnet-depth",
-    "Eugeoter/noob-sdxl-controlnet-normal",
-    "Eugeoter/noob-sdxl-controlnet-softedge_hed",
-    "Eugeoter/noob-sdxl-controlnet-scribble_pidinet",
-    "Eugeoter/noob-sdxl-controlnet-scribble_hed",
-    "Eugeoter/noob-sdxl-controlnet-manga_line",
-    "Eugeoter/noob-sdxl-controlnet-lineart_realistic",
-    "Eugeoter/noob-sdxl-controlnet-depth_midas-v1-1",
-    "dimitribarbot/controlnet-openpose-sdxl-1.0-safetensors",
-    "r3gm/controlnet-openpose-sdxl-1.0-fp16",
-    "r3gm/controlnet-canny-scribble-integrated-sdxl-v2-fp16",
-    "r3gm/controlnet-union-sdxl-1.0-fp16",
-    "r3gm/controlnet-lineart-anime-sdxl-fp16",
-    "r3gm/control_v1p_sdxl_qrcode_monster_fp16",
-    "r3gm/controlnet-tile-sdxl-1.0-fp16",
-    "r3gm/controlnet-recolor-sdxl-fp16",
-    "r3gm/controlnet-openpose-twins-sdxl-1.0-fp16",
-    "r3gm/controlnet-qr-pattern-sdxl-fp16",
-    "Yakonrus/SDXL_Controlnet_Tile_Realistic_v2",
-    "TheMistoAI/MistoLine",
-    "briaai/BRIA-2.3-ControlNet-Recoloring",
-    "briaai/BRIA-2.3-ControlNet-Canny",
-
-    "lllyasviel/control_v11p_sd15_openpose",
-    "lllyasviel/control_v11p_sd15_canny",
-    "lllyasviel/control_v11p_sd15_mlsd",
-    "lllyasviel/control_v11p_sd15_scribble",
-    "lllyasviel/control_v11p_sd15_softedge",
-    "lllyasviel/control_v11p_sd15_seg",
-    "lllyasviel/control_v11f1p_sd15_depth",
-    "lllyasviel/control_v11p_sd15_normalbae",
-    "lllyasviel/control_v11p_sd15_lineart",
-    "lllyasviel/control_v11p_sd15s2_lineart_anime",
-    "lllyasviel/control_v11e_sd15_shuffle",
-    "lllyasviel/control_v11e_sd15_ip2p",
-    "lllyasviel/control_v11p_sd15_inpaint",
-    "monster-labs/control_v1p_sd15_qrcode_monster",
-    "lllyasviel/control_v11f1e_sd15_tile",
-    "latentcat/control_v1p_sd15_brightness",
-    "yuanqiuye/qrcode_controlnet_v3",
-
-    "Shakker-Labs/FLUX.1-dev-ControlNet-Union-Pro",
-    # "Shakker-Labs/FLUX.1-dev-ControlNet-Pose",
-    # "Shakker-Labs/FLUX.1-dev-ControlNet-Depth",
-    # "jasperai/Flux.1-dev-Controlnet-Upscaler",
-    # "jasperai/Flux.1-dev-Controlnet-Depth",
-    # "jasperai/Flux.1-dev-Controlnet-Surface-Normals",
-    # "XLabs-AI/flux-controlnet-canny-diffusers",
-    # "XLabs-AI/flux-controlnet-hed-diffusers",
-    # "XLabs-AI/flux-controlnet-depth-diffusers",
-    # "InstantX/FLUX.1-dev-Controlnet-Union",
-    # "InstantX/FLUX.1-dev-Controlnet-Canny",
-]
-
-PROMPT_W_OPTIONS = [
-    ("Compel format: (word)weight", "Compel"),
-    ("Classic format: (word:weight)", "Classic"),
-    ("Classic-original format: (word:weight)", "Classic-original"),
-    ("Classic-no_norm format: (word:weight)", "Classic-no_norm"),
-    ("Classic-sd_embed format: (word:weight)", "Classic-sd_embed"),
-    ("Classic-ignore", "Classic-ignore"),
-    ("None", "None"),
-]
-
-WARNING_MSG_VAE = (
-    "Use the right VAE for your model to maintain image quality. The wrong"
-    " VAE can lead to poor results, like blurriness in the generated images."
-)
-
-SDXL_TASK = [k for k, v in TASK_STABLEPY.items() if v in SDXL_TASKS]
-SD_TASK = [k for k, v in TASK_STABLEPY.items() if v in SD15_TASKS]
-FLUX_TASK = list(TASK_STABLEPY.keys())[:3] + [k for k, v in TASK_STABLEPY.items() if v in FLUX_CN_UNION_MODES.keys()]
-
-MODEL_TYPE_TASK = {
-    "SD 1.5": SD_TASK,
-    "SDXL": SDXL_TASK,
-    "FLUX": FLUX_TASK,
-}
-
-MODEL_TYPE_CLASS = {
-    "diffusers:StableDiffusionPipeline": "SD 1.5",
-    "diffusers:StableDiffusionXLPipeline": "SDXL",
-    "diffusers:FluxPipeline": "FLUX",
-}
-
-DIFFUSECRAFT_CHECKPOINT_NAME = {
-    "sd1.5": "SD 1.5",
-    "sdxl": "SDXL",
-    "flux-dev": "FLUX",
-    "flux-schnell": "FLUX",
-}
-
-POST_PROCESSING_SAMPLER = ["Use same sampler"] + [
-    name_s for name_s in scheduler_names if "Auto-Loader" not in name_s
-]
-
-IP_MODELS = []
-ALL_IPA = sorted(set(IP_ADAPTERS_SD + IP_ADAPTERS_SDXL))
-
-for origin_name in ALL_IPA:
-    suffixes = []
-    if origin_name in IP_ADAPTERS_SD:
-        suffixes.append("sd1.5")
-    if origin_name in IP_ADAPTERS_SDXL:
-        suffixes.append("sdxl")
-    ref_name = f"{origin_name} ({'/'.join(suffixes)})"
-    IP_MODELS.append((ref_name, origin_name))
-
-MODE_IP_OPTIONS = ["original", "style", "layout", "style+layout"]
-
-SUBTITLE_GUI = (
-    "### This demo uses [diffusers](https://github.com/huggingface/diffusers)"
-    " to perform different tasks in image generation."
-)
-
-msg_zero = "" if not IS_ZERO_GPU else "- The current space runs on a ZERO GPU which is assigned for approximately 60 seconds; Therefore, if you submit expensive tasks, the operation may be canceled upon reaching the maximum allowed time with 'GPU TASK ABORTED'."
-
-HELP_GUI = (
-    f"""### Help:
-    {msg_zero}
-    - Distorted or strange images often result from high prompt weights, so it's best to use low weights and scales, and consider using Classic variants like 'Classic-original'.
-    - For better results with Pony Diffusion, try using sampler DPM++ 1s or DPM2 with Compel or Classic prompt weights.
-    """
-)
-
-EXAMPLES_GUI_HELP = (
-    """### The following examples perform specific tasks:
-    1. Generation with SDXL and upscale
-    2. Generation with FLUX dev
-    3. ControlNet Canny SDXL
-    4. Optical pattern (Optical illusion) SDXL
-    5. Convert an image to a coloring drawing
-    6. V prediction model inference
-    7. V prediction model sd_embed variant inference
-    8. ControlNet OpenPose SD 1.5 and Latent upscale
-
-    - Different tasks can be performed, such as img2img or using the IP adapter, to preserve a person's appearance or a specific style based on an image.
-    """
-)
-
-EXAMPLES_GUI = [
-    [
-        "splatter paint theme, 1girl, frame center, pretty face, face with artistic paint artwork, feminism, long hair, upper body view, futuristic expression illustrative painted background, origami, stripes, explosive paint splashes behind her, hand on cheek pose, strobe lighting, masterpiece photography creative artwork, golden morning light, highly detailed, masterpiece, best quality, very aesthetic, absurdres",
-        "logo, artist name, (worst quality, normal quality), bad-artist, ((bad anatomy)), ((bad hands)), ((bad proportions)), ((duplicate limbs)), ((fused limbs)), ((interlocking fingers)), ((poorly drawn face)), high contrast., score_6, score_5, score_4, lowres, (bad), text, error, fewer, extra, missing, worst quality, jpeg artifacts, low quality, watermark, unfinished, displeasing, oldest, early, chromatic aberration, signature, extra digits, artistic error, username, scan, [abstract]",
-        28,
-        5.0,
-        -1,
-        "None",
-        0.33,
-        "DPM++ 2M SDE",
-        1152,
-        896,
-        "John6666/noobai-xl-nai-xl-epsilonpred10version-sdxl",
-        "txt2img",
-        "image.webp",  # img conttol
-        1024,  # img resolution
-        0.35,  # strength
-        1.0,  # cn scale
-        0.0,  # cn start
-        1.0,  # cn end
-        "Classic-no_norm",
-        "Nearest",
-        45,
-        False,
-    ],
-    [
-        "a digital illustration of a movie poster titled 'Finding Emo', finding nemo parody poster, featuring a depressed cartoon clownfish with black emo hair, eyeliner, and piercings, bored expression, swimming in a dark underwater scene, in the background, movie title in a dripping, grungy font, moody blue and purple color palette",
-        "",
-        24,
-        3.5,
-        -1,
-        "None",
-        0.33,
-        "FlowMatch Euler",
-        1152,
-        896,
-        "black-forest-labs/FLUX.1-dev",
-        "txt2img",
-        None,  # img conttol
-        1024,  # img resolution
-        0.35,  # strength
-        1.0,  # cn scale
-        0.0,  # cn start
-        1.0,  # cn end
-        "Classic",
-        None,
-        70,
-        True,
-    ],
-    [
-        "((masterpiece)), best quality, blonde disco girl, detailed face, realistic face, realistic hair, dynamic pose, pink pvc, intergalactic disco background, pastel lights, dynamic contrast, airbrush, fine detail, 70s vibe, midriff",
-        "(worst quality:1.2), (bad quality:1.2), (poor quality:1.2), (missing fingers:1.2), bad-artist-anime, bad-artist, bad-picture-chill-75v",
-        48,
-        3.5,
-        -1,
-        "None",
-        0.33,
-        "DPM++ 2M SDE Ef",
-        1024,
-        1024,
-        "John6666/epicrealism-xl-v10kiss2-sdxl",
-        "canny ControlNet",
-        "image.webp",  # img conttol
-        1024,  # img resolution
-        0.35,  # strength
-        1.0,  # cn scale
-        0.0,  # cn start
-        1.0,  # cn end
-        "Classic",
-        None,
-        44,
-        False,
-    ],
-    [
-        "cinematic scenery old city ruins",
-        "(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), (illustration, 3d, 2d, painting, cartoons, sketch, blurry, film grain, noise), (low quality, worst quality:1.2)",
-        50,
-        4.0,
-        -1,
-        "None",
-        0.33,
-        "Euler a",
-        1024,
-        1024,
-        "SG161222/RealVisXL_V5.0",
-        "optical pattern ControlNet",
-        "spiral_no_transparent.png",  # img conttol
-        1024,  # img resolution
-        0.35,  # strength
-        1.0,  # cn scale
-        0.05,  # cn start
-        0.8,  # cn end
-        "Classic",
-        None,
-        35,
-        False,
-    ],
-    [
-        "black and white, line art, coloring drawing, clean line art, black strokes, no background, white, black, free lines, black scribbles, on paper, A blend of comic book art and lineart full of black and white color, masterpiece, high-resolution, trending on Pixiv fan box, palette knife, brush strokes, two-dimensional, planar vector, T-shirt design, stickers, and T-shirt design, vector art, fantasy art, Adobe Illustrator, hand-painted, digital painting, low polygon, soft lighting, aerial view, isometric style, retro aesthetics, 8K resolution, black sketch lines, monochrome, invert color",
-        "color, red, green, yellow, colored, duplicate, blurry, abstract, disfigured, deformed, animated, toy, figure, framed, 3d, bad art, poorly drawn, extra limbs, close up, b&w, weird colors, blurry, watermark, blur haze, 2 heads, long neck, watermark, elongated body, cropped image, out of frame, draft, deformed hands, twisted fingers, double image, malformed hands, multiple heads, extra limb, ugly, poorly drawn hands, missing limb, cut-off, over satured, grain, lowères, bad anatomy, poorly drawn face, mutation, mutated, floating limbs, disconnected limbs, out of focus, long body, disgusting, extra fingers, groos proportions, missing arms, mutated hands, cloned face, missing legs, ugly, tiling, poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, extra limbs, disfigured, deformed, body out of frame, blurry, bad anatomy, blurred, watermark, grainy, signature, cut off, draft, deformed, blurry, bad anatomy, disfigured, poorly drawn face, mutation, bluelish, blue",
-        20,
-        4.0,
-        -1,
-        ("loras/Coloring_book_-_LineArt.safetensors" if os.path.exists("loras/Coloring_book_-_LineArt.safetensors") else "None"),
-        1.0,
-        "DPM++ 2M SDE",
-        1024,
-        1024,
-        "eienmojiki/Anything-XL",
-        "lineart ControlNet",
-        "color_image.png",  # img conttol
-        896,  # img resolution
-        0.35,  # strength
-        1.0,  # cn scale
-        0.0,  # cn start
-        1.0,  # cn end
-        "Compel",
-        None,
-        35,
-        False,
-    ],
-    [
-        "[mochizuki_shiina], [syuri22], newest, reimu, solo, outdoors, water, flower, lantern",
-        "worst quality, normal quality, old, sketch,",
-        28,
-        7.0,
-        -1,
-        "None",
-        0.33,
-        "DPM 3M Ef",
-        1600,
-        1024,
-        "Laxhar/noobai-XL-Vpred-1.0",
-        "txt2img",
-        "color_image.png",  # img conttol
-        1024,  # img resolution
-        0.35,  # strength
-        1.0,  # cn scale
-        0.0,  # cn start
-        1.0,  # cn end
-        "Classic",
-        None,
-        30,
-        False,
-    ],
-    [
-        "[mochizuki_shiina], [syuri22], newest, multiple girls, 2girls, earrings, jewelry, gloves, purple eyes, black hair, looking at viewer, nail polish, hat, smile, open mouth, fingerless gloves, sleeveless, :d, upper body, blue eyes, closed mouth, black gloves, hands up, long hair, shirt, bare shoulders, white headwear, blush, black headwear, blue nails, upper teeth only, short hair, white gloves, white shirt, teeth, rabbit hat, star earrings, purple nails, pink hair, detached sleeves, fingernails, fake animal ears, animal hat, sleeves past wrists, black shirt, medium hair, fur trim, sleeveless shirt, turtleneck, long sleeves, rabbit ears, star \\(symbol\\)",
-        "worst quality, normal quality, old, sketch,",
-        28,
-        7.0,
-        -1,
-        "None",
-        0.33,
-        "DPM 3M Ef",
-        1600,
-        1024,
-        "Laxhar/noobai-XL-Vpred-1.0",
-        "txt2img",
-        "color_image.png",  # img conttol
-        1024,  # img resolution
-        0.35,  # strength
-        1.0,  # cn scale
-        0.0,  # cn start
-        1.0,  # cn end
-        "Classic-sd_embed",
-        None,
-        30,
-        False,
-    ],
-    [
-        "1girl,face,curly hair,red hair,white background,",
-        "(worst quality:2),(low quality:2),(normal quality:2),lowres,watermark,",
-        38,
-        5.0,
-        -1,
-        "None",
-        0.33,
-        "DPM++ 2M SDE",
-        512,
-        512,
-        "digiplay/majicMIX_realistic_v7",
-        "openpose ControlNet",
-        "image.webp",  # img conttol
-        1024,  # img resolution
-        0.35,  # strength
-        1.0,  # cn scale
-        0.0,  # cn start
-        0.9,  # cn end
-        "Classic-original",
-        "Latent (antialiased)",
-        46,
-        False,
-    ],
-]
-
-RESOURCES = (
-    """### Resources
-    - John6666's space has some great features you might find helpful [link](https://huggingface.co/spaces/John6666/DiffuseCraftMod).
-    - Try the image generator in Colab’s free tier, which provides free GPU [link](https://github.com/R3gm/SD_diffusers_interactive).
-    - `DiffuseCraft` in Colab:[link](https://github.com/R3gm/DiffuseCraft?tab=readme-ov-file#diffusecraft).
-    """
-)

image_processor.py

@@ -1,130 +0,0 @@
-import spaces
-import gradio as gr
-from stablepy import Preprocessor
-
-PREPROCESSOR_TASKS_LIST = [
-    "Canny",
-    "Openpose",
-    "DPT",
-    "Midas",
-    "ZoeDepth",
-    "DepthAnything",
-    "HED",
-    "PidiNet",
-    "TEED",
-    "Lineart",
-    "LineartAnime",
-    "Anyline",
-    "Lineart standard",
-    "SegFormer",
-    "UPerNet",
-    "ContentShuffle",
-    "Recolor",
-    "Blur",
-    "MLSD",
-    "NormalBae",
-]
-
-preprocessor = Preprocessor()
-
-
-def process_inputs(
-    image,
-    name,
-    resolution,
-    precessor_resolution,
-    low_threshold,
-    high_threshold,
-    value_threshod,
-    distance_threshold,
-    recolor_mode,
-    recolor_gamma_correction,
-    blur_k_size,
-    pre_openpose_extra,
-    hed_scribble,
-    pre_pidinet_safe,
-    pre_lineart_coarse,
-    use_cuda,
-):
-    if not image:
-        raise ValueError("To use this, simply upload an image.")
-
-    preprocessor.load(name, False)
-
-    params = dict(
-        image_resolution=resolution,
-        detect_resolution=precessor_resolution,
-        low_threshold=low_threshold,
-        high_threshold=high_threshold,
-        thr_v=value_threshod,
-        thr_d=distance_threshold,
-        mode=recolor_mode,
-        gamma_correction=recolor_gamma_correction,
-        blur_sigma=blur_k_size,
-        hand_and_face=pre_openpose_extra,
-        scribble=hed_scribble,
-        safe=pre_pidinet_safe,
-        coarse=pre_lineart_coarse,
-    )
-
-    if use_cuda:
-        @spaces.GPU(duration=15)
-        def wrapped_func():
-            preprocessor.to("cuda")
-            return preprocessor(image, **params)
-        return wrapped_func()
-
-    return preprocessor(image, **params)
-
-
-def preprocessor_tab():
-    with gr.Row():
-        with gr.Column():
-            pre_image = gr.Image(label="Image", type="pil", sources=["upload"])
-            pre_options = gr.Dropdown(label="Preprocessor", choices=PREPROCESSOR_TASKS_LIST, value=PREPROCESSOR_TASKS_LIST[0])
-            pre_img_resolution = gr.Slider(
-                minimum=64, maximum=4096, step=64, value=1024, label="Image Resolution",
-                info="The maximum proportional size of the generated image based on the uploaded image."
-            )
-            pre_start = gr.Button(value="PROCESS IMAGE", variant="primary")
-            with gr.Accordion("Advanced Settings", open=False):
-                with gr.Column():
-                    pre_processor_resolution = gr.Slider(minimum=64, maximum=2048, step=64, value=512, label="Preprocessor Resolution")
-                    pre_low_threshold = gr.Slider(minimum=1, maximum=255, step=1, value=100, label="'CANNY' low threshold")
-                    pre_high_threshold = gr.Slider(minimum=1, maximum=255, step=1, value=200, label="'CANNY' high threshold")
-                    pre_value_threshold = gr.Slider(minimum=0., maximum=2.0, step=0.01, value=0.1, label="'MLSD' Hough value threshold")
-                    pre_distance_threshold = gr.Slider(minimum=0., maximum=20.0, step=0.01, value=0.1, label="'MLSD' Hough distance threshold")
-                    pre_recolor_mode = gr.Dropdown(label="'RECOLOR' mode", choices=["luminance", "intensity"], value="luminance")
-                    pre_recolor_gamma_correction = gr.Number(minimum=0., maximum=25., value=1., step=0.001, label="'RECOLOR' gamma correction")
-                    pre_blur_k_size = gr.Number(minimum=0, maximum=100, value=9, step=1, label="'BLUR' sigma")
-                    pre_openpose_extra = gr.Checkbox(value=True, label="'OPENPOSE' face and hand")
-                    pre_hed_scribble = gr.Checkbox(value=False, label="'HED' scribble")
-                    pre_pidinet_safe = gr.Checkbox(value=False, label="'PIDINET' safe")
-                    pre_lineart_coarse = gr.Checkbox(value=False, label="'LINEART' coarse")
-                    pre_use_cuda = gr.Checkbox(value=False, label="Use CUDA")
-
-        with gr.Column():
-            pre_result = gr.Image(label="Result", type="pil", interactive=False, format="png")
-
-            pre_start.click(
-                fn=process_inputs,
-                inputs=[
-                    pre_image,
-                    pre_options,
-                    pre_img_resolution,
-                    pre_processor_resolution,
-                    pre_low_threshold,
-                    pre_high_threshold,
-                    pre_value_threshold,
-                    pre_distance_threshold,
-                    pre_recolor_mode,
-                    pre_recolor_gamma_correction,
-                    pre_blur_k_size,
-                    pre_openpose_extra,
-                    pre_hed_scribble,
-                    pre_pidinet_safe,
-                    pre_lineart_coarse,
-                    pre_use_cuda,
-                ],
-                outputs=[pre_result],
-            )

packages.txt

@@ -1,3 +1,3 @@
 git-lfs
-aria2
+aria2 -y
 ffmpeg

pre-requirements.txt

@@ -1 +0,0 @@
-pip>=23.0.0

requirements.txt

@@ -1,13 +1,4 @@
-stablepy==0.6.2
-torch==2.5.1
-diffusers
+git+https://github.com/R3gm/stablepy.git@flux_beta
+torch==2.2.0
 gdown
-opencv-python
-unidecode
-pydantic==2.10.6
-huggingface_hub
-hf_transfer
-hf_xet
-spaces
-gradio==5.44.1
-matplotlib-inline
+opencv-python

utils.py

@@ -1,714 +0,0 @@
-import os
-import re
-import gradio as gr
-from constants import (
-    DIFFUSERS_FORMAT_LORAS,
-    CIVITAI_API_KEY,
-    HF_TOKEN,
-    MODEL_TYPE_CLASS,
-    DIRECTORY_LORAS,
-    DIRECTORY_MODELS,
-    DIFFUSECRAFT_CHECKPOINT_NAME,
-    CACHE_HF_ROOT,
-    CACHE_HF,
-    STORAGE_ROOT,
-)
-from huggingface_hub import HfApi, get_hf_file_metadata, snapshot_download
-from diffusers import DiffusionPipeline
-from huggingface_hub import model_info as model_info_data
-from diffusers.pipelines.pipeline_loading_utils import variant_compatible_siblings
-from stablepy.diffusers_vanilla.utils import checkpoint_model_type
-from pathlib import PosixPath
-from unidecode import unidecode
-import urllib.parse
-import copy
-import requests
-from requests.adapters import HTTPAdapter
-from urllib3.util import Retry
-import shutil
-import subprocess
-import json
-import html as _html
-
-IS_ZERO_GPU = bool(os.getenv("SPACES_ZERO_GPU"))
-USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:127.0) Gecko/20100101 Firefox/127.0'
-MODEL_ARCH = {
-    'stable-diffusion-xl-v1-base/lora': "Stable Diffusion XL (Illustrious, Pony, NoobAI)",
-    'stable-diffusion-v1/lora': "Stable Diffusion 1.5",
-    'flux-1-dev/lora': "Flux",
-}
-
-
-def read_safetensors_header_from_url(url: str):
-    """Read safetensors header from a remote Hugging Face file."""
-    meta = get_hf_file_metadata(url)
-
-    # Step 1: first 8 bytes → header length
-    resp = requests.get(meta.location, headers={"Range": "bytes=0-7"})
-    resp.raise_for_status()
-    header_len = int.from_bytes(resp.content, "little")
-
-    # Step 2: fetch full header JSON
-    end = 8 + header_len - 1
-    resp = requests.get(meta.location, headers={"Range": f"bytes=8-{end}"})
-    resp.raise_for_status()
-    header_json = resp.content.decode("utf-8")
-
-    return json.loads(header_json)
-
-
-def read_safetensors_header_from_file(path: str):
-    """Read safetensors header from a local file."""
-    with open(path, "rb") as f:
-        # Step 1: first 8 bytes → header length
-        header_len = int.from_bytes(f.read(8), "little")
-
-        # Step 2: read header JSON
-        header_json = f.read(header_len).decode("utf-8")
-
-    return json.loads(header_json)
-
-
-class LoraHeaderInformation:
-    """
-    Encapsulates parsed info from a LoRA JSON header and provides
-    a compact HTML summary via .to_html().
-    """
-
-    def __init__(self, json_data):
-        self.original_json = copy.deepcopy(json_data or {})
-
-        # Check if text encoder was trained
-        # guard for json_data being a mapping
-        try:
-            self.text_encoder_trained = any("text_model" in ln for ln in json_data)
-        except Exception:
-            self.text_encoder_trained = False
-
-        # Metadata (may be None)
-        metadata = (json_data or {}).get("__metadata__", None)
-        self.metadata = metadata
-
-        # Default values
-        self.architecture = "undefined"
-        self.prediction_type = "undefined"
-        self.base_model = "undefined"
-        self.author = "undefined"
-        self.title = "undefined"
-        self.common_tags_list = []
-
-        if metadata:
-            self.architecture = MODEL_ARCH.get(
-                metadata.get('modelspec.architecture', None),
-                "undefined"
-            )
-
-            self.prediction_type = metadata.get('modelspec.prediction_type', "undefined")
-            self.base_model = metadata.get('ss_sd_model_name', "undefined")
-            self.author = metadata.get('modelspec.author', "undefined")
-            self.title = metadata.get('modelspec.title', "undefined")
-
-            base_model_hash = metadata.get('ss_new_sd_model_hash', None)  # SHA256
-            # AUTOV1 ss_sd_model_hash
-            # https://civitai.com/api/v1/model-versions/by-hash/{base_model_hash}  # Info
-            if base_model_hash:
-                self.base_model += f" hash={base_model_hash}"
-
-            # Extract tags
-            try:
-                tags = metadata.get('ss_tag_frequency') if "ss_tag_frequency" in metadata else metadata.get('ss_datasets', "")
-                tags = json.loads(tags) if tags else ""
-
-                if isinstance(tags, list):
-                    tags = tags[0].get("tag_frequency", {})
-
-                if tags:
-                    self.common_tags_list = list(tags[list(tags.keys())[0]].keys())
-            except Exception:
-                self.common_tags_list = []
-
-    def to_dict(self):
-        """Return a plain dict summary of parsed fields."""
-        return {
-            "architecture": self.architecture,
-            "prediction_type": self.prediction_type,
-            "base_model": self.base_model,
-            "author": self.author,
-            "title": self.title,
-            "text_encoder_trained": bool(self.text_encoder_trained),
-            "common_tags": self.common_tags_list,
-        }
-
-    def to_html(self, limit_tags=20):
-        """
-        Return a compact HTML snippet (string) showing the parsed info
-        in a small font. Values are HTML-escaped.
-        """
-        # helper to escape
-        esc = _html.escape
-
-        rows = [
-            ("Title", esc(str(self.title))),
-            ("Author", esc(str(self.author))),
-            ("Architecture", esc(str(self.architecture))),
-            ("Base model", esc(str(self.base_model))),
-            ("Prediction type", esc(str(self.prediction_type))),
-            ("Text encoder trained", esc(str(self.text_encoder_trained))),
-            ("Reference tags", esc(str(", ".join(self.common_tags_list[:limit_tags])))),
-        ]
-
-        # small, compact table with inline styling (small font)
-        html_rows = "".join(
-            f"<tr><th style='text-align:left;padding:2px 6px;white-space:nowrap'>{k}</th>"
-            f"<td style='padding:2px 6px'>{v}</td></tr>"
-            for k, v in rows
-        )
-
-        html_snippet = (
-            "<div style='font-family:system-ui, -apple-system, \"Segoe UI\", Roboto, "
-            "Helvetica, Arial, \"Noto Sans\", sans-serif; font-size:12px; line-height:1.2; "
-            "'>"
-            f"<table style='border-collapse:collapse; font-size:12px;'>"
-            f"{html_rows}"
-            "</table>"
-            "</div>"
-        )
-
-        return html_snippet
-
-
-def request_json_data(url):
-    model_version_id = url.split('/')[-1]
-    if "?modelVersionId=" in model_version_id:
-        match = re.search(r'modelVersionId=(\d+)', url)
-        model_version_id = match.group(1)
-
-    endpoint_url = f"https://civitai.com/api/v1/model-versions/{model_version_id}"
-
-    params = {}
-    headers = {'User-Agent': USER_AGENT, 'content-type': 'application/json'}
-    session = requests.Session()
-    retries = Retry(total=5, backoff_factor=1, status_forcelist=[500, 502, 503, 504])
-    session.mount("https://", HTTPAdapter(max_retries=retries))
-
-    try:
-        result = session.get(endpoint_url, params=params, headers=headers, stream=True, timeout=(3.0, 15))
-        result.raise_for_status()
-        json_data = result.json()
-        return json_data if json_data else None
-    except Exception as e:
-        print(f"Error: {e}")
-        return None
-
-
-class ModelInformation:
-    def __init__(self, json_data):
-        self.model_version_id = json_data.get("id", "")
-        self.model_id = json_data.get("modelId", "")
-        self.download_url = json_data.get("downloadUrl", "")
-        self.model_url = f"https://civitai.com/models/{self.model_id}?modelVersionId={self.model_version_id}"
-        self.filename_url = next(
-            (v.get("name", "") for v in json_data.get("files", []) if str(self.model_version_id) in v.get("downloadUrl", "") and v.get("type", "Model") == "Model"), ""
-        )
-        self.filename_url = self.filename_url if self.filename_url else ""
-        self.description = json_data.get("description", "")
-        if self.description is None:
-            self.description = ""
-        self.model_name = json_data.get("model", {}).get("name", "")
-        self.model_type = json_data.get("model", {}).get("type", "")
-        self.nsfw = json_data.get("model", {}).get("nsfw", False)
-        self.poi = json_data.get("model", {}).get("poi", False)
-        self.images = [img.get("url", "") for img in json_data.get("images", [])]
-        self.example_prompt = json_data.get("trainedWords", [""])[0] if json_data.get("trainedWords") else ""
-        self.original_json = copy.deepcopy(json_data)
-
-
-def get_civit_params(url):
-    try:
-        json_data = request_json_data(url)
-        mdc = ModelInformation(json_data)
-        if mdc.download_url and mdc.filename_url:
-            return mdc.download_url, mdc.filename_url, mdc.model_url
-        else:
-            ValueError("Invalid Civitai model URL")
-    except Exception as e:
-        print(f"Error retrieving Civitai metadata: {e} — fallback to direct download")
-        return url, None, None
-
-
-def civ_redirect_down(url, dir_, civitai_api_key, romanize, alternative_name):
-    filename_base = filename = None
-
-    if alternative_name:
-        output_path = os.path.join(dir_, alternative_name)
-        if os.path.exists(output_path):
-            return output_path, alternative_name
-
-    # Follow the redirect to get the actual download URL
-    curl_command = (
-        f'curl -L -sI --connect-timeout 5 --max-time 5 '
-        f'-H "Content-Type: application/json" '
-        f'-H "Authorization: Bearer {civitai_api_key}" "{url}"'
-    )
-
-    headers = os.popen(curl_command).read()
-
-    # Look for the redirected "Location" URL
-    location_match = re.search(r'location: (.+)', headers, re.IGNORECASE)
-
-    if location_match:
-        redirect_url = location_match.group(1).strip()
-
-        # Extract the filename from the redirect URL's "Content-Disposition"
-        filename_match = re.search(r'filename%3D%22(.+?)%22', redirect_url)
-        if filename_match:
-            encoded_filename = filename_match.group(1)
-            # Decode the URL-encoded filename
-            decoded_filename = urllib.parse.unquote(encoded_filename)
-
-            filename = unidecode(decoded_filename) if romanize else decoded_filename
-            # print(f"Filename redirect: {filename}")
-
-    filename_base = alternative_name if alternative_name else filename
-    if not filename_base:
-        return None, None
-    elif os.path.exists(os.path.join(dir_, filename_base)):
-        return os.path.join(dir_, filename_base), filename_base
-
-    aria2_command = (
-        f'aria2c --console-log-level=error --summary-interval=10 -c -x 16 '
-        f'-k 1M -s 16 -d "{dir_}" -o "{filename_base}" "{redirect_url}"'
-    )
-    r_code = os.system(aria2_command)  # noqa
-
-    # if r_code != 0:
-    #     raise RuntimeError(f"Failed to download file: {filename_base}. Error code: {r_code}")
-
-    output_path = os.path.join(dir_, filename_base)
-    if not os.path.exists(output_path):
-        return None, filename_base
-
-    return output_path, filename_base
-
-
-def civ_api_down(url, dir_, civitai_api_key, civ_filename):
-    """
-    This method is susceptible to being blocked because it generates a lot of temp redirect links with aria2c.
-    If an API key limit is reached, generating a new API key and using it can fix the issue.
-    """
-    output_path = None
-
-    url_dl = url + f"?token={civitai_api_key}"
-    if not civ_filename:
-        aria2_command = f'aria2c -c -x 1 -s 1 -d "{dir_}" "{url_dl}"'
-        os.system(aria2_command)
-    else:
-        output_path = os.path.join(dir_, civ_filename)
-        if not os.path.exists(output_path):
-            aria2_command = (
-                f'aria2c --console-log-level=error --summary-interval=10 -c -x 16 '
-                f'-k 1M -s 16 -d "{dir_}" -o "{civ_filename}" "{url_dl}"'
-            )
-            os.system(aria2_command)
-
-    return output_path
-
-
-def drive_down(url, dir_):
-    import gdown
-
-    output_path = None
-
-    drive_id, _ = gdown.parse_url.parse_url(url, warning=False)
-    dir_files = os.listdir(dir_)
-
-    for dfile in dir_files:
-        if drive_id in dfile:
-            output_path = os.path.join(dir_, dfile)
-            break
-
-    if not output_path:
-        original_path = gdown.download(url, f"{dir_}/", fuzzy=True)
-
-        dir_name, base_name = os.path.split(original_path)
-        name, ext = base_name.rsplit(".", 1)
-        new_name = f"{name}_{drive_id}.{ext}"
-        output_path = os.path.join(dir_name, new_name)
-
-        os.rename(original_path, output_path)
-
-    return output_path
-
-
-def hf_down(url, dir_, hf_token, romanize):
-    url = url.replace("?download=true", "")
-    # url = urllib.parse.quote(url, safe=':/')  # fix encoding
-
-    filename = unidecode(url.split('/')[-1]) if romanize else url.split('/')[-1]
-    output_path = os.path.join(dir_, filename)
-
-    if os.path.exists(output_path):
-        return output_path
-
-    if "/blob/" in url:
-        url = url.replace("/blob/", "/resolve/")
-
-    if hf_token:
-        user_header = f'"Authorization: Bearer {hf_token}"'
-        os.system(f"aria2c --console-log-level=error --summary-interval=10 --header={user_header} -c -x 16 -k 1M -s 16 {url} -d {dir_}  -o {filename}")
-    else:
-        os.system(f"aria2c --optimize-concurrent-downloads --console-log-level=error --summary-interval=10 -c -x 16 -k 1M -s 16 {url} -d {dir_}  -o {filename}")
-
-    return output_path
-
-
-def download_things(directory, url, hf_token="", civitai_api_key="", romanize=False):
-    url = url.strip()
-    downloaded_file_path = None
-
-    if "drive.google.com" in url:
-        downloaded_file_path = drive_down(url, directory)
-    elif "huggingface.co" in url:
-        downloaded_file_path = hf_down(url, directory, hf_token, romanize)
-    elif "civitai.com" in url:
-        if not civitai_api_key:
-            msg = "You need an API key to download Civitai models."
-            print(f"\033[91m{msg}\033[0m")
-            gr.Warning(msg)
-            return None
-
-        url, civ_filename, civ_page = get_civit_params(url)
-        if civ_page and not IS_ZERO_GPU:
-            print(f"\033[92mCivitai model: {civ_filename} [page: {civ_page}]\033[0m")
-
-        downloaded_file_path, civ_filename = civ_redirect_down(url, directory, civitai_api_key, romanize, civ_filename)
-
-        if not downloaded_file_path:
-            msg = (
-                "Download failed.\n"
-                "If this is due to an API limit, generating a new API key may resolve the issue.\n"
-                "Attempting to download using the old method..."
-            )
-            print(msg)
-            gr.Warning(msg)
-            downloaded_file_path = civ_api_down(url, directory, civitai_api_key, civ_filename)
-    else:
-        os.system(f"aria2c --console-log-level=error --summary-interval=10 -c -x 16 -k 1M -s 16 -d {directory} {url}")
-
-    return downloaded_file_path
-
-
-def get_model_list(directory_path):
-    model_list = []
-    valid_extensions = {'.ckpt', '.pt', '.pth', '.safetensors', '.bin'}
-
-    for filename in os.listdir(directory_path):
-        if os.path.splitext(filename)[1] in valid_extensions:
-            # name_without_extension = os.path.splitext(filename)[0]
-            file_path = os.path.join(directory_path, filename)
-            # model_list.append((name_without_extension, file_path))
-            model_list.append(file_path)
-            print('\033[34mFILE: ' + file_path + '\033[0m')
-    return model_list
-
-
-def extract_parameters(input_string):
-    parameters = {}
-    input_string = input_string.replace("\n", "")
-
-    if "Negative prompt:" not in input_string:
-        if "Steps:" in input_string:
-            input_string = input_string.replace("Steps:", "Negative prompt: Steps:")
-        else:
-            msg = "Generation data is invalid."
-            gr.Warning(msg)
-            print(msg)
-            parameters["prompt"] = input_string
-            return parameters
-
-    parm = input_string.split("Negative prompt:")
-    parameters["prompt"] = parm[0].strip()
-    if "Steps:" not in parm[1]:
-        parameters["neg_prompt"] = parm[1].strip()
-        return parameters
-    parm = parm[1].split("Steps:")
-    parameters["neg_prompt"] = parm[0].strip()
-    input_string = "Steps:" + parm[1]
-
-    # Extracting Steps
-    steps_match = re.search(r'Steps: (\d+)', input_string)
-    if steps_match:
-        parameters['Steps'] = int(steps_match.group(1))
-
-    # Extracting Size
-    size_match = re.search(r'Size: (\d+x\d+)', input_string)
-    if size_match:
-        parameters['Size'] = size_match.group(1)
-        width, height = map(int, parameters['Size'].split('x'))
-        parameters['width'] = width
-        parameters['height'] = height
-
-    # Extracting other parameters
-    other_parameters = re.findall(r'([^,:]+): (.*?)(?=, [^,:]+:|$)', input_string)
-    for param in other_parameters:
-        parameters[param[0].strip()] = param[1].strip('"')
-
-    return parameters
-
-
-def get_my_lora(link_url, romanize):
-    l_name = ""
-    for url in [url.strip() for url in link_url.split(',')]:
-        if not os.path.exists(f"./loras/{url.split('/')[-1]}"):
-            l_name = download_things(DIRECTORY_LORAS, url, HF_TOKEN, CIVITAI_API_KEY, romanize)
-    new_lora_model_list = get_model_list(DIRECTORY_LORAS)
-    new_lora_model_list.insert(0, "None")
-    new_lora_model_list = new_lora_model_list + DIFFUSERS_FORMAT_LORAS
-    msg_lora = "Downloaded"
-    if l_name:
-        msg_lora += f": <b>{l_name}</b>"
-        print(msg_lora)
-
-    try:
-        # Works with non-Civitai loras.
-        json_data = read_safetensors_header_from_file(l_name)
-        metadata_lora = LoraHeaderInformation(json_data)
-        msg_lora += "<br>" + metadata_lora.to_html()
-    except Exception:
-        pass
-
-    return gr.update(
-        choices=new_lora_model_list
-    ), gr.update(
-        choices=new_lora_model_list
-    ), gr.update(
-        choices=new_lora_model_list
-    ), gr.update(
-        choices=new_lora_model_list
-    ), gr.update(
-        choices=new_lora_model_list
-    ), gr.update(
-        choices=new_lora_model_list
-    ), gr.update(
-        choices=new_lora_model_list
-    ), gr.update(
-        value=msg_lora
-    )
-
-
-def info_html(json_data, title, subtitle):
-    return f"""
-        <div style='padding: 0; border-radius: 10px;'>
-            <p style='margin: 0; font-weight: bold;'>{title}</p>
-            <details>
-                <summary>Details</summary>
-                <p style='margin: 0; font-weight: bold;'>{subtitle}</p>
-            </details>
-        </div>
-        """
-
-
-def get_model_type(repo_id: str):
-    api = HfApi(token=os.environ.get("HF_TOKEN"))  # if use private or gated model
-    default = "SD 1.5"
-    try:
-        if os.path.exists(repo_id):
-            tag, _, _, _ = checkpoint_model_type(repo_id)
-            return DIFFUSECRAFT_CHECKPOINT_NAME[tag]
-        else:
-            model = api.model_info(repo_id=repo_id, timeout=5.0)
-            tags = model.tags
-            for tag in tags:
-                if tag in MODEL_TYPE_CLASS.keys():
-                    return MODEL_TYPE_CLASS.get(tag, default)
-
-    except Exception:
-        return default
-    return default
-
-
-def restart_space(repo_id: str, factory_reboot: bool):
-    api = HfApi(token=os.environ.get("HF_TOKEN"))
-    try:
-        runtime = api.get_space_runtime(repo_id=repo_id)
-        if runtime.stage == "RUNNING":
-            api.restart_space(repo_id=repo_id, factory_reboot=factory_reboot)
-            print(f"Restarting space: {repo_id}")
-        else:
-            print(f"Space {repo_id} is in stage: {runtime.stage}")
-    except Exception as e:
-        print(e)
-
-
-def extract_exif_data(image):
-    if image is None:
-        return ""
-
-    try:
-        metadata_keys = ['parameters', 'metadata', 'prompt', 'Comment']
-
-        for key in metadata_keys:
-            if key in image.info:
-                return image.info[key]
-
-        return str(image.info)
-
-    except Exception as e:
-        return f"Error extracting metadata: {str(e)}"
-
-
-def create_mask_now(img, invert):
-    import numpy as np
-    import time
-
-    time.sleep(0.5)
-
-    transparent_image = img["layers"][0]
-
-    # Extract the alpha channel
-    alpha_channel = np.array(transparent_image)[:, :, 3]
-
-    # Create a binary mask by thresholding the alpha channel
-    binary_mask = alpha_channel > 1
-
-    if invert:
-        print("Invert")
-        # Invert the binary mask so that the drawn shape is white and the rest is black
-        binary_mask = np.invert(binary_mask)
-
-    # Convert the binary mask to a 3-channel RGB mask
-    rgb_mask = np.stack((binary_mask,) * 3, axis=-1)
-
-    # Convert the mask to uint8
-    rgb_mask = rgb_mask.astype(np.uint8) * 255
-
-    return img["background"], rgb_mask
-
-
-def download_diffuser_repo(repo_name: str, model_type: str, revision: str = "main", token=True):
-
-    variant = None
-    if token is True and not os.environ.get("HF_TOKEN"):
-        token = None
-
-    if model_type == "SDXL":
-        info = model_info_data(
-            repo_name,
-            token=token,
-            revision=revision,
-            timeout=5.0,
-        )
-
-        filenames = {sibling.rfilename for sibling in info.siblings}
-        model_filenames, variant_filenames = variant_compatible_siblings(
-            filenames, variant="fp16"
-        )
-
-        if len(variant_filenames):
-            variant = "fp16"
-
-    if model_type == "FLUX":
-        cached_folder = snapshot_download(
-            repo_id=repo_name,
-            allow_patterns="transformer/*"
-        )
-    else:
-        cached_folder = DiffusionPipeline.download(
-            pretrained_model_name=repo_name,
-            force_download=False,
-            token=token,
-            revision=revision,
-            # mirror="https://hf-mirror.com",
-            variant=variant,
-            use_safetensors=True,
-            trust_remote_code=False,
-            timeout=5.0,
-        )
-
-    if isinstance(cached_folder, PosixPath):
-        cached_folder = cached_folder.as_posix()
-
-    # Task model
-    # from huggingface_hub import hf_hub_download
-    # hf_hub_download(
-    #     task_model,
-    #     filename="diffusion_pytorch_model.safetensors",  # fix fp16 variant
-    # )
-
-    return cached_folder
-
-
-def get_folder_size_gb(folder_path):
-    result = subprocess.run(["du", "-s", folder_path], capture_output=True, text=True)
-
-    total_size_kb = int(result.stdout.split()[0])
-    total_size_gb = total_size_kb / (1024 ** 2)
-
-    return total_size_gb
-
-
-def get_used_storage_gb(path_storage=STORAGE_ROOT):
-    try:
-        used_gb = get_folder_size_gb(path_storage)
-        print(f"Used Storage: {used_gb:.2f} GB")
-    except Exception as e:
-        used_gb = 999
-        print(f"Error while retrieving the used storage: {e}.")
-
-    return used_gb
-
-
-def delete_model(removal_candidate):
-    print(f"Removing: {removal_candidate}")
-
-    if os.path.exists(removal_candidate):
-        os.remove(removal_candidate)
-    else:
-        diffusers_model = f"{CACHE_HF}{DIRECTORY_MODELS}--{removal_candidate.replace('/', '--')}"
-        if os.path.isdir(diffusers_model):
-            shutil.rmtree(diffusers_model)
-
-
-def clear_hf_cache():
-    """
-    Clears the entire Hugging Face cache at ~/.cache/huggingface.
-    Hugging Face will re-download models as needed later.
-    """
-    try:
-        if os.path.exists(CACHE_HF):
-            shutil.rmtree(CACHE_HF, ignore_errors=True)
-            print(f"Hugging Face cache cleared: {CACHE_HF}")
-        else:
-            print(f"No Hugging Face cache found at: {CACHE_HF}")
-    except Exception as e:
-        print(f"Error clearing Hugging Face cache: {e}")
-
-
-def progress_step_bar(step, total):
-    # Calculate the percentage for the progress bar width
-    percentage = min(100, ((step / total) * 100))
-
-    return f"""
-        <div style="position: relative; width: 100%; background-color: gray; border-radius: 5px; overflow: hidden;">
-            <div style="width: {percentage}%; height: 17px; background-color: #800080; transition: width 0.5s;"></div>
-            <div style="position: absolute; width: 100%; text-align: center; color: white; top: 0; line-height: 19px; font-size: 13px;">
-                {int(percentage)}%
-            </div>
-        </div>
-        """
-
-
-def html_template_message(msg):
-    return f"""
-        <div style="position: relative; width: 100%; background-color: gray; border-radius: 5px; overflow: hidden;">
-            <div style="width: 0%; height: 17px; background-color: #800080; transition: width 0.5s;"></div>
-            <div style="position: absolute; width: 100%; text-align: center; color: white; top: 0; line-height: 19px; font-size: 14px; font-weight: bold; text-shadow: 1px 1px 2px black;">
-                {msg}
-            </div>
-        </div>
-        """
-
-
-def escape_html(text):
-    """Escapes HTML special characters in the input text."""
-    return text.replace("<", "&lt;").replace(">", "&gt;").replace("\n", "<br>")