import os if os.environ.get("SPACES_ZERO_GPU") is not None: import spaces else: class spaces: @staticmethod def GPU(func): def wrapper(*args, **kwargs): return func(*args, **kwargs) return wrapper import argparse from pathlib import Path import os import torch from diffusers import StableDiffusionXLPipeline, AutoencoderKL from transformers import CLIPTokenizer, CLIPTextModel import gradio as gr import shutil import gc # also requires aria, gdown, peft, huggingface_hub, safetensors, transformers, accelerate, pytorch_lightning from utils import (set_token, is_repo_exists, is_repo_name, get_download_file, upload_repo) @spaces.GPU def fake_gpu(): pass TEMP_DIR = "." DTYPE_DICT = { "fp16": torch.float16, "bf16": torch.bfloat16, "fp32": torch.float32, "fp8": torch.float8_e4m3fn } def get_dtype(dtype: str): return DTYPE_DICT.get(dtype, torch.float16) from diffusers import ( DPMSolverMultistepScheduler, DPMSolverSinglestepScheduler, KDPM2DiscreteScheduler, EulerDiscreteScheduler, EulerAncestralDiscreteScheduler, HeunDiscreteScheduler, LMSDiscreteScheduler, DDIMScheduler, DEISMultistepScheduler, UniPCMultistepScheduler, LCMScheduler, PNDMScheduler, KDPM2AncestralDiscreteScheduler, DPMSolverSDEScheduler, EDMDPMSolverMultistepScheduler, DDPMScheduler, EDMEulerScheduler, TCDScheduler, ) SCHEDULER_CONFIG_MAP = { "DPM++ 2M": (DPMSolverMultistepScheduler, {"use_karras_sigmas": False}), "DPM++ 2M Karras": (DPMSolverMultistepScheduler, {"use_karras_sigmas": True}), "DPM++ 2M SDE": (DPMSolverMultistepScheduler, {"use_karras_sigmas": False, "algorithm_type": "sde-dpmsolver++"}), "DPM++ 2M SDE Karras": (DPMSolverMultistepScheduler, {"use_karras_sigmas": True, "algorithm_type": "sde-dpmsolver++"}), "DPM++ 2S": (DPMSolverSinglestepScheduler, {"use_karras_sigmas": False}), "DPM++ 2S Karras": (DPMSolverSinglestepScheduler, {"use_karras_sigmas": True}), "DPM++ 1S": (DPMSolverMultistepScheduler, {"solver_order": 1}), "DPM++ 1S Karras": (DPMSolverMultistepScheduler, {"solver_order": 1, "use_karras_sigmas": True}), "DPM++ 3M": (DPMSolverMultistepScheduler, {"solver_order": 3}), "DPM++ 3M Karras": (DPMSolverMultistepScheduler, {"solver_order": 3, "use_karras_sigmas": True}), "DPM++ SDE": (DPMSolverSDEScheduler, {"use_karras_sigmas": False}), "DPM++ SDE Karras": (DPMSolverSDEScheduler, {"use_karras_sigmas": True}), "DPM2": (KDPM2DiscreteScheduler, {}), "DPM2 Karras": (KDPM2DiscreteScheduler, {"use_karras_sigmas": True}), "DPM2 a": (KDPM2AncestralDiscreteScheduler, {}), "DPM2 a Karras": (KDPM2AncestralDiscreteScheduler, {"use_karras_sigmas": True}), "Euler": (EulerDiscreteScheduler, {}), "Euler a": (EulerAncestralDiscreteScheduler, {}), "Euler trailing": (EulerDiscreteScheduler, {"timestep_spacing": "trailing", "prediction_type": "sample"}), "Euler a trailing": (EulerAncestralDiscreteScheduler, {"timestep_spacing": "trailing"}), "Heun": (HeunDiscreteScheduler, {}), "Heun Karras": (HeunDiscreteScheduler, {"use_karras_sigmas": True}), "LMS": (LMSDiscreteScheduler, {}), "LMS Karras": (LMSDiscreteScheduler, {"use_karras_sigmas": True}), "DDIM": (DDIMScheduler, {}), "DDIM trailing": (DDIMScheduler, {"timestep_spacing": "trailing"}), "DEIS": (DEISMultistepScheduler, {}), "UniPC": (UniPCMultistepScheduler, {}), "UniPC Karras": (UniPCMultistepScheduler, {"use_karras_sigmas": True}), "PNDM": (PNDMScheduler, {}), "Euler EDM": (EDMEulerScheduler, {}), "Euler EDM Karras": (EDMEulerScheduler, {"use_karras_sigmas": True}), "DPM++ 2M EDM": (EDMDPMSolverMultistepScheduler, {"solver_order": 2, "solver_type": "midpoint", "final_sigmas_type": "zero", "algorithm_type": "dpmsolver++"}), "DPM++ 2M EDM Karras": (EDMDPMSolverMultistepScheduler, {"use_karras_sigmas": True, "solver_order": 2, "solver_type": "midpoint", "final_sigmas_type": "zero", "algorithm_type": "dpmsolver++"}), "DDPM": (DDPMScheduler, {}), "DPM++ 2M Lu": (DPMSolverMultistepScheduler, {"use_lu_lambdas": True}), "DPM++ 2M Ef": (DPMSolverMultistepScheduler, {"euler_at_final": True}), "DPM++ 2M SDE Lu": (DPMSolverMultistepScheduler, {"use_lu_lambdas": True, "algorithm_type": "sde-dpmsolver++"}), "DPM++ 2M SDE Ef": (DPMSolverMultistepScheduler, {"algorithm_type": "sde-dpmsolver++", "euler_at_final": True}), "LCM": (LCMScheduler, {}), "TCD": (TCDScheduler, {}), "LCM trailing": (LCMScheduler, {"timestep_spacing": "trailing"}), "TCD trailing": (TCDScheduler, {"timestep_spacing": "trailing"}), "LCM Auto-Loader": (LCMScheduler, {}), "TCD Auto-Loader": (TCDScheduler, {}), } def get_scheduler_config(name): if not name in SCHEDULER_CONFIG_MAP.keys(): return SCHEDULER_CONFIG_MAP["Euler a"] return SCHEDULER_CONFIG_MAP[name] def save_readme_md(dir, url): orig_url = "" orig_name = "" if is_repo_name(url): orig_name = url orig_url = f"https://huggingface.co/{url}/" elif "http" in url: orig_name = url orig_url = url if orig_name and orig_url: md = f"""--- license: other language: - en library_name: diffusers pipeline_tag: text-to-image tags: - text-to-image --- Converted from [{orig_name}]({orig_url}). """ else: md = f"""--- license: other language: - en library_name: diffusers pipeline_tag: text-to-image tags: - text-to-image --- """ path = str(Path(dir, "README.md")) with open(path, mode='w', encoding="utf-8") as f: f.write(md) def fuse_loras(pipe, lora_dict={}, temp_dir=TEMP_DIR, civitai_key=""): if not lora_dict or not isinstance(lora_dict, dict): return pipe a_list = [] w_list = [] for k, v in lora_dict.items(): if not k: continue new_lora_file = get_download_file(temp_dir, k, civitai_key) if not new_lora_file or not Path(new_lora_file).exists(): print(f"LoRA not found: {k}") continue w_name = Path(new_lora_file).name a_name = Path(new_lora_file).stem pipe.load_lora_weights(new_lora_file, weight_name=w_name, adapter_name=a_name) a_list.append(a_name) w_list.append(v) if not a_list: return pipe pipe.set_adapters(a_list, adapter_weights=w_list) pipe.fuse_lora(adapter_names=a_list, lora_scale=1.0) pipe.unload_lora_weights() return pipe def convert_url_to_diffusers_sdxl(url, civitai_key="", is_upload_sf=False, dtype="fp16", vae="", clip="", scheduler="Euler a", lora_dict={}, is_local=True, progress=gr.Progress(track_tqdm=True)): progress(0, desc="Start converting...") temp_dir = TEMP_DIR new_file = get_download_file(temp_dir, url, civitai_key) if not new_file: print(f"Not found: {url}") return "" new_dir = Path(new_file).stem.replace(" ", "_").replace(",", "_").replace(".", "_") # kwargs = {} type_kwargs = {} if dtype != "default": type_kwargs["torch_dtype"] = get_dtype(dtype) new_vae_file = "" if vae: if is_repo_name(vae): my_vae = AutoencoderKL.from_pretrained(vae, **type_kwargs) else: new_vae_file = get_download_file(temp_dir, vae, civitai_key) my_vae = AutoencoderKL.from_single_file(new_vae_file, **type_kwargs) if new_vae_file else None if my_vae: kwargs["vae"] = my_vae if clip: my_tokenizer = CLIPTokenizer.from_pretrained(clip) if my_tokenizer: kwargs["tokenizer"] = my_tokenizer my_text_encoder = CLIPTextModel.from_pretrained(clip, **type_kwargs) if my_text_encoder: kwargs["text_encoder"] = my_text_encoder pipe = None if is_repo_name(url): pipe = StableDiffusionXLPipeline.from_pretrained(new_file, use_safetensors=True, **kwargs, **type_kwargs) else: pipe = StableDiffusionXLPipeline.from_single_file(new_file, use_safetensors=True, **kwargs, **type_kwargs) pipe = fuse_loras(pipe, lora_dict, temp_dir, civitai_key) sconf = get_scheduler_config(scheduler) pipe.scheduler = sconf[0].from_config(pipe.scheduler.config, **sconf[1]) pipe.save_pretrained(new_dir, safe_serialization=True, use_safetensors=True) if Path(new_dir).exists(): save_readme_md(new_dir, url) if not is_local: if not is_repo_name(new_file) and is_upload_sf: shutil.move(str(Path(new_file).resolve()), str(Path(new_dir, Path(new_file).name).resolve())) else: os.remove(new_file) del pipe torch.cuda.empty_cache() gc.collect() progress(1, desc="Converted.") return new_dir def convert_url_to_diffusers_repo(dl_url, hf_user, hf_repo, hf_token, civitai_key="", is_private=True, is_overwrite=False, is_upload_sf=False, urls=[], dtype="fp16", vae="", clip="", scheduler="Euler a", lora1=None, lora1s=1.0, lora2=None, lora2s=1.0, lora3=None, lora3s=1.0, lora4=None, lora4s=1.0, lora5=None, lora5s=1.0, progress=gr.Progress(track_tqdm=True)): is_local = False if not civitai_key and os.environ.get("CIVITAI_API_KEY"): civitai_key = os.environ.get("CIVITAI_API_KEY") # default Civitai API key if not hf_token and os.environ.get("HF_TOKEN"): hf_token = os.environ.get("HF_TOKEN") # default HF write token if not hf_user and os.environ.get("HF_USER"): hf_user = os.environ.get("HF_USER") # default username if not hf_user: raise gr.Error(f"Invalid user name: {hf_user}") if not hf_repo and os.environ.get("HF_REPO"): hf_repo = os.environ.get("HF_REPO") # default reponame set_token(hf_token) lora_dict = {lora1: lora1s, lora2: lora2s, lora3: lora3s, lora4: lora4s, lora5: lora5s} new_path = convert_url_to_diffusers_sdxl(dl_url, civitai_key, is_upload_sf, dtype, vae, clip, scheduler, lora_dict, is_local) if not new_path: return "" new_repo_id = f"{hf_user}/{Path(new_path).stem}" if hf_repo != "": new_repo_id = f"{hf_user}/{hf_repo}" if not is_repo_name(new_repo_id): raise gr.Error(f"Invalid repo name: {new_repo_id}") if not is_overwrite and is_repo_exists(new_repo_id): raise gr.Error(f"Repo already exists: {new_repo_id}") repo_url = upload_repo(new_repo_id, new_path, is_private) shutil.rmtree(new_path) if not urls: urls = [] urls.append(repo_url) md = "### Your new repo:\n" for u in urls: md += f"[{str(u).split('/')[-2]}/{str(u).split('/')[-1]}]({str(u)})
" return gr.update(value=urls, choices=urls), gr.update(value=md) if __name__ == "__main__": parser = argparse.ArgumentParser() parser.add_argument("--url", default=None, type=str, required=True, help="URL of the model to convert.") parser.add_argument("--dtype", default="fp16", type=str, choices=["fp16", "fp32", "bf16", "fp8", "default"], help='Output data type. (Default: "fp16")') parser.add_argument("--scheduler", default="Euler a", type=str, choices=list(SCHEDULER_CONFIG_MAP.keys()), required=False, help="Scheduler name to use.") parser.add_argument("--vae", default=None, type=str, required=False, help="URL of the VAE to use.") parser.add_argument("--civitai_key", default=None, type=str, required=False, help="Civitai API Key (If you want to download file from Civitai).") parser.add_argument("--lora1", default=None, type=str, required=False, help="URL of the LoRA to use.") parser.add_argument("--lora1s", default=1.0, type=float, required=False, help="LoRA weight scale of --lora1.") parser.add_argument("--lora2", default=None, type=str, required=False, help="URL of the LoRA to use.") parser.add_argument("--lora2s", default=1.0, type=float, required=False, help="LoRA weight scale of --lora2.") parser.add_argument("--lora3", default=None, type=str, required=False, help="URL of the LoRA to use.") parser.add_argument("--lora3s", default=1.0, type=float, required=False, help="LoRA weight scale of --lora3.") parser.add_argument("--lora4", default=None, type=str, required=False, help="URL of the LoRA to use.") parser.add_argument("--lora4s", default=1.0, type=float, required=False, help="LoRA weight scale of --lora4.") parser.add_argument("--lora5", default=None, type=str, required=False, help="URL of the LoRA to use.") parser.add_argument("--lora5s", default=1.0, type=float, required=False, help="LoRA weight scale of --lora5.") parser.add_argument("--loras", default=None, type=str, required=False, help="Folder of the LoRA to use.") args = parser.parse_args() assert args.url is not None, "Must provide a URL!" is_local = True lora_dict = {args.lora1: args.lora1s, args.lora2: args.lora2s, args.lora3: args.lora3s, args.lora4: args.lora4s, args.lora5: args.lora5s} if args.loras and Path(args.loras).exists(): for p in Path(args.loras).glob('**/*.safetensors'): lora_dict[str(p)] = 1.0 clip = "" convert_url_to_diffusers_sdxl(args.url, args.civitai_key, args.dtype, args.vae, clip, args.scheduler, lora_dict, is_local)