Spaces:
Running
on
Zero
Running
on
Zero
| import torch | |
| import os | |
| import cv2 | |
| import numpy as np | |
| from config import Config | |
| from diffusers import ( | |
| ControlNetModel, | |
| LCMScheduler | |
| ) | |
| from diffusers.models.controlnets.multicontrolnet import MultiControlNetModel | |
| # Import the custom pipeline from your local file | |
| from pipeline_stable_diffusion_xl_instantid_img2img import StableDiffusionXLInstantIDImg2ImgPipeline | |
| from huggingface_hub import snapshot_download, hf_hub_download | |
| from insightface.app import FaceAnalysis | |
| # --- MODIFIED: Import new detectors --- | |
| from controlnet_aux import LeresDetector, LineartAnimeDetector | |
| # --- END MODIFIED --- | |
| class ModelHandler: | |
| def __init__(self): | |
| self.pipeline = None | |
| self.app = None # InsightFace | |
| # --- MODIFIED: Rename detectors --- | |
| self.leres_detector = None | |
| self.lineart_anime_detector = None | |
| # --- END MODIFIED --- | |
| self.face_analysis_loaded = False | |
| def load_face_analysis(self): | |
| """ | |
| Load face analysis model. | |
| Downloads from HF Hub to the path insightface expects. | |
| Forces CPU to avoid ZeroGPU initialization errors. | |
| """ | |
| print("Loading face analysis model...") | |
| # insightface expects models in '{root}/models/{name}' | |
| # Since our root='.' and name='antelopev2', the expected path is './models/antelopev2' | |
| model_path = os.path.join(Config.ANTELOPEV2_ROOT, "models", Config.ANTELOPEV2_NAME) | |
| if not os.path.exists(os.path.join(model_path, "scrfd_10g_bnkps.onnx")): | |
| print(f"Downloading AntelopeV2 models from {Config.ANTELOPEV2_REPO} to {model_path}...") | |
| try: | |
| snapshot_download( | |
| repo_id=Config.ANTELOPEV2_REPO, | |
| local_dir=model_path, # Download to the correct expected path | |
| ) | |
| except Exception as e: | |
| print(f" [ERROR] Failed to download AntelopeV2 models: {e}") | |
| return False | |
| try: | |
| # Initialize with root='.' and name='antelopev2' | |
| self.app = FaceAnalysis( | |
| name=Config.ANTELOPEV2_NAME, | |
| root=Config.ANTELOPEV2_ROOT, | |
| providers=['CPUExecutionProvider'] | |
| ) | |
| self.app.prepare(ctx_id=0, det_size=(640, 640)) | |
| print(f" [OK] Face analysis model loaded successfully.") | |
| return True | |
| except Exception as e: | |
| print(f" [WARNING] Face detection system failed to initialize: {e}") | |
| return False | |
| def load_models(self): | |
| # 1. Load Face Analysis | |
| self.face_analysis_loaded = self.load_face_analysis() | |
| # 2. Load ControlNets | |
| print("Loading ControlNets (InstantID, Zoe, LineArt)...") | |
| # Load the InstantID ControlNet from the correct subfolder | |
| print("Loading InstantID ControlNet from subfolder 'ControlNetModel'...") | |
| cn_instantid = ControlNetModel.from_pretrained( | |
| Config.INSTANTID_REPO, # "InstantX/InstantID" | |
| subfolder="ControlNetModel", # Correct casing | |
| torch_dtype=Config.DTYPE | |
| ) | |
| print(" [OK] Loaded InstantID ControlNet.") | |
| # Load other ControlNets normally | |
| print("Loading Zoe and LineArt ControlNets...") | |
| cn_zoe = ControlNetModel.from_pretrained(Config.CN_ZOE_REPO, torch_dtype=Config.DTYPE) | |
| cn_lineart = ControlNetModel.from_pretrained(Config.CN_LINEART_REPO, torch_dtype=Config.DTYPE) | |
| # --- Manually wrap the list of models in a MultiControlNetModel --- | |
| print("Wrapping ControlNets in MultiControlNetModel...") | |
| controlnet_list = [cn_instantid, cn_zoe, cn_lineart] | |
| controlnet = MultiControlNetModel(controlnet_list) | |
| # --- End wrapping --- | |
| # 3. Load SDXL Pipeline | |
| print(f"Loading SDXL Pipeline ({Config.CHECKPOINT_FILENAME})...") | |
| # Manually download the checkpoint file first. | |
| checkpoint_local_path = os.path.join("./models", Config.CHECKPOINT_FILENAME) | |
| if not os.path.exists(checkpoint_local_path): | |
| print(f"Downloading checkpoint to {checkpoint_local_path}...") | |
| hf_hub_download( | |
| repo_id=Config.REPO_ID, | |
| filename=Config.CHECKPOINT_FILENAME, | |
| local_dir="./models", | |
| local_dir_use_symlinks=False | |
| ) | |
| # Use the custom Img2Img pipeline class you provided, loading from the LOCAL FILE | |
| print(f"Loading pipeline from local file: {checkpoint_local_path}") | |
| self.pipeline = StableDiffusionXLInstantIDImg2ImgPipeline.from_single_file( | |
| checkpoint_local_path, # Pass the local path | |
| controlnet=controlnet, # Pass the single, wrapped object | |
| torch_dtype=Config.DTYPE, | |
| use_safetensors=True | |
| ) | |
| self.pipeline.to(Config.DEVICE) | |
| # 4. Set Scheduler | |
| self.pipeline.scheduler = LCMScheduler.from_config(self.pipeline.scheduler.config) | |
| # 5. Load Adapters (IP-Adapter & LoRA) | |
| print("Loading Adapters (IP-Adapter & LoRA)...") | |
| # Download the ip-adapter.bin file and pass its local path | |
| ip_adapter_filename = "ip-adapter.bin" | |
| ip_adapter_local_path = os.path.join("./models", ip_adapter_filename) | |
| if not os.path.exists(ip_adapter_local_path): | |
| print(f"Downloading IP-Adapter to {ip_adapter_local_path}...") | |
| hf_hub_download( | |
| repo_id=Config.INSTANTID_REPO, | |
| filename=ip_adapter_filename, | |
| local_dir="./models", | |
| local_dir_use_symlinks=False | |
| ) | |
| print(f"Loading IP-Adapter from local file: {ip_adapter_local_path}") | |
| self.pipeline.load_ip_adapter_instantid(ip_adapter_local_path) # Pass local path | |
| print("Loading LoRA weights...") | |
| self.pipeline.load_lora_weights(Config.REPO_ID, weight_name=Config.LORA_FILENAME) | |
| # --- NEW: Fuse LoRA at build time with fixed strength --- | |
| print(f"Fusing LoRA with scale {Config.LORA_STRENGTH}...") | |
| self.pipeline.fuse_lora(lora_scale=Config.LORA_STRENGTH) | |
| print(" [OK] LoRA fused.") | |
| # --- DISABLED torch.compile due to runtime errors --- | |
| # try: | |
| # print("Compiling UNet with torch.compile...") | |
| # self.pipeline.unet = torch.compile(self.pipeline.unet, mode="reduce-overhead", fullgraph=True) | |
| # print(" [OK] UNet compiled.") | |
| # except Exception as e: | |
| # print(f" [WARNING] torch.compile failed: {e}. Running without compilation.") | |
| # 6. Load Preprocessors | |
| # --- MODIFIED: Load new detectors --- | |
| print("Loading Preprocessors (LeReS, LineArtAnime)...") | |
| self.leres_detector = LeresDetector.from_pretrained(Config.ANNOTATOR_REPO) | |
| self.lineart_anime_detector = LineartAnimeDetector.from_pretrained(Config.ANNOTATOR_REPO) | |
| # --- END MODIFIED --- | |
| print("--- All models loaded successfully ---") | |
| def get_face_embedding(self, image): | |
| """Extracts face embedding, returns None if no face is found.""" | |
| if not self.face_analysis_loaded: | |
| return None | |
| try: | |
| # Convert PIL to CV2 | |
| # --- FIX: Corrected OpenCV attribute --- | |
| cv2_img = cv2.cvtColor(np.array(image), cv2.COLOR_RGB2BGR) | |
| faces = self.app.get(cv2_img) | |
| if len(faces) == 0: | |
| return None | |
| # Sort by size (width * height) to find the main character | |
| faces = sorted(faces, key=lambda x: (x['bbox'][2]-x['bbox'][0])*(x['bbox'][3]-x['bbox'][1]), reverse=True) | |
| # Return the largest face | |
| return torch.tensor(faces[0].normed_embedding).unsqueeze(0) | |
| except Exception as e: | |
| print(f"Face embedding extraction failed: {e}") | |
| return None |