import subprocess subprocess.run( 'pip install numpy==1.26.4', shell=True ) import os import gradio as gr import torch import spaces import random from PIL import Image import numpy as np from glob import glob from pathlib import Path from typing import Optional from diffsynth import save_video, ModelManager, SVDVideoPipeline from diffsynth import SDVideoPipeline, ControlNetConfigUnit, VideoData, save_frames from diffsynth.extensions.RIFE import RIFESmoother import requests def download_model(url, file_path): model_file = requests.get(url, allow_redirects=True) with open(file_path, "wb") as f: f.write(model_file.content) download_model("https://civitai.com/api/download/models/229575", "models/stable_diffusion/aingdiffusion_v12.safetensors") download_model("https://civitai.com/api/download/models/266360?type=Model&format=SafeTensor&size=pruned&fp=fp16", "models/stable_diffusion/flat2DAnimerge_v45Sharp.safetensors") download_model("https://huggingface.co/guoyww/animatediff/resolve/main/mm_sd_v15_v2.ckpt", "models/AnimateDiff/mm_sd_v15_v2.ckpt") download_model("https://huggingface.co/lllyasviel/ControlNet-v1-1/resolve/main/control_v11p_sd15_lineart.pth", "models/ControlNet/control_v11p_sd15_lineart.pth") download_model("https://huggingface.co/lllyasviel/ControlNet-v1-1/resolve/main/control_v11f1e_sd15_tile.pth", "models/ControlNet/control_v11f1e_sd15_tile.pth") download_model("https://huggingface.co/lllyasviel/Annotators/resolve/main/sk_model.pth", "models/Annotators/sk_model.pth") download_model("https://huggingface.co/lllyasviel/Annotators/resolve/main/sk_model2.pth", "models/Annotators/sk_model2.pth") download_model("https://civitai.com/api/download/models/25820?type=Model&format=PickleTensor&size=full&fp=fp16", "models/textual_inversion/verybadimagenegative_v1.3.pt") download_model("https://drive.google.com/file/d/1APIzVeI-4ZZCEuIRE1m6WYfSCaOsi_7_/view?usp=sharing", "models/RIFE/flownet.pkl") HF_TOKEN = os.environ.get("HF_TOKEN", None) # Constants MAX_SEED = np.iinfo(np.int32).max CSS = """ footer { visibility: hidden; } """ JS = """function () { gradioURL = window.location.href if (!gradioURL.endsWith('?__theme=dark')) { window.location.replace(gradioURL + '?__theme=dark'); } }""" # Ensure model and scheduler are initialized in GPU-enabled function if torch.cuda.is_available(): model_manager = ModelManager( torch_dtype=torch.float16, device="cuda", model_id_list=["stable-video-diffusion-img2vid-xt", "ExVideo-SVD-128f-v1"], downloading_priority=["HuggingFace"]) pipe = SVDVideoPipeline.from_model_manager(model_manager) model_manager2 = ModelManager(torch_dtype=torch.float16, device="cuda") model_manager2.load_textual_inversions("models/textual_inversion") model_manager2.load_models([ "models/stable_diffusion/flat2DAnimerge_v45Sharp.safetensors", "models/AnimateDiff/mm_sd_v15_v2.ckpt", "models/ControlNet/control_v11p_sd15_lineart.pth", "models/ControlNet/control_v11f1e_sd15_tile.pth", "models/RIFE/flownet.pkl" ]) pipe2 = SDVideoPipeline.from_model_manager( model_manager2, [ ControlNetConfigUnit( processor_id="lineart", model_path="models/ControlNet/control_v11p_sd15_lineart.pth", scale=0.5 ), ControlNetConfigUnit( processor_id="tile", model_path="models/ControlNet/control_v11f1e_sd15_tile.pth", scale=0.5 ) ] ) smoother = RIFESmoother.from_model_manager(model_manager2) def video_to_image(selected): if selected == "ExVideo": return gr.Image(label='Upload Image', height=600, scale=2, image_mode="RGB", type="filepath") @spaces.GPU(duration=120) def generate( media, selected, seed: Optional[int] = -1, num_inference_steps: int = 10, animatediff_batch_size: int = 32, animatediff_stride: int = 16, motion_bucket_id: int = 127, fps_id: int = 25, num_frames: int = 50, prompt: str = "best quality", output_folder: str = "outputs", progress=gr.Progress(track_tqdm=True)): print(media) if seed == -1: seed = random.randint(0, MAX_SEED) torch.manual_seed(seed) os.makedirs(output_folder, exist_ok=True) base_count = len(glob(os.path.join(output_folder, "*.mp4"))) video_path = os.path.join(output_folder, f"{base_count:06d}.mp4") if selected == "ExVideo": image = Image.open(media) video = pipe( input_image=image.resize((512, 512)), num_frames=num_frames, fps=fps_id, height=512, width=512, motion_bucket_id=motion_bucket_id, num_inference_steps=num_inference_steps, min_cfg_scale=2, max_cfg_scale=2, contrast_enhance_scale=1.2 ) model_manager.to("cpu") else: up_video = VideoData( video_file=media, height=1024, width=1024) input_video = [up_video[i] for i in range(40*60, 41*60)] video = pipe( prompt=prompt, negative_prompt="verybadimagenegative_v1.3", cfg_scale=3, clip_skip=2, controlnet_frames=input_video, num_frames=len(input_video), num_inference_steps=num_inference_steps, height=1024, width=1024, animatediff_batch_size=animatediff_batch_size, animatediff_stride=animatediff_stride, vram_limit_level=0, ) video = smoother(video) save_video(video, video_path, fps=fps_id) return video_path, seed examples = [ "./train.jpg", "./girl.webp", "./robo.jpg", './working.mp4', ] # Gradio Interface with gr.Blocks(css=CSS, js=JS, theme="soft") as demo: gr.HTML("