# -*- coding: utf-8 -*- # Copyright 2024-2025 The Alibaba Wan Team Authors. All rights reserved import spaces import logging,os os.makedirs("/root/weights",exist_ok=True) cmd="huggingface-cli download IndexTeam/AnisoraV3 --include=\"14B/*\" --local-dir=/root/weights --token %s"%os.environ['token'] os.system(cmd) # os.environ["HF_ENDPOINT"] = "https://hf-mirror.com" from time import time as ttime import argparse from datetime import datetime import logging import sys import warnings from fastapi import FastAPI import uvicorn import gradio as gr warnings.filterwarnings('ignore') import torch, random import torch.distributed as dist from PIL import Image import wan from wan.image2video_if_oss import WanI2V from wan.configs import WAN_CONFIGS, SIZE_CONFIGS, MAX_AREA_CONFIGS, SUPPORTED_SIZES from wan.utils.prompt_extend import DashScopePromptExpander, QwenPromptExpander from wan.utils.utils import cache_video, cache_image, str2bool value2speed={ "原版":0, "加速版":1, } EXAMPLE_PROMPT = { "t2v-1.3B": { "prompt": "Two anthropomorphic cats in comfy boxing gear and bright gloves fight intensely on a spotlighted stage.", }, "t2v-14B": { "prompt": "Two anthropomorphic cats in comfy boxing gear and bright gloves fight intensely on a spotlighted stage.", }, "t2i-14B": { "prompt": "一个朴素端庄的美人", }, "i2v-14B": { "prompt": "Summer beach vacation style, a white cat wearing sunglasses sits on a surfboard. The fluffy-furred feline gazes directly at the camera with a relaxed expression. Blurred beach scenery forms the background featuring crystal-clear waters, distant green hills, and a blue sky dotted with white clouds. The cat assumes a naturally relaxed posture, as if savoring the sea breeze and warm sunlight. A close-up shot highlights the feline's intricate details and the refreshing atmosphere of the seaside.", "image": "examples/i2v_input.JPG", }, } def _validate_args(args): # Basic check assert args.ckpt_dir is not None, "Please specify the checkpoint directory." assert args.task in WAN_CONFIGS, f"Unsupport task: {args.task}" assert args.task in EXAMPLE_PROMPT, f"Unsupport task: {args.task}" # The default sampling steps are 40 for image-to-video tasks and 50 for text-to-video tasks. if args.sample_steps is None: args.sample_steps = 40 if "i2v" in args.task else 50 if args.sample_shift is None: args.sample_shift = 5.0 if "i2v" in args.task and args.size in ["832*480", "480*832"]: args.sample_shift = 3.0 # The default number of frames are 1 for text-to-image tasks and 81 for other tasks. if args.frame_num is None: args.frame_num = 1 if "t2i" in args.task else 81 # T2I frame_num check if "t2i" in args.task: assert args.frame_num == 1, f"Unsupport frame_num {args.frame_num} for task {args.task}" args.base_seed = args.base_seed if args.base_seed >= 0 else random.randint( 0, sys.maxsize) # Size check assert args.size in SUPPORTED_SIZES[ args. task], f"Unsupport size {args.size} for task {args.task}, supported sizes are: {', '.join(SUPPORTED_SIZES[args.task])}" def _parse_args(): parser = argparse.ArgumentParser( description="Generate a image or video from a text prompt or image using Wan" ) parser.add_argument( "--task", type=str, default="i2v-14B", choices=list(WAN_CONFIGS.keys()), help="The task to run.") parser.add_argument( "--size", type=str, default="960*544", choices=list(SIZE_CONFIGS.keys()), help="The area (width*height) of the generated video. For the I2V task, the aspect ratio of the output video will follow that of the input image." ) parser.add_argument( "--frame_num", type=int, default=None, help="How many frames to sample from a image or video. The number should be 4n+1" ) parser.add_argument( "--ckpt_dir", type=str, default="/root/weights/14B", help="The path to the checkpoint directory.") parser.add_argument( "--offload_model", type=str2bool, default=None, help="Whether to offload the model to CPU after each model forward, reducing GPU memory usage." ) parser.add_argument( "--ulysses_size", type=int, default=1, help="The size of the ulysses parallelism in DiT.") parser.add_argument( "--ring_size", type=int, default=1, help="The size of the ring attention parallelism in DiT.") parser.add_argument( "--t5_fsdp", action="store_true", default=False, help="Whether to use FSDP for T5.") parser.add_argument( "--t5_cpu", action="store_true", default=False, help="Whether to place T5 model on CPU.") parser.add_argument( "--dit_fsdp", action="store_true", default=False, help="Whether to use FSDP for DiT.") parser.add_argument( "--save_file", type=str, default=None, help="The file to save the generated image or video to.") parser.add_argument( "--prompt", type=str, default=None, help="The prompt to generate the image or video from.") parser.add_argument( "--use_prompt_extend", action="store_true", default=False, help="Whether to use prompt extend.") parser.add_argument( "--prompt_extend_method", type=str, default="local_qwen", choices=["dashscope", "local_qwen"], help="The prompt extend method to use.") parser.add_argument( "--prompt_extend_model", type=str, default=None, help="The prompt extend model to use.") parser.add_argument( "--prompt_extend_target_lang", type=str, default="ch", choices=["ch", "en"], help="The target language of prompt extend.") parser.add_argument( "--base_seed", type=int, default=-1, help="The seed to use for generating the image or video.") parser.add_argument( "--image", type=str, default=None, help="The image to generate the video from.") parser.add_argument( "--sample_solver", type=str, default='unipc', choices=['unipc', 'dpm++'], help="The solver used to sample.") parser.add_argument( "--sample_steps", type=int, default=None, help="The sampling steps.") parser.add_argument( "--sample_shift", type=float, default=None, help="Sampling shift factor for flow matching schedulers.") parser.add_argument( "--sample_guide_scale", type=float, default=5.0, help="Classifier free guidance scale.") args = parser.parse_args() _validate_args(args) return args def _init_logging(rank): # logging if rank == 0: # set format logging.basicConfig( level=logging.INFO, format="[%(asctime)s] %(levelname)s: %(message)s", handlers=[logging.StreamHandler(stream=sys.stdout)]) else: logging.basicConfig(level=logging.ERROR) def generate(args): rank = int(os.getenv("RANK", 0)) world_size = int(os.getenv("WORLD_SIZE", 1)) local_rank = int(os.getenv("LOCAL_RANK", 0)) device = local_rank _init_logging(rank) if args.offload_model is None: args.offload_model = False if world_size > 1 else True logging.info( f"offload_model is not specified, set to {args.offload_model}.") cfg = WAN_CONFIGS[args.task] if args.ulysses_size > 1: assert cfg.num_heads % args.ulysses_size == 0, f"`num_heads` must be divisible by `ulysses_size`." logging.info(f"Generation job args: {args}") logging.info(f"Generation model config: {cfg}") if dist.is_initialized(): base_seed = [args.base_seed] if rank == 0 else [None] dist.broadcast_object_list(base_seed, src=0) args.base_seed = base_seed[0] logging.info("Creating WanI2V pipeline.") # wan_i2v = wan.WanI2V( wan_i2v = WanI2V( config=cfg, checkpoint_dir=args.ckpt_dir, device_id=device, rank=rank, t5_fsdp=args.t5_fsdp, dit_fsdp=args.dit_fsdp, use_usp=(args.ulysses_size > 1 or args.ring_size > 1), t5_cpu=args.t5_cpu, ) @spaces.GPU(duration=298.8) def generate_i2v(prompt,img,seed,nf,speed): logging.info("Generating video ...") save_file="output/%s-%s-%s-%s.mp4"%(seed,nf,speed,int(ttime())) video = wan_i2v.generate( prompt, img, max_area=MAX_AREA_CONFIGS[args.size], frame_num=int(nf)*16+1,#args.frame_num shift=args.sample_shift, sample_solver=args.sample_solver, sampling_steps=args.sample_steps, guide_scale=args.sample_guide_scale, seed=seed,#args.base_seed, offload_model=args.offload_model, speed=value2speed[speed] ) if rank==0: video_update = gr.update(visible=True, value=save_file) seed_update = gr.update(visible=True, value=seed) cache_video( tensor=video[None], save_file=save_file, fps=cfg.sample_fps, nrow=1, normalize=True, value_range=(-1, 1)) return save_file, video_update, seed_update if rank == 0: from app_os import DEMO demo=DEMO(generate_i2v).demo demo.launch() if __name__ == "__main__": args = _parse_args() generate(args)