按照Wan2.1的推理手册运行出现问题
按照手册指导的通过运行以下代码可以快速加载 Wan-AI/Wan2.1-T2V-1.3B 模型并进行推理
import torch from diffsynth import save_video from diffsynth.pipelines.wan_video_new import WanVideoPipeline, ModelConfig
pipe = WanVideoPipeline.from_pretrained( torch_dtype=torch.bfloat16, device="cuda", model_configs=[ ModelConfig(model_id="Wan-AI/Wan2.1-T2V-1.3B", origin_file_pattern="diffusion_pytorch_model*.safetensors", offload_device="cpu"), ModelConfig(model_id="Wan-AI/Wan2.1-T2V-1.3B", origin_file_pattern="models_t5_umt5-xxl-enc-bf16.pth", offload_device="cpu"), ModelConfig(model_id="Wan-AI/Wan2.1-T2V-1.3B", origin_file_pattern="Wan2.1_VAE.pth", offload_device="cpu"), ], ) pipe.enable_vram_management()
video = pipe( prompt="纪实摄影风格画面,一只活泼的小狗在绿茵茵的草地上迅速奔跑。小狗毛色棕黄,两只耳朵立起,神情专注而欢快。阳光洒在它身上,使得毛发看上去格外柔软而闪亮。背景是一片开阔的草地,偶尔点缀着几朵野花,远处隐约可见蓝天和几片白云。透视感鲜明,捕捉小狗奔跑时的动感和四周草地的生机。中景侧面移动视角。", negative_prompt="色调艳丽,过曝,静态,细节模糊不清,字幕,风格,作品,画作,画面,静止,整体发灰,最差质量,低质量,JPEG压缩残留,丑陋的,残缺的,多余的手指,画得不好的手部,画得不好的脸部,畸形的,毁容的,形态畸形的肢体,手指融合,静止不动的画面,杂乱的背景,三条腿,背景人很多,倒着走", seed=0, tiled=True, ) save_video(video, "video1.mp4", fps=15, quality=5)
报错信息:
Traceback (most recent call last):
File "/workspace/DiffSynth-Studio/test.py", line 14, in
参考 #659 将torch版本升级到2.6.0后解决了此问题.