modelscope / modelscope/DiffSynth-Studio

按照Wan2.1的推理手册运行出现问题

Open
#1,080 1 comment 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
13.1k
Forks
1.3k
Avg merge
13h 12m
Merged PRs (30d)
45

Description

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
pipe.enable_vram_management()
File "/workspace/DiffSynth-Studio/diffsynth/pipelines/wan_video_new.py", line 135, in enable_vram_management
vram_limit = self.get_vram()
^^^^^^^^^^^^^^^
File "/workspace/DiffSynth-Studio/diffsynth/utils/init.py", line 132, in get_vram
return torch.cuda.mem_get_info(self.device)[1] / (1024 ** 3)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/conda/lib/python3.11/site-packages/torch/cuda/memory.py", line 684, in mem_get_info
device = _get_device_index(device)
^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/conda/lib/python3.11/site-packages/torch/cuda/_utils.py", line 38, in _get_device_index
return _torch_get_device_index(device, optional, allow_cpu)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/conda/lib/python3.11/site-packages/torch/_utils.py", line 803, in _get_device_index
raise ValueError(
ValueError: Expected a torch.device with a specified index or an integer, but got:cuda

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Reproduce the failure with the provided test.py example, then inspect diffsynth/pipelines/wan_video_new.py around enable_vram_management and diffsynth/utils/init.py around get_vram. Trace how the configured CUDA device reaches torch.cuda.mem_get_info, and verify the example completes past VRAM management without the device-index error.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
2/5
Estimated time
1-3 hours
Activity status
Stale
Clarity
Clearly specified
Newbie friendliness
45/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.