modelscope / modelscope/DiffSynth-Studio
qwen-image如何读取本地目录下的模型
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 13.1k
- Forks
- 1.3k
- Avg merge
- 13h 12m
- Merged PRs (30d)
- 45
Description
这种方式是先下载模型，对于已经下载好的模型路径无法使用这种写法
pipe = QwenImagePipeline.from_pretrained(
torch_dtype=torch.bfloat16,
device="cuda",
model_configs=[
ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors"),
ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors"),
ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
],
tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
)
提供了ModelConfig(path="models/xxx.safetensors")，然而path一次只能加载一个文件，无法加载一个完整路径
还提供了local_model_path，这种用了报错
请问正确的完整的加载本地模型的代码是怎样的写法
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with QwenImagePipeline.from_pretrained and the ModelConfig and local_model_path handling shown in the issue. Reproduce the failure using a complete local model directory, then trace how its transformer, text encoder, VAE, and tokenizer files are resolved. Done means documenting or correcting a working local-loading path and verifying it against the reported setup.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 30/100