请问模型在本地下载好了，如何加载？

[lify]

因为从hugging上自动下载总是会因为网络问题出错，所以自主下载了传入text encoder和vae这两个模型，下载好之后代码里如何加入这两个模型？

[github-actions]

This issue is stale because it has been open for 7 days with no activity.

[Zheng Zangwei (Alex Zheng)]

抱歉我们之前没考虑到用户自主下载的问题。作用一个临时解决方案，huggingface from_pretrained 能支持 cache_dir 这个参数。在 opensora/models/vae/vae.py 和 opensora/models/text_encoder/t5.py 中找到 from_pretrained，将其中 cache_dir 更换为你的本地文件夹。这个本地文件夹的组织方式应该和 huggingface 的 .cache 一致。具体而言：

> ls models--DeepFloyd--t5-v1_1-xxl
blobs  refs  snapshots

[github-actions]

This issue is stale because it has been open for 7 days with no activity.

[github-actions]

This issue was closed because it has been inactive for 7 days since being marked as stale.