New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
无法加载clip interrogator / unable to load clip interrogator #172
Comments
手动更新torch和transformer后还是无法加载 |
How to use transformers==4.36.0 in a separate venv for Mixlab nodes (where can I get a step-by-step tutorial for configuring venv for a separate node in Comfi)? transformers==4.26.0 is needed for Blip Analize Image (WAS Node Suite) nodes to work correctly :``( |
You can't have a separate venv specifically for a custom node. You'll have to run the command in the venv for ComfyUI. |
This is disappointing, because some nodes stop working when there is a package version conflict. It would be great to find a way to run such nodes in a separate venv so that there are no version conflicts to run specific nodes. Every year there are more and more new cool nodes and the number of these conflicts is growing too. |
I just did an update to ComfyUI and was getting these errors, I just manually created the folders and git cloned them into the new folders and everything was up and running pretty quick. I don't know the correct solution, but that worked for me lol. Mixlab Nodes: LoadedLaMaInpainting.available True |
无法加载clip interrogator 这个节点,已经从hugging face 下载模型,并且放到model \ clip interrogator的目录下。
unable to load clip interrogator, I have downloaded models from hugging face, and save it into model \ clip interrogator.
Can someone help, plz.
The text was updated successfully, but these errors were encountered: