-
Notifications
You must be signed in to change notification settings - Fork 39
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
Fix tensors in different device error. #41
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
thanks! |
这是什么意思?不懂编程,博主能讲清楚点吗? |
@reitani Just download this file pulidflux.py and place it in this folder (overwrite the original file): |
I did that and it worked! Thank you so much for telling me! |
I tried this method but it didn't work. If you have the same issue, you can try using ComfyUI-PuLID-Flux-master instead of Enhanced. I noticed the error message indicated master, so I used the pulidflux.py mentioned above to overwrite the same file in master, and it worked successfully. |
找不到ComfyUI-PuLID-Flux-master这个节点,你有尝试过成功了吗?
|
think you so much,it's helped me |
thx, it saves my days |
@sipie800 Could you please merge the @broken-rotor 's PR? Fixes errors we still encounter in ComfyUI (already tested to the latest version) using PuLID Flux Enhanced : "Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! (when checking argument for argument weight in method wrapper_CUDA__native_layer_norm)" and "Enable Batch Processing >1 in Image Generation" |
Where can I download the master version? Tell me, I can't solve the error issue by any means either. |
@StanislavShashkov This PR is not merged yet so you need to download this file pulidflux.py and place it in this folder (overwrite the original file): |
I am also still getting this issue, after 1 or 2 queues it comes up with the "Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! (when checking argument for argument weight in method wrapper_CUDA__native_layer_norm)" error. I tried downloading the [pulidflux.py](https://github.com/sipie800/ComfyUI-PuLID-Flux-Enhanced/blob/95f15884511af22c49394c54227914a2bbc7bbb1/pulidflux.py) file and restarting, and I still have the error. I hope a fix comes soon. |
Do you have a full stack trace? |
error: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! (when checking argument for argument weight in method wrapper_CUDA__native_layer_norm) sipie800/ComfyUI-PuLID-Flux-Enhanced#41 sipie800/ComfyUI-PuLID-Flux-Enhanced#35
我这边出现的问题是覆盖并重启comfyui后提示缺失pulid节点,尝试修复再重启comfyui这个节点仍然缺失,只能卸载了这个节点重新安装,但又出现了最初的报错提示。可能我的配置存在错误? |
You're probably encountering this problem because @sipie800 already pulled an older PR (last week #51 ). So ... Try updating ComfyUI-PuLID-Flux-Enhanced and then modifying that file manually, following the changes made by @broken-rotor here: For reference (ONLY!), I have also attached my file, with which ComfyUI-PuLID-Flux-Enhanced works (on Win10/RTX4090). I hope this information helps you. |
This fixes #35 for me.