Fix arcface loading for non-CUDA devices #19
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
@slezica Thanks for creating the PR. Just one comment about the model path.. |
YuminJia
reviewed
Jul 7, 2025
| def init_arcface_model(device='cuda'): | ||
| model = arcface_arch.Backbone(num_layers=50, drop_ratio=0.6, mode='ir_se').to(device).eval() | ||
|
|
||
| model_path = load_file_from_url(url=ARCFACE_MODEL_URL, model_dir='facexlib/weights') |
There was a problem hiding this comment.
can we store the model file in the comfyUI/models folder?
There was a problem hiding this comment.
Yes! There's no need to load it from URL, it can be loaded from a local file. That would actually be nicer in my personal opinion, I just copied the way it was done under the hood by the arcface module, to avoid loading the PR with other changes
|
This solved my issues. I'm on Mac. Kept getting "Torch not compiled with CUDA enabled" errors. Thanks a lot. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Fixes #11
.cuda()call inextract_arcface_bgr_embeddingfacexlib.recognition.init_recognition_modelwith own utility function