Movatterモバイル変換


[0]ホーム

URL:


Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

feat: add support for underline style lora of flux#1103

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 ourterms of service andprivacy statement. We’ll occasionally send you account related emails.

Already on GitHub?Sign in to your account

Open
leejet wants to merge3 commits intomaster
base:master
Choose a base branch
Loading
fromflux_underline_lora

Conversation

@leejet
Copy link
Owner

No description provided.

Green-Sky and ddpasa reacted with thumbs up emoji
@ddpasa
Copy link

This improves#1092 . Text encoders are still not completely loaded, but it looks like the transformer is fine after this.

@leejet
Copy link
OwnerAuthor

@ddpasa This update should make the LoRA for text_encoders work. However, I couldn’t find a corresponding LoRA to test it with. If you could upload a LoRA to HuggingFace or Civitai for me to download and test, I would really appreciate it.

@ddpasa
Copy link

@ddpasa This update should make the LoRA for text_encoders work. However, I couldn’t find a corresponding LoRA to test it with. If you could upload a LoRA to HuggingFace or Civitai for me to download and test, I would really appreciate it.

Thanks@leejet , I uploaded an example Lora here:https://huggingface.co/ddhfacc/lora_debug/tree/main It has T5 and Clip layers as well.

Pulling the additional commit did not reduce the number of unused lora layers for me.

@leejet
Copy link
OwnerAuthor

@ddpasa Everything should be ok now.

@ddpasa
Copy link

@ddpasa Everything should be ok now.

I think so, testing now. I don't see similar errors in the log after6bff0d9. I'll generate a few and compare with Comfy.

@ddpasa
Copy link

I generated multiple images, as far as I can tell, it works great now. Thanks for fixing this!

Sign up for freeto join this conversation on GitHub. Already have an account?Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@leejet@ddpasa

[8]ページ先頭

©2009-2025 Movatter.jp