Skip to content
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 the OFT/BOFT bugs when using new LyCORIS implementation #14973

Merged
merged 4 commits into from
Feb 26, 2024

Conversation

KohakuBlueleaf
Copy link
Collaborator

Checklist:


def calc_updown(self, orig_weight):
oft_blocks = self.oft_blocks.to(orig_weight.device)
eye = torch.eye(self.block_size, device=oft_blocks.device)

if self.is_kohya:
if not self.is_R:
block_Q = oft_blocks - oft_blocks.transpose(1, 2) # ensure skew-symmetric orthogonal matrix
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@KohakuBlueleaf I used 2.1.0.post3 to train a new boft and diag-oft
boft got an error during inference
56M0QF 3B{W$IZR~9I%YMG3

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@KohakuBlueleaf I used 2.1.0.post3 to train a new boft and diag-oft boft got an error during inference 56M0QF 3B{W$IZR~9I%YMG3

Got it

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@KohakuBlueleaf I used 2.1.0.post3 to train a new boft and diag-oft boft got an error during inference 56M0QF 3B{W$IZR~9I%YMG3

Try new Commit

Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks , boft looks like work,
And I found that diag-oft needs to specify "constrain" in training, otherwise it doesn’t take effect.
Is it a bug?
xyz_grid-0000-528576219

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks , boft looks like work, And I found that diag-oft needs to specify "constrain" in training, otherwise it doesn’t take effect. Is it a bug? xyz_grid-0000-528576219

It is bug

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@Exist-c fixed

Copy link

@Enferlain Enferlain Feb 29, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Noticed the same thing with my diag-oft so went to find if anything has been updated, but after pulling the changes there is an error about 'MultiHeadAttention' object has no attribute 'weight'

send help pls image

edit just don't train TE, works fine

@AUTOMATIC1111 AUTOMATIC1111 merged commit 900419e into dev Feb 26, 2024
6 checks passed
@AUTOMATIC1111 AUTOMATIC1111 deleted the Fix-new-oft-boft branch February 26, 2024 04:12
AUTOMATIC1111 added a commit that referenced this pull request Feb 26, 2024
Fix the OFT/BOFT bugs when using new LyCORIS implementation
@pawel665j pawel665j mentioned this pull request Apr 16, 2024
ruchej pushed a commit to ruchej/stable-diffusion-webui that referenced this pull request Sep 30, 2024
…-boft

Fix the OFT/BOFT bugs when using new LyCORIS implementation
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants