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

prompt handler: check for index error before requesting caption | vaecache: more robust handling of batched encoding | vaecache: fix for trailing slash existing in cache_dir property resulting in excessive scans at startup | bucket manager: cheaply remove duplicate images from the dataset during sorting | aspect bucketing: modify precision of bucket categories to 3 decimals from 2, this might require re-caching aspect buckets and VAE outputs | sd2.x: LoRA training fixes, still not quite right, but better | DoRA: initial support from PEFT integrated for XL and legacy models. #320

Merged
merged 9 commits into from
Feb 28, 2024

Conversation

bghira
Copy link
Owner

@bghira bghira commented Feb 28, 2024

No description provided.

bghira added 9 commits February 26, 2024 07:32
…, we hit a condition with mixed tensor sizes. this resolves that
vaecache: pass a value through the queue to ensure that the final sample in a given aspect bucket is processed immediately, avoiding mismatched tensors for high vae batch sizes.

logging: unfortunately, a lot more debug spam. sorry in advance
@bghira bghira merged commit 396ff92 into release Feb 28, 2024
1 check passed
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.

1 participant