New Lama inpainting model finetuned on larger datasets #498
Conversation
This file contains 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
litebeyond123
pushed a commit
to litebeyond123/manga-image-translator
that referenced
this pull request
Dec 16, 2023
New Lama inpainting model finetuned on larger datasets
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
New lama inpainter (big-lama) finetuned on 512x512 mixture of 300k manga and anime-style images, it performs much better on manga with screentone.
Also added bfloat16 inference for it, as it was finetuning with bf16 mixed precision, however, fp16 sometimes produces total black results when target resolution is high, I think it overflows somewhere performing fft.