Conversation
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
This branch has not been deployed
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
For using vae tiling which is required to be able to run the model at high resoltuions with consumer GPUs, the default tiling values produce seams and even artifacts, this PR change the defaults values to the minimal ones that don't produce them.
For a 2048x2048 image like the one in the examples, it requires ~27GB of VRAM to decode it, with these values for tiling it requires ~4.4GB of VRAM. Any smaller sizes will produce the seams, at 512/256 they are thinner but I could still see them.
To reproduce this issue, just do inference with vae tiling.
@sayakpaul @naykun