Skip to content

Conversation

@kuantuna
Copy link
Contributor

What does this PR do?

This PR fixes the same issue that was recently addressed in AutoencoderKLMochi, where tile_latent_min_width was incorrectly calculated using tile_sample_stride_width instead of tile_sample_min_width.

The same mistake was found in the following autoencoders:

This update ensures consistent and correct behavior across all affected models when VAE tiling is enabled.

Fixes: #11291.

Who can review?

@a-r-r-o-w

Copy link
Contributor

@a-r-r-o-w a-r-r-o-w left a comment

Choose a reason for hiding this comment

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

Tysm for the awesome catch! 👁️

@HuggingFaceDocBuilderDev

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.

@a-r-r-o-w a-r-r-o-w merged commit 36538e1 into huggingface:main Apr 13, 2025
12 checks 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.

Inconsistent variable usage in tile_latent_min_width computation in AutoencoderKLMochi decoder

3 participants