Document Flux2Pipeline latents shape #12807
Open
+5
−0
Conversation
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
Contributor
|
This issue has been automatically marked as stale because it has not had recent activity. If you think this still needs to be addressed please comment on this thread. Please note that issues that do not follow the contributing guidelines are likely to be ignored. |
Collaborator
|
can you run make fix-copies? |
Collaborator
|
@bot /style |
Contributor
|
Style fix is beginning .... View the workflow run here. |
|
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. |
preetam1407
force-pushed
the
docs/flux2-latents-shape
branch
from
543a4b3 to
a530e7d
Compare
preetam1407
force-pushed
the
docs/flux2-latents-shape
branch
from
a530e7d to
f8f8d9d
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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Outdated suggestions cannot be applied.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.
Fixes #12755.
This PR documents the expected shape of the
latentsargument inFlux2Pipeline.__call__.For the default
AutoencoderKLFlux2VAE used by FLUX.2, the pipeline first applies 8× spatial compression in the VAE,and then a 2×2 patch packing step in the pipeline. This results in:
The expected shape for user-provided latents is therefore:
(batch_size, 128, height // 16, width // 16)where
heightandwidthare the requested output image size. Passing latents with a different shape leads to shapemismatches inside the VAE and transformer.
Tests
(1, 128, H // 16, W // 16)runs end-to-end with the FLUX.2-dev checkpoint.