Support sd3.5 medium and MMDiT-X #2587
Merged
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
Czxck001
commented
Oct 30, 2024
| depth: 24, | ||
| head_size: 64, | ||
| adm_in_channels: 2048, | ||
| pos_embed_max_size: 384, |
There was a problem hiding this comment.
Notably, pos_embed_max_size for position embedding has been increased for SD3.5-medium, making it even bigger than SD3.5-large, which kept the original size of that of SD3-medium...
|
Amazing, thanks! |
super-fun-surf
pushed a commit
to aifx-art/candle
that referenced
this pull request
Oct 30, 2024
* extract attn out of joint_attn * further adjust attn and joint_attn * add mmdit-x support * support sd3.5-medium in the example * update README.md
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Outdated suggestions cannot be applied.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.
Stable Diffusion 3.5 Medium has been released on Oct 29, with modified archetecture named MMDiT-X. This PR adds support to the Stable Diffusion 3.5 Medium and MMDiT-X model.
Change is based on reference design sd3.5/mmdit-x.py in comparison with sd3-ref/mmdit.py, including
Note: A change has been made in sd3.5 after the release of Stable Diffusion 3.5 Medium on Oct 29 that fixes some bugs in the original reference design.
Implementation-wise,
attn2side track (namely "Self Attention"). None of the context-blocks have this extra attention. So the MMDiTXJointBlock is set to use this specification without further generalization.References:
Sample image generated with Stable Diffusion 3.5 Medium:
