-
Notifications
You must be signed in to change notification settings - Fork 5.2k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[Community Pipeline
] Add 🪆Matryoshka Diffusion Models
#9157
Draft
tolgacangoz
wants to merge
49
commits into
huggingface:main
Choose a base branch
from
tolgacangoz:Add-Matryoshka-Diffusion-Models
base: main
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Draft
[Community Pipeline
] Add 🪆Matryoshka Diffusion Models
#9157
tolgacangoz
wants to merge
49
commits into
huggingface:main
from
tolgacangoz:Add-Matryoshka-Diffusion-Models
+4,074
−1
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
tolgacangoz
changed the title
Add Matryoshka Diffusion Models
Add 🪆Matryoshka Diffusion Models
Aug 12, 2024
@tolgacangoz would you have cycles to work on this soon? Another contributor has expressed interest in working on it. Maybe you two could collaborate? |
I am into the inference code atm. Will the training code in |
For now, we don't have to focus on training. |
…t_down_block` for FF layers in attention
tolgacangoz
changed the title
Add 🪆Matryoshka Diffusion Models
[Sep 7, 2024
Community Pipeline
] Add 🪆Matryoshka Diffusion Models
…r for Matryoshka models
…tryoshkaTransformer2DModelOutput`
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.
Thanks for the opportunity to work on this model!
The Abstract of the paper (emphasis is mine):
Paper: 🪆Matryoshka Diffusion Models
Repository: https://github.com/apple/ml-mdm
License: MIT license
Key takeaways from the paper:
None
; since Matryoshka Diffusion Models work on the (extended) pixel space(s).flan-t5-xl
TODOs:
✅ The U-Net; in other words, the inner-most structure,
NestedUNet2DConditionModel(nesting_level=0)
; approximately would be as follows:⏳ Scheduler(s)
⬜
NestedUNet2DConditionModel(nesting_level=(1, 2))
✅
convert_matryoshka_model_to_diffusers.py
⏳ Verify outputs with the original implementation for:
64×64, nesting_level=0
256×256, nesting_level=1
1024×1024, nesting_level=2
⬜ Show example results
⏳ Upload converted checkpoints to HF
⬜
README.md
❓
examples/**/train_matryoshka.py