Add Hunyuan 3D 2.1 Support #8714
Open
+1,370
−119
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
fixed not returning y in the forward method of MoEBlock
yousef-rafat
changed the title
and Image Processor
yousef-rafat
requested review from
yoland68,
robinjhuang,
pythongosssss,
ltdrdata,
Kosinkadink,
webfiltered and
christian-byrne
as code owners
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Outdated suggestions cannot be applied.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.
I have created the reimplementation of the VAE. The main contributions are in rewriting/avoiding the use of unnecessary libraries and modularizing the code by removing code redundancy and better structuring of the code.
The implemented VAE is faster by approximately 5 seconds in the encoding process and 2 seconds in the decoding process.
The fps.py file contains the implementation of Farthest Point Sampling, avoiding using torch_cluster. The preprocess.py contains the Volume Decoder, Surface Extractor, and Trimesh exporting. The point_attention.py contains the code for the encoder. The transformer.py contains the code for the Transformer model that is used in the geo decoder of the VAE and the Self-Attention in the encoder. The vae.py contains the VAE code along with a test example.