microsoft / microsoft/TRELLIS.2

Sparse structure of 3d model after training SC-VAE

Open
#133 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
11.3k
Forks
1.4k
PR merge metrics
No merged PRs in 30d

Description

Hello
I've trained SC-VAE, get .pt model and convert it to .safetensors, but my 3d model has sparse structure of 3d model
I've used this code to convert model to safetensor: https://github.com/jeffeDurand/TRELLIS/blob/main/convert_safetensors.py, and original training code
What i did wrong?
Input image:
Image

Resulting model:
Image

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with convert_safetensors.py and the original training code referenced in the report; reproduce the .pt-to-.safetensors conversion and inspect where the sparse 3D result first appears. Compare the input image, resulting model, and checkpoint-loading path, then document the cause and a correction verified by a non-sparse result.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-graphics, machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.