microsoft / microsoft/TRELLIS

Anime Model Generation

Open
#70 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
13.7k
Forks
1.3k
PR merge metrics
No merged PRs in 30d

Description

Am I doing something wrong with the settings, or is this type of content just not generable?
Because, on one hand, with objects or characters that already have a sense of depth in the photo, I get good results. But as soon as I switch to a 2D style, anime, in this case, the proportions get really distorted, and the faces end up completely ruined and unrecognizable.

Examples with images and video:
Image
https://github.com/user-attachments/assets/b2484baa-da96-4256-af18-65d3cbbb510c

Image
https://github.com/user-attachments/assets/7c224263-30ed-4289-8ea3-5966d88feae6

Image
https://github.com/user-attachments/assets/756b6969-ff8e-4265-afbc-d35992b38229

Image
https://github.com/user-attachments/assets/9f81f1f0-17b6-4db9-905b-2cc33362f794

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

The report provides example images and videos but names no source file, test, or entry point. Start by reproducing the reported distortion for 2D anime inputs and reviewing the model-generation path; done would require an agreed diagnosis and a validated change or documented limitation.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-graphics, machine-learning
Issue type
Bug
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.