microsoft / microsoft/TRELLIS

Regarding Multimodal Generation

Open
#316 0 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

Dear Authors,
Your work is truly remarkable. When testing the released pre-trained models, the generation results under separate image conditions and text conditions are both stunning. However, I noticed that the paper does not seem to mention the use of text and image simultaneously as conditional guidance, and I also found that the code does not support multimodal generation. Moreover, multimodal guided generation is an extremely useful method and also holds great significance in certain scenarios. May I ask if you have any follow-up work planned to support multimodal generation? Additionally, if I intend to modify the code myself to implement multimodal generation, what suggestions do you have regarding this?

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 by reviewing the released pre-trained models and the existing generation code, which the issue identifies as the relevant areas. The issue does not name specific files, tests, or entry points, and completion would require defining and validating multimodal image-and-text conditional generation.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-graphics, machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.