microsoft / microsoft/TRELLIS.2
multi-image inputs is worse
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 11.3k
- Forks
- 1.4k
- PR merge metrics
- No merged PRs in 30d
Description
check out here https://github.com/OpsiClear/Trellis2_multi_image_conditioning
Originally posted by @Allen-Zhou729 in #77
Hi, thank you for your contribution to the code: https://github.com/Allen-Zhou729/Trellis2_multiimage . I've noticed that the performance with multi-image inputs is surprisingly worse than with single-image inputs. Could you please explain what might be causing this? Also, are there any plans to optimize this in the future?
multi-image inputs result
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reviewing the multi-image implementation linked in the issue and comparing its behavior with the single-image path. Done means identifying why multi-image inputs perform worse and documenting or addressing the cause, with evidence from a reproducible comparison.
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
- 25/100