kohya-ss / kohya-ss/sd-scripts
How to train an image with multiple resolutions?
Open
- Dominant language
- Python
- Stars
- 7.2k
- Forks
- 1.2k
- Avg merge
- 11m
- Merged PRs (30d)
- 2
Description
Is it a bug that an image specifies different resolutions in different datasets. subsets, but the same image ultimately appears to only use one resolution?
Contributor guide
No contributing guide indexed for this repository
Research direction
Start by reproducing the reported setup and trace how the training process handles an image assigned different resolutions across dataset subsets. Done means answering whether the behavior is expected and documenting the relevant training procedure or a reproducible bug; no files or tests are named.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100