kohya-ss / kohya-ss/sd-scripts
Influence of seed
Open
- Dominant language
- Python
- Stars
- 7.2k
- Forks
- 1.2k
- Avg merge
- 11m
- Merged PRs (30d)
- 2
Description
Hi @kohya-ss, I've noticed that the result of a dreambooth training can deviate a lot when changing the seed. What exactly does the seed influence when passing it to `sdxl_train.py` and what happens if I don't pass the seed?
Contributor guide
No contributing guide indexed for this repository
Research direction
Start by reading the seed handling and training entry point in sdxl_train.py. Trace what the seed affects and the behavior when it is omitted, then document both cases with enough context to explain why DreamBooth results can differ.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- documentation, machine-learning
- Issue type
- Documentation
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100