kohya-ss / kohya-ss/sd-scripts
whether I choose to train_text_encoder or not, the memory occupied is basically the same. Is this situation normal?
Open
- Dominant language
- Python
- Stars
- 7.2k
- Forks
- 1.2k
- Avg merge
- 11m
- Merged PRs (30d)
- 2
Description
whether I choose to train_text_encoder or not, the memory occupied is basically the same. Is this situation normal?
i use fune_tune.py script.
Contributor guide
No contributing guide indexed for this repository
Research direction
Start with the fune_tune.py entry point and trace how the train_text_encoder option affects model loading and memory allocation. Compare runs with the option enabled and disabled, then document whether the observed memory usage is expected or identify the allocation path responsible.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100