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
#614 0 comments 0 reactions 0 assignees View on GitHub
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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.