modelscope / modelscope/DiffSynth-Studio

how to reduce video memory when running lora

Open
#1,201 3 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
13.1k
Forks
1.3k
Avg merge
13h 12m
Merged PRs (30d)
45

Description

HI

when I run qwen-image lora using this script, https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/qwen_image/model_training/lora/Qwen-Image-2512.sh, how do I reduce the video memory requirement?

I would like to have a try on the consumer GPUs, so the video memory is 32G or 48G. could you help share some solutions? I have tried to reduce the number of rank to be 16, but still OOM

Thanks

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reading examples/qwen_image/model_training/lora/Qwen-Image-2512.sh and identify which settings affect the reported out-of-memory behavior. Reproduce the run with the available memory constraints, then document validated changes that allow training on 32G or 48G GPUs, including any limitations.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Documentation
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.