modelscope / modelscope/DiffSynth-Studio
How to train Qwen Image on 4090, getting non stop OOM no matter what I set up the config to.
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 13.1k
- Forks
- 1.3k
- Avg merge
- 13h 12m
- Merged PRs (30d)
- 45
Description
I’m unable to train Qwen-Image on a 24GB GPU — it always runs into CUDA OOM.
Steps I already tried:
export PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True--enable_fp8_training--use_gradient_checkpointing--gradient_accumulation_steps 2--max_pixels 262144
Even with these, the model immediately runs out of memory on 24GB card
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
The report names no file, test, or training entry point. Start by reproducing Qwen-Image training on a 24GB GPU with the listed memory settings and capture the exact command and failure details. Done means identifying a reproducible cause and supported configuration, or documenting that this setup cannot fit in 24GB.
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
- Mostly clear
- Newbie friendliness
- 25/100