huggingface / huggingface/diffusers
How to finetune Flux-dev full params, 80G OOM ...
Open
training
- Dominant language
- Python
- Stars
- 34.5k
- Forks
- 7.3k
- Avg merge
- 3d 3h
- Merged PRs (30d)
- 91
Description
I am using the [train_dreambooth_flux](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/train_dreambooth_flux.py) script to fine-tune the `flux-dev` model with full parameters using DeepSpeed Stage 2. However, I am still encountering out-of-memory issues on an 80GB GPU. Are there any solutions available to address this problem? Thanks!
Contributor guide
Assessment
This issue has not been assessed yet.