huggingface / huggingface/diffusers

How to finetune Flux-dev full params, 80G OOM ...

Open
#10,196 21 comments 1 reaction 1 assignee Claimed by @linoytsaban View on GitHub
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

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.