|
--- |
|
library_name: diffusers |
|
license: other |
|
license_name: flux-1-dev-non-commercial-license |
|
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md |
|
--- |
|
|
|
## Running Flux.1-dev under 12GBs |
|
|
|
This repository contains the NF4 params for the T5 and transformer of Flux.1-Dev. Check out this [Colab Notebook](https://colab.research.google.com/gist/sayakpaul/4af4d6642bd86921cdc31e5568b545e1/scratchpad.ipynb) for details on how they were obtained. |
|
|
|
Check out [this notebook](https://colab.research.google.com/gist/sayakpaul/8fb27a653934c1bc6b013913c346e456/scratchpad.ipynb) that shows how to use the checkpoints and run in a free-tier Colab Notebook. |
|
|
|
Respective `diffusers` PR: https://github.com/huggingface/diffusers/pull/9213/. |
|
|
|
> [!NOTE] |
|
> The checkpoints of this repository were optimized to run on a T4 notebook. More specifically, the compute datatype of the quantized checkpoints was kept to FP16. In practice, if you have a GPU card that supports BF16, you should change the compute datatype to BF16 (`bnb_4bit_compute_dtype`). |
