Instructions to use hf-internal-testing/flux.1-dev-nf4-pkg with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use hf-internal-testing/flux.1-dev-nf4-pkg with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("hf-internal-testing/flux.1-dev-nf4-pkg", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Running on gpu A100, cuda 12.2
#4
by almogbensim - opened
Hi, I got some problems while running this optimization on cuda 12.2.
The bitsandbytes library can't be imported with it because it suits for cuda 11.
I tried to change some env variable as CUDA_VERSION and similar ones.
There is any solution for it? or maybe another optimization for this case?
Thanks.