Instructions to use diffusers/FLUX.1-dev-bnb-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use diffusers/FLUX.1-dev-bnb-8bit with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("diffusers/FLUX.1-dev-bnb-8bit", 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
- Local Apps
- Draw Things
- DiffusionBee
Release Time of PipelineQuantizationConfig
#1
by Boynn - opened
Hi, I saw PipelineQuantizationConfig in diffusers repo code but it hasnt packaged in the latest release. So as far for now, we could just use this hf repo's pre-quantized model.
And I'm wonder when it would be release?, it's a great job, thx.
~15 days. Thanks for the kind words!
sayakpaul changed discussion status to closed