Instructions to use mit-han-lab/nunchaku with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use mit-han-lab/nunchaku with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("mit-han-lab/nunchaku", 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
We need nunchaku 0.3.0 wheel file,thank you
#3
by like8522 - opened
We need nunchaku 0.3.0 wheel file,thank you
hey, build few wheel files, it's worked for RTX4090 python3.10+torch2.6 and python3.11+torch2.7
Lmxyy changed discussion status to closed