Instructions to use nunchaku-ai/nunchaku with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use nunchaku-ai/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("nunchaku-ai/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 Settings
- Draw Things
- DiffusionBee
adapter FLUX2 klein
๐ 4
#8 opened 7 months ago
by
TJundx
Please adapt zai-org/GLM-Image
#7 opened 7 months ago
by
TJundx
ๅ่ๆฃ็่ฝฎๅญๆฑๅฉ
โ 3
#6 opened 8 months ago
by
dblfeng
nunchaku-1.1.0+torch2.8-cp312-cp312-win_amd64.whl
๐ 2
2
#5 opened 8 months ago
by
makisekurisu-jp
Nunchaku 1.0.2 is compatible with transformer<4.57 only but Qwen3 VL only works under transformer 4.57.1 or above
#4 opened 9 months ago
by
anitman
please, add 2.9 support
#3 opened 10 months ago
by
vvhitevvizard
When will you release nunchaku for wan?
โค๏ธ 5
#2 opened 10 months ago
by
Faint6005
no wheel file for torch 2.4
1
#1 opened 12 months ago
by
arksam