Instructions to use nunchaku-ai/nunchaku-qwen-image with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use nunchaku-ai/nunchaku-qwen-image 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-qwen-image", 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
Thank you!
#2
by Verole - opened
Can't wait to have it on comfyui. Thanks team.
Amazing news! Waiting to test it on Comfyui! You're the best!
im waiting for comfyui support
wait for comfyui
+1
🔥Nunchaku now supports SVDQuant 4-bit Qwen-Image in ComfyUI!
Please use the following versions:
• ComfyUI-nunchaku v1.0.0dev1 (Please use the main branch on GitHub. We haven't published it into the ComfyUI registry as it is still a dev version.)
📖 Example workflow: https://nunchaku.tech/docs/ComfyUI-nunchaku/workflows/qwenimage.html#nunchaku-qwen-image-json
✨ LoRA support will be available in upcoming updates!
Lmxyy changed discussion status to closed