Image-to-Image
Diffusers
English
Chinese
custom_qwen_image
image-generation
multimodal
qwen
quantized
nunchaku
comfyui
Instructions to use QuantFunc/Nunchaku-Qwen-Image-EDIT-2511 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use QuantFunc/Nunchaku-Qwen-Image-EDIT-2511 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("QuantFunc/Nunchaku-Qwen-Image-EDIT-2511", dtype=torch.bfloat16, device_map="cuda") prompt = "Turn this cat into a dog" input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png") image = pipe(image=input_image, prompt=prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Guide on how to create nunchaku weights
#5
by vibhavagarwal5 - opened
Hi, so good to see someone outside of the nunchaku team generating these weights, can you outline the process and the steps in order to achieve the same. What all is required and how to even do this via deepcompressor for other models if needed or even replicate this for your qwen models.
vibhavagarwal5 changed discussion title from How to create nunchaku weights to Guide on how to create nunchaku weights