Image-to-Image
Diffusers
Safetensors
English
Image-to-Image
ControlNet
Diffusers
QwenImageControlNetPipeline
Qwen-Image
Instructions to use InstantX/Qwen-Image-ControlNet-Union with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use InstantX/Qwen-Image-ControlNet-Union 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("InstantX/Qwen-Image-ControlNet-Union", 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
will there be a edit version?
#2
by jasoncow - opened
,,,to control the charactor already been created
PLaying around with just chucking controlnets in the edit workflow it seems to work. It's a bit funny coz the edit model is like a nonlocalised controlnet, so it fights itself trying to be more like the reference image while trying to be more like control net, even with strength of cn at 1 and 0-100% start-end step.
Prompts like "Maintaining the character(/object/style etc), change this image completely." Seem to help