Instructions to use Qwen/Qwen-Image-Edit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Qwen/Qwen-Image-Edit 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("Qwen/Qwen-Image-Edit", 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] - Inference
- Notebooks
- Google Colab
- Kaggle
Does Qwen-Image-Edit works with some images and with others not?
#42
by nourako - opened
I am a newbie and i am trying to using Qwen-Image-Edit in comfyui. I have a 4050 card and i use the smaller Qwen-Image-Edit-2509-Q2_K.gguf version of the model, and i run the workflow you have on the web page (image_qwen_image_edit.json with a small alteration to run the gguf model) although it works with some images with others it seems it doesn't do anything and just returns the same image as the input eg with the poster bellow when i say for example in the prompt "remove godzilla" or "translate the text" or "put a flower on the foreground". Maybe i am missing something. Thank you.
