Simon Willison’s Weblog

Qwen-Image-Edit: Image Editing with Higher Quality and Efficiency. As promised in their August 4th release of the Qwen image generation model, Qwen have now followed it up with a separate model, Qwen-Image-Edit, which can take an image and a prompt and return an edited version of that image.

Ivan Fioravanti upgraded his macOS qwen-image-mps tool (previously) to run the new model via a new edit command. Since it's now on PyPI you can run it directly using uvx like this:

uvx qwen-image-mps edit -i pelicans.jpg \
  -p 'Give the pelicans rainbow colored plumage' -s 10

Be warned... it downloads a 54GB model file (to ~/.cache/huggingface/hub/models--Qwen--Qwen-Image-Edit) and appears to use all 64GB of my system memory - if you have less than 64GB it likely won't work, and I had to quit almost everything else on my system to give it space to run. A larger machine is almost required to use this.

I fed it this image:

The following prompt:

Give the pelicans rainbow colored plumage

And told it to use just 10 inference steps - the default is 50, but I didn't want to wait that long.

It still took nearly 25 minutes (on a 64GB M2 MacBook Pro) to produce this result:

To get a feel for how much dropping the inference steps affected things I tried the same prompt with the new "Image Edit" mode of Qwen's chat.qwen.ai, which I believe uses the same model. It gave me a result much faster that looked like this:

Update: I left the command running overnight without the -s 10 option - so it would use all 50 steps - and my laptop took 2 hours and 59 minutes to generate this image, which is much more photo-realistic and similar to the one produced by Qwen's hosted model:

Marko Simic reported that:

50 steps took 49min on my MBP M4 Max 128GB