Incredibly fast, on my 5090 with CUDA 13 (& the latest diffusers, xformers, transformers, etc...), 9 samplig steps and the "Tongyi-MAI/Z-Image-Turbo" model I get:

- 1.5s to generate an image at 512x512

- 3.5s to generate an image at 1024x1024

- 26.s to generate an image at 2048x2048

It uses almost all the 32Gb Gb of VRAM and GPU usage. I'm using the script from the HF post: https://huggingface.co/Tongyi-MAI/Z-Image-Turbo

Weird, even at 2048 I don’t think it should be using all your 32GB VRAM.

It stays around 26Gb at 512x512. I still haven't profiled the execution or looked much into the details of the architecture but I would assume it trades off memory for speed by creating caches for each inference step

IDK. Seems odd. It’s an 11GB model, I don’t know what it could caching in ram.

Even on my 4080 it's extremely fast, it takes ~15 seconds per image.

Did you use PyTorch Native or Diffusers Inference? I couldn't get the former working yet so I used Diffusers, but it's terribly slow on my 4080 (4 min/image). Trying again with PyTorch now, seems like Diffusers is expected to be slow.

Uh, not sure? I downloaded the portable build of ComfyUI and ran the CUDA-specific batch file it comes with.

(I'm not used to using Windows and I don't know how to do anything complicated on that OS. Unfortunately, the computer with the big GPU also runs Windows.)

Haha, I know how it goes. Thanks, I'll give that a try!

Update: works great and much faster via ComfyUI + the provided workflow file.