Z-Image: Powerful and highly efficient image generation model with 6B parameters

>>doener+(OP)
I've done some preliminary testing with Z-Image Turbo in the past week.

Thoughts

- It's fast (~3 seconds on my RTX 4090)

- Surprisingly capable of maintaining image integrity even at high resolutions (1536x1024, sometimes 2048x2048)

- The adherence is impressive for a 6B parameter model

Some tests (2 / 4 passed):

Personally I find it works better as a refiner model downstream of Qwen-Image 20b which has significantly better prompt understanding but has an unnatural "smoothness" to its generated images.

>>vunder+fCk
> It's fast (~3 seconds on my RTX 4090)

It is amazing how far behind Apple Silicon is when it comes to use non- language models.

Using the reference code from Z-image on my M1 ultra, it takes 8 seconds per step. Over a minute for the default of 9 steps.

>>tarrud+R7l
The diffusion process is usually compute-bound, while transformer inference is memory-bound.

Apple Silicon is comparable in memory bandwidth to mid-range GPUs, but it’s light years behind on compute.

>>p-e-w+mkl
> but it’s light years behind on compute.

Is that the only factor though? I wonder if pytorch is lacking optimization for the MPS backend.

zlacker