←back to thread

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

(github.com)
396 points doener | 3 comments | 30 Nov 25 11:36 UTC | HN request time: 0s | source
Show context
pawelduda ◴[06 Dec 25 17:10 UTC] No.46174861[source]▶
Did anyone test it on 5090? I saw some 30xx reports and it seemed very fast
replies(2): >>46175501 #>>46177259 #
Wowfunhappy ◴[06 Dec 25 18:35 UTC] No.46175501[source]▶
Even on my 4080 it's extremely fast, it takes ~15 seconds per image.
replies(1): >>46177791 #
1. accrual ◴[06 Dec 25 23:56 UTC] No.46177791[source]▶
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.
replies(1): >>46177830 #
2. Wowfunhappy ◴[07 Dec 25 00:01 UTC] No.46177830[source]▶
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.)

replies(1): >>46177979 #
3. accrual ◴[07 Dec 25 00:19 UTC] No.46177979[source]▶
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.