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

(github.com)

396 points doener | 1 comments | 30 Nov 25 11:36 UTC | HN request time: 0s | source

Show context

vunderba ◴[06 Dec 25 17:36 UTC] No.46175068[source]▶

>>46095817 (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):

https://imgpb.com/exMoQ

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.

replies(6): >>46175104 #>>46175331 #>>46177028 #>>46177043 #>>46177543 #>>46178707 #

echelon ◴[06 Dec 25 17:41 UTC] No.46175104[source]▶

>>46175068 #

So does this finally replace SDXL?

Is Flux 1/2/Kontext left in the dust by the Z Image and Qwen combo?

replies(3): >>46175236 #>>46175387 #>>46178341 #

1. vunderba ◴[06 Dec 25 18:21 UTC] No.46175387[source]▶

>>46175104 #

Yeah, I've definitely switched largely away from Flux. Much as I do like Flux (for prompt adherency), BFL's baffling licensing structure along with its excessive censorship makes it a noop.

For ref, the Porcupine-cone creature that ZiT couldn't handle by itself in my aforementioned test was easily handled using a Qwen20b + ZiT refiner workflow and even with two separate models STILL runs faster than Flux2 [dev].

https://imgur.com/a/5qYP0Vc

↑