Remix.run Logo
vunderba 4 hours ago

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.

amrrs 3 hours ago | parent | next [-]

On fal, it takes less than a second many times.

https://fal.ai/models/fal-ai/z-image/turbo/api

Couple that with the LoRA, in about 3 seconds you can generate completely personalized images.

The speed alone is a big factor but if you put the model side by side with seedream and nanobanana and other models it's definitely in the top 5 and that's killer combo imho.

echelon 4 hours ago | parent | prev [-]

So does this finally replace SDXL?

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

vunderba 3 hours ago | parent | next [-]

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

tripplyons 3 hours ago | parent | prev [-]

SDXL has been outclassed for a while, especially since Flux came out.

aeon_ai 3 hours ago | parent [-]

Subjective. Most in creative industries regularly still use SDXL.

Once Z-image base comes out and some real tuning can be done, I think it has a chance of replacing it for the function SDXL has

Scrapemist 2 hours ago | parent [-]

Source?