zimage turbo — ZIMAGE AI Model

Also known as "ZIT" -- Z-Image Turbo from Alibaba is a fast, low-steps general purpose realism text to image model. Doesn't support negative prompts. Works best at around 9 steps and 1 guidance at 1024x1024.

ModelTrends.ai Model ID

#28293

Flag content

Guides for this model

ComfyUI

Z-Image Turbo ComfyUI workflow: photoreal portraits in 8 steps

The ComfyUI team's Z-Image Turbo template: the 6B single-stream model, the Qwen3 4B text encoder and the Flux VAE in twelve nodes, 8 steps at cfg 1 with res_multistep. Three files, English and Chinese prompts, and the settings for 8 GB and 16 GB cards. Workflow JSON hosted here.

Similar Models

Badges for creators

Made this model? Put its standing on your Civitai page, your Hugging Face card, your README or your site. Each badge is a small picture that shows the standing on the day you copy it and never changes afterwards, however the rankings move later. The date is part of the badge.

AI Models for Image, Video & Text Generation

zimage turbo is a base model for the Zimage family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Zimage models, check its heat score to see how it is trending, and open it on PirateDiffusion or BitVector to try it.

More Zimage models More Zimage Base Models workflow graydient realistic effects

Browse by Model Family