Z-Image Family: 6B S3-DiT Models by Tongyi-MAI (Alibaba)

Z-Image is an efficient image generation model family by Tongyi-MAI (Alibaba). Features a 6B parameter single-stream DiT architecture with variants for quality (Z-Image) and speed (Z-Image-Turbo).

Z

Z-Image by Tongyi-MAI

Text-to-Image6B ParametersS3-DiTOpen Source

An efficient image generation foundation model family by Alibaba's Tongyi-MAI team. Built on a Scalable Single-Stream DiT (S3-DiT) architecture with 6B parameters. Comes in two variants: the full-capacity Z-Image for quality and fine-tuning, and the distilled Z-Image-Turbo for 8-step sub-second inference.

Variants

VariantParamsStepsCFGFine-TunableBest For
Z-Image6B28-50YesYesQuality, diversity, fine-tuning
Z-Image-Turbo6B8NoNoSpeed, photorealism

Select a variant for tutorials, custom nodes, and related news. Curated weight downloads live in the Model Hub catalog.