Z-Image Models by Zhipu AI

Zhipu AIApache 2.0Open source
Zhipu AI releases · 15 in the last 12 months · this family litChangelog →
1 model2025

Last refreshed 2026-09-10. Next refresh: weekly.

Details

ResearcherZhipu AI
LicenseApache 2.0OSI-approved
Commercial useCommercial use: permitted
Models1
Released2025

Capabilities

MultimodalAll models

Links

Website

About

Zhipu AI's (Z.ai) efficient text-to-image generation family based on a single-stream Diffusion Transformer (S3-DiT) architecture. Optimized for fast few-step sampling with bilingual Chinese-English text rendering.

Decision facts

Best fit
image generationvision and multimodal work
Capability starting point
Z-Image with multimodal inputs
Lowest tracked input
Not tracked
Closest related family
AutoGLM

Current Variants

Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.

1 in view
Z-ImageCurrent

Use when the workload needs image generation, 6B parameters, and multimodal inputs.

2025-11image generation6B parametersmultimodal inputs

Release Timeline

1 release group
2025-11
1 current
Z-Image
image generation6B parametersmultimodal inputs
Current

Specifications(1 models)

Z-Image model specifications comparison
ModelReleasedParametersMultimodal
Z-Image2025-116BYes

Available From(1 provider)

fal API