Z-Image-Turbo
About Z-Image-Turbo
Z-Image-Turbo is an open-source, lightweight 6B-parameter text-to-image model developed by Alibaba Tongyi Laboratory. Built on the S³-DiT single-stream architecture, it requires only 8 inference steps—enabling sub-second image generation on H800 and running smoothly on devices with just 16GB VRAM (lowering hardware barriers). Core advantages: accurate Chinese-English text rendering, strong instruction adherence, and high photorealism. It is open-source and free with low integration costs, suitable for diverse scenarios such as creative content generation and application development.
Available Serverless
Run queries immediately, pay only for usage
$
0.005
Per Image
Metadata
Specification
State
Available
Architecture
Calibrated
Yes
Mixture of Experts
No
Total Parameters
6B
Activated Parameters
6B
Reasoning
No
Precision
FP8
Context length
0K
Max Tokens
Supported Functionality
Serverless
Supported
Serverless LoRA
Not supported
Fine-tuning
Not supported
Embeddings
Not supported
Rerankers
Not supported
Support image input
Not supported
JSON Mode
Not supported
Structured Outputs
Not supported
Tools
Not supported
Fim Completion
Not supported
Chat Prefix Completion
Not supported
SiliconFlow Service
Comprehensive solutions to deploy and scale your AI applications with maximum flexibility
60%
lower latency
2x
higher throughput
65%
cost savings
Compare with Other Models
See how this model stacks up against others.
Model FAQs: Usage, Deployment
Learn how to use, fine-tune, and deploy this model with ease.
