Z-Image — AI Image Generator
High-quality AI image generation model
About Z-Image
Z-Image is the 6B-parameter image generation foundation model from Tongyi-MAI, Alibaba's Tongyi lab. Its technical report (November 2025) describes a Scalable Single-Stream Diffusion Transformer (S3-DiT) that concatenates text tokens, visual semantic tokens, and image VAE tokens into one input stream, an efficiency-first design aimed squarely at the 20B-plus models that dominated open image generation. The whole model trained in roughly 314,000 H800 GPU hours, a fraction of typical foundation-model budgets, and the weights are Apache 2.0.
This entry runs the base (undistilled) checkpoint, released on Hugging Face and ModelScope on January 27, 2026 after the Turbo variant had already shipped. The base model is the full-capacity member of the family: classifier-free guidance, robust negative prompting, high output diversity, and fine-tuning support that the distilled Turbo gives up. On Artifio it runs pay-per-generation in the same workspace as 100+ other models.
Features
- 6B-parameter S3-DiT architecture with a single unified input stream for text, semantic, and VAE tokens
- Full sampling control: classifier-free guidance (recommended scale 3.0 to 5.0) and negative prompting, at 28 to 50 inference steps
- Resolution range from 512x512 up to 2048x2048
- Photorealistic generation plus cinematic digital art, anime, and stylized illustration from one checkpoint
- Bilingual text rendering in English and Chinese
- Apache 2.0 weights, with the family also spanning Z-Image-Turbo (distilled), Z-Image-Edit (instruction editing), and Z-Image-Omni-Base
What people use it for
- Prompt-heavy creative work that benefits from negative prompts and guidance-scale control
- Generating varied candidate sets, since the base model keeps the diversity the Turbo distillation trades away
- Photorealistic portraits and scenes with embedded English or Chinese text
- Base checkpoint for teams that fine-tune styles on their own data
- Large-format 2K renders for print and web hero images
Reported strengths
- The technical report claims results comparable to or surpassing leading competitors, including commercial systems, at a 6B size that undercuts 20B to 80B rivals
- High output diversity and easy fine-tunability relative to Z-Image-Turbo, per the family's own comparison table
- Documented low training cost (about 314K H800 GPU hours), which backs the efficiency claims with numbers
Z-Image FAQ
What is Z-Image?
Z-Image is an AI model (prompt to image) available on Artifio.ai through alibaba. You can run it in our workspace from a single shared wallet and download your outputs.
How much does Z-Image cost on Artifio?
Z-Image starts at about $0.005 per generation on Artifio.ai. The exact cost is shown in the workspace before you confirm and can vary with the options you select.
How do I use Z-Image on Artifio?
Click Generate Now to open the workspace at /create/z-image. Fill in the form fields, review the live cost estimate, and run your generation.
What kind of outputs does Z-Image produce?
Z-Image is configured for prompt to image workflows in the image category. See the technical parameters below for supported inputs and options.
Can I try Z-Image for free?
Sign up free, top up your wallet from $5, and you can run Z-Image pay-as-you-go without a separate subscription for this model.
Similar models
More in the same category
Try Z-Image on Artifio
Open the workspace with this model pre-selected. Your prompt and settings stay in the browser until you generate.
Generate Now