Z-Image

This is the base model of the ⚡️-Image family, designed for high-quality image generation, broad style coverage, and precise alignment with text prompts. It is intended for professional use, creative tasks, and research, in contrast to the accelerated version Z-Image-Turbo.

Key Features

• Undistilled Architecture:
  • Supports full Classifier-Free Guidance (CFG), enabling handling of complex prompts and fine-tuning of generation.
  • Ideal for LoRA training, integration with ControlNet, and other conditional learning methods.
• Masterfully covers photorealism, cinematic digital art, anime style, stylized illustrations, and other visual directions.
• Generates varied compositions, unique faces, lighting, and scenes even when varying the random generator parameters (seed). Ensures dynamism in scenes with multiple characters.
• Efficiently suppresses unwanted elements (artifacts, extra objects) through negative prompts.

---

The model is a component of the image generation pipeline, consisting of:

• Text encoder: ~4B parameters,
• Transformer: ~6B parameters,
• VAE: ~83 parameters,

Total: ~10B parameters

Announce Date: 23.01.2026
Parameters: 6B
Developer: Tongyi-MAI
Diffusers Version: 0.37.0.dev0
vLLM-Omni Version: 0.12.0rc1
License: Apache 2.0

Use our pre-built public endpoints for free to test inference and explore Z-Image capabilities. You can obtain an API access token on the token management page after registration and verification.

Rent your own physically dedicated instance with hourly or long-term monthly billing.

We recommend deploying private instances in the following scenarios:

• maximize endpoint performance,
• enable full context for long sequences,
• ensure top-tier security for data processing in an isolated, dedicated environment,
• use custom weights, such as fine-tuned models or LoRA adapters.

Contact our dedicated neural networks support team at nn@immers.cloud or send your request to the sales department at sale@immers.cloud.