1. Tutorial Introduction

Z-Image-Turbo is a next-generation high-efficiency image generation model released by Alibaba's Tongyi Qianwen team in November 2025. This model, with only 6 bytes of parameters, achieves performance comparable to flagship closed-source models with over 20 bytes of parameters, and excels at generating high-fidelity, photorealistic portraits. The related paper is titled "Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer".

This tutorial uses a single RTX 5090 graphics card as computing resource.

2. Effect display

3. Operation steps

1. Start the container

2. Usage steps

If "Bad Gateway" is displayed, it means the model is initializing. Since the model is large, please wait about 3-5 minutes and refresh the page.

Specific parameters:

• Prompt: You can enter text here.
• Resolution Category: Used to select the base resolution level for the generated image.
• Width x Height (Ratio): Select the specific aspect ratio.
• Seed: Used to control the randomness of the generated results.
• Steps: Iterative steps of diffusion sampling.
• Time Shift: Used to control the "time curve shift" during the model sampling process, it is a super-resolution naturalness enhancement parameter unique to Z-Image.

Citation Information

The citation information for this project is as follows:

@article{team2025zimage,
  title={Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer},
  author={Z-Image Team},
  journal={arXiv preprint arXiv:2511.22699},
  year={2025}
}