1. Tutorial Introduction

Qwen-Image is a high-quality image generation and editing model released in August 2025 by Alibaba's Tongyi Qianwen team. This model achieves breakthroughs in text rendering, supporting high-fidelity output of multi-line paragraphs in both Chinese and English, and possessing accurate reproduction capabilities for complex scenes and millimeter-level details. Through a multi-task collaborative training paradigm, Qwen-Image achieves pixel-level consistency in image editing, ensuring zero drift across the subject, lighting, and texture throughout the process. It can generate dozens of styles with a single click, including realistic, anime, cyberpunk, science fiction, minimalist, retro, surreal, and ink painting styles, and supports full-dimensional fine-grained operations such as style transfer, element addition and deletion, detail enhancement, text redrawing, and pose resetting. Related research papers are available. Qwen-Image Technical Report .

This tutorial uses dual-card RTX A6000 resources.

2. Project Examples

3. Operation steps

1. After starting the container, click the API address to enter the Web interface

2. Usage steps

If "Bad Gateway" is displayed, it means the model is initializing. Since the model is large, please wait about 2-3 minutes and refresh the page.

Parameter Description

• Advanced Settings:
  • Negative prompt: Negative prompt words are used to specify content or styles that are not desired to appear in the image.
  • Seed: Random seed.
  • Randomize seed: Whether to automatically randomize the seed.
  • Image size (ratio): Controls the resolution ratio of the output image.
  • Guidance scale: Guidance scale, used to control the quality of the generated image.
  • Number of inference steps: The number of inference steps used to control the level of detail of the generated image.

4. Discussion

🖌️ If you see a high-quality project, please leave a message in the background to recommend it! In addition, we have also established a tutorial exchange group. Welcome friends to scan the QR code and remark [SD Tutorial] to join the group to discuss various technical issues and share application effects↓

Citation Information

The citation information for this project is as follows:

@article{qwen-image,
    title={Qwen-Image Technical Report}, 
    author={Qwen Team},
    journal={arXiv preprint},
    year={2025}
}