1. Tutorial Introduction

HunyuanImage-2.1 is an open-source text-to-image model released by Tencent's Hunyuan team in September 2025. It supports native 2K resolution, possesses powerful complex semantic understanding capabilities, and can accurately generate scene details, facial expressions, and actions. The model supports both Chinese and English input and can generate images in various styles, such as comics and figurines, while maintaining stable control over text and details within the images. The model is based on a dual-channel text encoder and high-compression VAE technologies, significantly improving training and inference efficiency. Related research papers are available. PromptEnhancer: A Simple Approach to Enhance Text-to-Image Models via Chain-of-Thought Prompt Rewriting .

This tutorial uses a single RTX PRO 6000 graphics card as computing resource, providing two functions: Text-to-Image Generation and Image Refinement for testing.

2. Effect display

Text-to-image Generation

Image Refinement

3. Operation steps

1. Start the container

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.

2. Usage steps

1. Text-to-image Generation

Parameter Description:

• Use Distilled Model: Using distilled model will generate faster results but slightly lower quality.
• Prompt: You can enter text here.
• Negative Prompt: A negative prompt that tells the AI "not to generate something".
• Aspect Ratio: Select the aspect ratio of the generated image.
• Inference Steps: Inference steps. More steps = better quality, slower generation speed.
• Guidance Scale: How strictly prompts are followed.
• Seed: seed.
• Use Refiner: Whether to use image refinement.

2. Image Refinement

Parameter Description:

• Refinement Prompt: You can enter text here.
• Width: Output image width.
• Height: Output image height.
• Refinement Steps: Refine the reasoning steps. More steps = better quality, slower generation speed.
• Guidance Scale: How strictly prompts are followed.
• Seed: seed.

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:

@misc{HunyuanImage-2.1,
  title={HunyuanImage 2.1: An Efficient Diffusion Model for High-Resolution (2K) Text-to-Image Generation},
  author={Tencent Hunyuan Team},
  year={2025},
  howpublished={\url{https://github.com/Tencent-Hunyuan/HunyuanImage-2.1}},
}