What Is Hunyuan Image 3.0?
Hunyuan Image 3.0 is Tencent’s large open text-to-image base model, with 80 billion total parameters and 13 billion active parameters. This page keeps its direct diffusion controls and optional prompt expansion separate from the reasoning-oriented Instruct version.
Hunyuan Image Model Versions
Hunyuan Image 3.0
Base model · 2K
From 8 Credits
Hunyuan Image 3 Instruct
Tencent’s instruction-focused image model for detailed prompts and deliberate composition.
- Resolutions: 1K
- Reference images: not supported
- Modes: Text to Image
- Speed: Slow
Hunyuan Image 3.0
Tencent’s native multimodal base generator for complex scenes and high prompt alignment.
- Resolutions: 1K / 2K
- Reference images: not supported
- Modes: Text to Image
- Speed: Slow
Hunyuan Image 2.1
A configurable Hunyuan generation for users who want direct sampling and negative-prompt controls.
- Resolutions: 1K
- Reference images: not supported
- Modes: Text to Image
- Speed: Slow
What Is Hunyuan Image 3.0 Best For?
- Complex scene composition
- Detailed descriptive prompts
- Open-model research workflows
- Large final renders
How to Use Hunyuan Image 3.0
- Describe spatial relationships clearly.
- Use a short negative prompt.
- Test the composition at 1K.
- Render only the winner at 2K.
Hunyuan Image 3.0 Settings Explained
Guidance
7.5 is the documented base-model default for prompt adherence.
Prompt Expansion
Disabled by default so the expensive run follows the text you supplied.
The panel above shows only the parameters Hunyuan Image 3.0 actually supports. Switch versions and unsupported controls disappear rather than sitting there doing nothing.
Hunyuan Image 3.0 Prompt Examples
Crowded scene
Telephoto photograph through a festival crowd, one laughing subject in sharp focus, layered banners and lanterns, natural background compression
Technical cutaway
Architectural cutaway of a compact tidal research station, labelled functional zones, coherent structure, restrained scientific illustration
Hunyuan Image 3.0 Test Results
Testing in progress
Every model runs the same eight-category prompt set — portrait, product, poster text, anime character, interior, multi-reference, image editing and character consistency — recording generation time, success rate, text accuracy and identity retention. That run has not finished for Hunyuan Image 3.0, so this page shows no scores. We do not publish numbers we have not measured.
Hunyuan Image 3.0 Limitations
- Substantially more expensive than distilled draft models
- Text-to-image only here
- The 2K tier should be reserved for final candidates
Hunyuan Image 3.0 Pricing and Credits
Credits scale with resolution and image count. The Generate button always shows what this run costs.
1K
8 credits / image
2K
30 credits / image
Failed generations cost 0 credits.
Commercial Use and Image Rights
Commercial use is governed by Tencent’s Hunyuan model licence and the selected service terms.
- Model used: Hunyuan Image 3.0
- Model developer: Tencent
- The inference route is managed internally and may change without changing the selected model
- Uploads are sent only to the configured inference service needed to complete the generation
- You can delete any generation from your history at any time
Frequently Asked Questions
How is this different from Hunyuan Image 3 Instruct?+
This is the base text-to-image model with classic diffusion controls; Instruct adds a reasoning-oriented prompt workflow.
Why does 2K cost many more credits?+
The upstream route bills by output megapixel, so a square 2K image contains four times the pixels of 1K.
Release History and Sources
September 28, 2025 · Weights and model code released
This date applies to the event shown. Later API access, weights and availability on All Image AI may have different dates.
Explore this event on the image model timeline →
Related Models and Tools
AI Image Generator
Create an image, try a new look or transform a photo. Start with the result you want.
Poster Generator
Posters with headlines that come out right the first time.
Qwen Image 3 Pro
Alibaba
The higher-fidelity Qwen Image 3 tier for polished text, editing and final assets.
Qwen Image 3
Alibaba
A fast, economical Qwen generation for ideation, localisation and everyday image work.
Qwen Image Max
Alibaba
A high-fidelity Qwen tier for natural-looking scenes, bilingual prompts and controlled edits.
Qwen Image 2512
Alibaba
Alibaba’s upgraded Qwen Image checkpoint for more realistic people, richer texture and bilingual prompts.