Tencent's licence excludes the UK and EU, so British developers can't legally use these open weights.
Kenning's take
What it does
HunyuanImage 3.0 is Tencent's open-weight image generation model, an 80-billion-parameter mixture-of-experts with 13 billion active per token. It uses one model for text and images, so it can reason about a prompt and fill in missing detail, and an Instruct version added in January 2026 supports image-to-image editing. Weights are on Hugging Face under Tencent's community licence, and the model is also served by inference providers such as fal.
- 80B mixture-of-experts, 13B active
- Unified text and image model
- Instruct version with reasoning and editing
- Distilled checkpoint for faster sampling
- vLLM support
Who it suits. Developers and researchers who want a large open image model to run or fine-tune.
Key facts
- Category
- AI models
- Made by
- Tencent
- Based in
- China
- Released
- 28 September 2025
- How to get it
- open weights on Hugging Face; hosted on inference providers such as fal; Tencent's licence states it does not apply in the UK, EU or South Korea
- Works on
- open-weights, API
- In the UK
- No
- Free plan
- yes, open weights (outside the UK, EU and South Korea)
FAQ
When was HunyuanImage 3.0 released?
Tencent open-sourced it on 28 September 2025.
Can I use HunyuanImage 3.0 in the UK?
Tencent's licence says it does not apply in the UK, EU or South Korea.
Facts from the maker's own pages and the sources listed. Checked 2026-10-11.
Similar tools
ACE-Step 1.5
Open-source music generation model that writes full songs with lyrics and runs on ordinary consumer GPUs.
AlphaGenome Atlas
Google DeepMind database of AI-predicted effects for every possible single-letter change in human DNA.
Amazon Nova 2
Amazon's second family of Nova AI models, covering reasoning, speech conversation and combined text-and-image generation.
Cisco Antares
Cisco's small open-weight models that find where known security vulnerabilities sit in a codebase, running locally.