What are the closest alternatives to HunyuanImage 3.0?

The closest alternatives, matched on model kind and release date with no comparable price, are Qwen-Image-Edit by Qwen, FLUX.2 [dev] by Black Forest Labs, and FLUX.2 Klein 4B by Black Forest Labs.

Is HunyuanImage 3.0 open source or open weights?

HunyuanImage 3.0 is open weights, licensed under tencent-hunyuan-community.

Where can I download the HunyuanImage 3.0 weights?

You can download the weights from the Hugging Face repository tencent/HunyuanImage-3.0.

Who made HunyuanImage 3.0 and when was it released?

HunyuanImage 3.0 was made by Tencent and released on September 28, 2025.

Is HunyuanImage 3.0 free to use?

Yes, HunyuanImage 3.0 is released as open weights.

Can HunyuanImage 3.0 edit existing images?

No, image editing with image input is not listed for HunyuanImage 3.0.

Where does HunyuanImage 3.0 rank on the Arena image leaderboards?

HunyuanImage 3.0 ranks 35 on the Arena Text to Image leaderboard, which is Arena's own rank, with a score of 1152.

HunyuanImage 3.0

Tencent

HunyuanImage 3.0

Developer	Tencent
Release date	September 28, 2025
Parameters	83B
Input	Text
Output	Image
Weights	Open weights
License	tencent-hunyuan-community
Website	tencent.com
Links	Model card Hugging Face

Part of a series on

Tencent

Pricing: Not published
Released: 1y ago

HunyuanImage 3.0 is an open-weights text-to-image model from Tencent's Hunyuan team, built on the Hunyuan-A13B base model. Tencent's launch announcement called it the first open-source industrial-grade native multimodal image generation model, saying a single autoregressive model handles both multimodal understanding and image generation rather than a combination of separate models. It is built for generating images from text prompts, with the maker claiming it uses world knowledge to interpret and enrich long or sparse prompts.