Hunyuan V3 T2I

Hunyuan-Image/v3 (text-to-image) is a model developed by Tencent that accepts text prompts and generates corresponding images. It uses a unified autoregressive architecture that blends language and visual modalities to produce outputs with strong semantic alignment. The model supports bilingual input (Chinese and English) and is tuned for prompt consistency, scene structure, and compositional coherence. It handles difficult cases like embedded typography, layout guidance, and detail fidelity in complex scenes. The architecture is based on a Mixture-of-Experts (MoE) design, delivering both scale and efficiency. Hunyuan-Image/v3 is made available with open inference code, model weights, and commercial licensing options, making it accessible for a range of creative and production use cases.

September 28, 2025

Tencent

Text to Image (T2I)