Try For Free
Sign Up
9
Hunyuan Image V3 is an advanced text-to-image model that generates high-quality images from text prompts.
The model improves 3D asset usability by delivering production-ready parts with preserved topology and high structural accuracy.
HunyuanImage 3.0 is a cutting-edge open-source text-to-image model developed by Tencent, featuring 80 billion parameters with an efficient mixture-of-experts design activating 13 billion parameters at inference.
Generate foley audio for videos using Tencent Hunyuan Video Foley model. Adds realistic sound effects synchronized with video content.
Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent, supporting 33 language pairs plus five Chinese dialect and minority-language pairs.
Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family, a 30B-parameter Mixture-of-Experts model with 3B active parameters, supporting 33 language pairs plus five Chinese dialect and minority-language pairs.
Hy-MT2-7B is a 7B-parameter translation model from Tencent, supporting 33 language pairs plus five Chinese dialect and minority-language pairs.
Hy3 is Tencent's 295B-parameter Mixture-of-Experts model (21B active) for reasoning, agentic workflows, and production coding tasks.
Hy4 Preview is Tencent Hunyuan's new-generation flagship MoE model -- 770B total / 49B active parameters, with a 1M-token context window and native speculative decoding.
