Lates News

On September 28, Tencent Hunyuan launched and open-sourced the native multimodal image generation model "Hunyuan Image 3.0" with a parameter scale of 80B. It is reported that this model is the first open-source industrial-grade native multimodal image model, Tencent claims that this model's performance can rival top closed-source models in the industry. Additionally, the model is capable of utilizing knowledge to infer and analyze complex semantics at the level of thousands of words and generate long text.