Tencent Hunyuan launched and Open Source "Hunyuan Image 3.0"

Jin10 Data, September 28 - Tencent Hunyuan has launched and open-sourced its native multi-modal image generation model “HunyuanImage 3.0,” with a parameter scale reaching 80B. It is reported that this model is the first open-source industrial-grade native multi-modal image generation model, and Tencent claims that its performance can match that of leading closed-source models in the industry. In addition, the model can utilize knowledge for reasoning, analyze complex semantics at the k-character level, and generate long-form text.