Tencent Unveils 80 Billion Parameter Open-Source AI Image Generator with Revolutionary Architecture
Summary
Tencent launches HunyuanImage-3.0, the world's largest open-source AI image generator with 80 billion parameters and revolutionary autoregressive architecture, featuring 64 experts in a Mixture of Experts design that delivers superior text-to-image generation with advanced world-knowledge reasoning capabilities.
Key Points
- Tencent releases HunyuanImage-3.0, an 80 billion parameter open-source image generation model that uses a unified autoregressive framework instead of traditional DiT-based architectures
- The model features 64 experts in a Mixture of Experts design with 13 billion parameters activated per token, making it the largest open-source image generation MoE model to date
- HunyuanImage-3.0 demonstrates superior performance in text-to-image generation with intelligent world-knowledge reasoning capabilities and requires at least 3x80GB GPU memory for inference