Tencent-Hunyuan/HunyuanImage-3.0
A Tencent open-source diffusion-based text-to-image generation model with native multimodal architecture.

Velocity · 7d
+12
★ / day
Trend
→steady
star history
HunyuanImage-3.0 is a large-scale image generation model trained by Tencent, released with model weights on HuggingFace. It supports text-to-image generation and instruction-guided image-to-image editing. The model is available in multiple variants including a distilled version for faster inference, and comes with a prompt handbook and technical documentation.