Pro, an updated version of its multimodal model, Janus. The new model improves training strategies, data scaling, and model size, enhancing multimodal understanding and text-to-image generation.

The Chinese startup has released an image-generation model called Janus-Pro, aiming to take on US rivals DALL-E 3 and Stable Diffusion. The multimodal model, which generates images from text prompts, is said to outperform competing services in areas such as image quality and accuracy.

DeepSeek Janus Pro a new open-source multimodal AI image generator model offering cost-effective and versatile text-to-image AI for users