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.

Explore DeepSeek Janus Pro, the new AI image generator redefining multimodal technology with autoregressive modeling, creative visuals and

DeepSeek says its updated text-to-image generator Janus pro-7B outperforms OpenAI's DALL-E 3 across multiple benchmarks.