DeepSeek claims its Janus-Pro-7B outperforms existing models such as OpenAI's DALL-E and Stable Diffusion. In a bold move that mirrors its approach with DeepSeek-R1, the company has made Janus-Pro-7B free and open source.

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

The Chinese startup that has stunned Silicon Valley with its language models now boasts superior image generation and understanding.

Now DeepSeek has released Janus Pro, an image generating model the company claims that has been engineered for versatility and efficiency. It is and advanced version based on the Janus model, released last year, that performs text-to-image creation that scales up the training data and increases the model size.

DeepSeek unveils Janus-Pro AI models, outperforming DALL-E 3 in benchmarks. These multimodal models, licensed under MIT

Fresh off the viral success of its new AI model over the weekend, DeepSeek is already back with another launch – this time focusing on AI image generation. The Chinese startup has released an image-generation model called Janus-Pro,

DeepSeek, a China-based AI company that launched a chatbot that disrupted US tech stocks and App Store rankings, has launched an AI image generator just days after its chatbot went viral. Janus-Pro is a multi-modal image generator that DeepSeek says both understands and performs better than earlier models.

This story incorporates reporting from decrypt, Business Insider, gadgets360 and The Gazette.DeepSeek, a China-based artificial intelligence lab, has once again raised industry standards with the release of its latest image generation model,