← Back to archive

DeepSeek launches Janus-Pro open-source multimodal AI model

🚀 DeepSeek has launched Janus-Pro, an open-source multimodal AI model that enhances text-to-image generation and multimodal understanding. It improved Janus with a more efficient training strategy, a larger dataset, and a scalable architecture. It works better than SD3 and DALL-E 3.

DeepSeek launches Janus-Pro open-source multimodal AI model
DeepSeek launches Janus-Pro open-source multimodal AI model

Originally posted on X

PS: I'm pretty active on 𝕏 if you'd like to follow along

Archive

2026

2025

2024

2018