Janus1.3B
66 downloads
0 likes
on ModelScope
updated
Papers using or citing this model 1
-
Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation
In this paper, we introduce Janus, an autoregressive framework that unifies multimodal understanding and generation. Prior research often relies on a single visual encoder for both tasks, such as Chameleon. However, due to the differing...