Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling
Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling
Xi-aokang Chen,Zhiyu Wu,5 Authors,C. Ruan
TLDR
Janus-Pro is introduced, an advanced version of the previous work Janus that incorporates an optimized training strategy, expanded training data, and scaling to larger model size, achieving significant advancements in both multimodal understanding and text-to-image instruction-following capabilities.
Abstract
In this work, we introduce Janus-Pro, an advanced version of the previous work Janus. Specifically, Janus-Pro incorporates (1) an optimized training strategy, (2) expanded training data, and (3) scaling to larger model size. With these improvements, Janus-Pro achieves significant advancements in both multimodal understanding and text-to-image instruction-following capabilities, while also enhancing the stability of text-to-image generation. We hope this work will inspire further exploration in the field. Code and models are publicly available.