Janus Pro: Multimodal Image Understanding and Generation
ComfyUI Wiki
Janus Pro is DeepSeek's multimodal AI model for image understanding and generation, available in 1B and 7B variants.
J
Janus Pro
MultimodalImage UnderstandingText-to-ImageOpen SourceDeepSeek's multimodal AI model open-sourced on January 27, 2025. Capable of both image understanding and generation. Available in 1B and 7B parameter variants. MIT licensed. Supports image captioning, visual question answering, and text-to-image generation via ComfyUI-Janus-Pro plugin.
| Developer | DeepSeek |
| Release Date | 2025-01-27 |
| Architecture | Multimodal Transformer (autoregressive) |
| License | MIT |
| Model Sizes | 7B (recommended), 1B (lightweight) |
| Capabilities | Image understanding, visual QA, text-to-image generation |
| Plugin | ComfyUI-Janus-Pro (CY-CHENYUE) |
Guides and workflows related to this model series.
DeepSeek Janus Pro ComfyUI Workflow
How to set up and use DeepSeek Janus Pro in ComfyUI, based on the ComfyUI-Janus-Pro plugin
Deepseek
Comments
Sign in with GitHub to join the discussion.