
JanusFlow: Unified Multimodal Understanding and Generation via Autoregressive Flow
Suraj Khanal
JanusFlow unifies image understanding/generation using rectified flow and an autoregressive model. It decouples encoders for tasks, aligning representations during training. Training occurs in 3 stages: adaptation, pre-training, and fine-tuning. This achieves strong performance in both areas with 1.3B parameters
- 1 Episode
About
JanusFlow unifies image understanding/generation using rectified flow and an autoregressive model. It decouples encoders for tasks, aligning representations during training. Training occurs in 3 stages: adaptation, pre-training, and fine-tuning. This achieves strong performance in both areas with 1.3B parameters
Information
- CreatorSuraj Khanal
- Years Active2K
- Episodes1
- RatingClean
- Copyright© Suraj Khanal
- Show Website