AI RESEARCH
NAMI: Efficient Image Generation via Bridged Progressive Rectified Flow Transformers
arXiv CS.CV
•
ArXi:2503.09242v3 Announce Type: replace Flow-based Transformer models have achieved state-of-the-art image generation performance, but often suffer from high inference latency and computational cost due to their large parameter sizes. To improve inference efficiency without compromising quality, we propose Bridged Progressive Rectified Flow Transformers (NAMI), which decompose the generation process across temporal, spatial, and architectural demensions. We divide the rectified flow into different stages according to resolution, and use a BridgeFlow module to connect them.