AI RESEARCH
Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos
arXiv CS.CV
•
ArXi:2605.18233v1 Announce Type: new Without incurring significant computational overhead, train-free long video generation aims to enable foundation video generation models to produce longer videos. Frame-level autoregressive frameworks, e.g., FIFO-diffusion, offer the advantage of generating infinitely long videos with constant memory consumption. However, the mismatch between