谢赛宁推荐视频扩散新采样器
if you are building video diffusion / world simulators, try this new sampler.
如果你在做视频扩散 / 世界模拟器，试试这个新采样器。 时间一致性把视频钉在总像素空间的低维流形上。 自精炼采样让它们留在那里。
查看原帖What if your video generator could refine itself—at inference time? ❌No new models. ❌No retraining. ❌No external verifier. 💡 Introducing Self-Refining Video Sampling By reinterpreting a pretrained generator (Wan2.2, Cosmos) as a denoising autoencoder, we enable iterative self-refinement at inference time ➡️dramatically improving physical realism and…
展开完整原文
What if your video generator could refine itself—at inference time? ❌No new models. ❌No retraining. ❌No external verifier. 💡 Introducing Self-Refining Video Sampling By reinterpreting a pretrained generator (Wan2.2, Cosmos) as a denoising autoencoder, we enable iterative self-refinement at inference time ➡️dramatically improving physical realism and achieving over 70% human preference! 🧵
正文
当前显示原文，中文全文译文尚未就绪。
if you are building video diffusion / world simulators, try this new sampler. temporal consistency pins videos to a low-dimensional manifold in the total pixel space. self-refinement sampling keeps them there.