NVIDIA新出的Flex-Forcing，一个模型就能在双向扩散和自回归之间切换，想快想稳都行，挺省事的。
Flex-Forcing是NVIDIA研究团队发布的视频生成方法。当前主流方法有双向扩散（同时建模所有帧，结构稳但慢）和自回归（逐帧生成，快且支持长片段，但漂移）。Flex-Forcing训练单一模型在推理时可根据计算预算选择任一种方式或中间态。
Our research team just released Flex-Forcing: a video generation method that lets a single model swi...
Our research team just released Flex-Forcing: a video generation method that lets a single model switch between generation methods at inference time. Right now there are two main approaches to video generation. Bidirectional diffusion models attend to every frame at once, holding structure well at the cost of speed. Autoregressive models generate frame by frame, so they stream fast and scale to long clips, but accumulate error and drift over time. Flex-Forcing trains a single model to do both, letting you choose from the range at inference based on your compute budget. Your browser does not support the video tag. 🔗 View on Twitter 💬 3 🔄 8 ❤️ 16 👀 2451 📊 7 ⚡