Long videos stop drifting: Reference Forcing anchors each new frame to the first, holding consistency over two hours
Autoregressive video diffusion models generate video chunk by chunk, but short-window distillation does not constrain long-range appearance, so subjects and backgrounds drift over time. Reference Forcing treats the initial frames as an appearance reference: a teacher built from segmentation and optical-flow models forces each region of a new frame to attend only to the same region of the initial frames, and this behavior is distilled into a separate anchor attention path in the student, which also guides correction of drifted values in the KV cache. On the LongLive base model it achieves the highest subject and background consistency at 30 and 60 seconds, and its advantage grows with video length.