Skip to content

Source paper

Stable Video Infinity: Infinite-Length Video Generation with Error Recycling

Wuyang Li, Wentao Pan, Po-Chien Luan and 2 more

Wuyang Li, Wentao Pan, Po-Chien Luan, Yang Gao, Alexandre Alahi

arXiv 2510.09212 · 202517 upvotes on Hugging Face

Research ideas from this paper (3)

Generated by AI. The paper’s authors did not write these.

AI summary

This paper introduces Stable Video Infinity (SVI), a framework designed to generate infinite-length videos with high consistency by addressing the problem of error accumulation in autoregressive models. The authors identify a 'hypothesis gap' where models trained on clean data fail when exposed to their own self-generated errors during inference, and they propose 'Error-Recycling Fine-Tuning' to train the model to actively correct these errors.

How it works (AI summary)

The core technique is Error-Recycling Fine-Tuning (ERFT). Instead of training on clean ground-truth transitions, the method injects historical errors (predicted from a replay memory bank) into the input latents during training. It uses a bidirectional integration step to calculate specific error terms (video latent error, noise error, and image condition error) and stores them in a dynamic memory bank. This forces the Diffusion Transformer (DiT) to learn a velocity field that points back to the clean trajectory from an error-corrupted state, effectively bridging the gap between training and autoregressive inference.