EverAnimate: Minute-Scale Human Animation via Latent Flow Restoration

TL;DR

EverAnimate is a novel method for long-horizon human animation that maintains visual quality and character consistency by restoring flow trajectories using a persistent latent context and velocity adjustment.

Contribution

It introduces a new approach combining latent context memory and flow restoration to improve long-form animated video generation.

Findings

Outperforms state-of-the-art methods in short- and long-horizon settings.

Achieves 8-15% improvements in PSNR/SSIM and 22-32% reductions in LPIPS/FID.

Effectively preserves character identity and visual quality over extended durations.

Abstract

We propose EverAnimate, an efficient post-training method for long-horizon animated video generation that preserves visual quality and character identity. Long-form animation remains challenging because highly dynamic human motion must be synthesized against relatively static environments, making chunk-based generation prone to accumulated drift: (i) low-level quality drift, such as progressive degradation of static backgrounds, and (ii) high-level semantic drift, such as inconsistent character identity and view-dependent attributes. To address this issue, EverAnimate restores drifted flow trajectories by anchoring generation to a persistent latent context memory, consisting of two complementary mechanisms. (i) Persistent Latent Propagation maintains a context memory across chunks to propagate identity and motion in latent space while mitigating temporal forgetting. (ii) Restorative Flow Matching introduces an implicit restoration objective during sampling through velocity adjustment, improving within-chunk fidelity. With only lightweight LoRA tuning, EverAnimate outperforms state-of-the-art long-animation methods in both short- and long-horizon settings: at 10 seconds, it improves PSNR/SSIM by 8%/7% and reduces LPIPS/FID by 22%/11%; at 90 seconds, the gains increase to 15%/15% and 32%/27%, respectively.