EverAnimate: Minute-Scale Human Animation via Latent Flow Restoration

• URL: http://arxiv.org/abs/2605.15042v1
• Date: Thu, 14 May 2026 16:36:34 GMT
• Title: EverAnimate: Minute-Scale Human Animation via Latent Flow Restoration
• Abstract summary: We propose EverAnimate, an efficient post-training method for long-horizon animated video generation.<n>EverAnimate restores drifted flow trajectories by anchoring generation to a persistent latent context memory.<n>With only lightweight LoRA tuning, EverAnimate outperforms state-of-the-art long-animation methods in both short- and long-horizon settings.
• Score: 74.49189147054337
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• LiveAnimate: Stable Long-Form Streaming Human Animation in Real-Time [26.186924581106087]
  We present the first animation system to combine real-time streaming with stable long-form generation at billion scale.<n>LiveAnimate maintains nearly constant perceptual quality and identity from the first 30 seconds to the final minute.<n>These results establish a new operating point in quality, latency, and duration for interactive full-body animation.
  arXiv  Detail & Related papers  (2026-08-12T07:35:52Z)
• Wan-Animate-2: Pushing the Application Boundaries of Character Animation [26.88580952829003]
  Wan-Animate-2 is an end-to-end character animation framework that directly consumes the driving video within a redesigned Diffusion Transformer.<n>Our architecture achieves superior motion fidelity and identity preservation by eliminating intermediate motion extractors entirely.<n>We present Wan-Animate-2-Lite, an efficient variant that reduces inference latency to real-time thresholds.
  arXiv  Detail & Related papers  (2026-08-06T13:13:10Z)
• IM-Animation: An Implicit Motion Representation for Identity-decoupled Character Animation [58.297199313494]
  Implicit methods capture motion semantics directly from driving video, but suffer from identity leakage and entanglement between motion and appearance.<n>We propose a novel implicit motion representation that compresses per-frame motion into compact 1D motion tokens.<n>Our methodology employs a three-stage training strategy to enhance the training efficiency and ensure high fidelity.
  arXiv  Detail & Related papers  (2026-02-07T11:17:20Z)
• Knot Forcing: Taming Autoregressive Video Diffusion Models for Real-time Infinite Interactive Portrait Animation [16.692450893925148]
  We present a novel streaming framework named Knot Forcing for real-time portrait animation.<n>K Knot Forcing enables high-fidelity, temporally consistent, and interactive portrait animation over infinite sequences.
  arXiv  Detail & Related papers  (2025-12-25T16:34:56Z)
• Soul: Breathe Life into Digital Human for High-fidelity Long-term Multimodal Animation [70.86886231976439]
  Soul is a framework for high-fidelity long-term digital human animation.<n>It generates semantically coherent videos from a single-frame portrait image, text prompts, and audio.<n>It achieves precise lip synchronization, vivid facial expressions, and robust identity preservation.
  arXiv  Detail & Related papers  (2025-12-15T16:25:56Z)
• Deep Forcing: Training-Free Long Video Generation with Deep Sink and Participative Compression [36.99018442740971]
  We find that naively applying StreamingLLM-style attention sinks to video diffusion leads to fidelity degradation and motion stagnation.<n>We introduce Deep Forcing, which consists of two training-free mechanisms that address this without any fine-tuning.<n>Our results demonstrate that training-free KV-cache management can match or exceed training-based approaches for autoregressively streaming long-video generation.
  arXiv  Detail & Related papers  (2025-12-04T18:46:44Z)
• StableAnimator: High-Quality Identity-Preserving Human Image Animation [64.63765800569935]
  This paper presents StableAnimator, the first end-to-end ID-preserving video diffusion framework.<n>It synthesizes high-quality videos without any post-processing, conditioned on a reference image and a sequence of poses.<n>During inference, we propose a novel Hamilton-JacobiBellman (HJB) equation-based optimization to further enhance the face quality.
  arXiv  Detail & Related papers  (2024-11-26T18:59:22Z)
• Zero-shot High-fidelity and Pose-controllable Character Animation [89.74818983864832]
  Image-to-video (I2V) generation aims to create a video sequence from a single image. Existing approaches suffer from inconsistency of character appearances and poor preservation of fine details. We propose PoseAnimate, a novel zero-shot I2V framework for character animation.
  arXiv  Detail & Related papers  (2024-04-21T14:43:31Z)
• MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model [74.84435399451573]
  This paper studies the human image animation task, which aims to generate a video of a certain reference identity following a particular motion sequence. Existing animation works typically employ the frame-warping technique to animate the reference image towards the target motion. We introduce MagicAnimate, a diffusion-based framework that aims at enhancing temporal consistency, preserving reference image faithfully, and improving animation fidelity.
  arXiv  Detail & Related papers  (2023-11-27T18:32:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.