LiveAnimate: Stable Long-Form Streaming Human Animation in Real-Time

• URL: http://arxiv.org/abs/2608.11745v2
• Date: Thu, 13 Aug 2026 06:21:16 GMT
• Title: LiveAnimate: Stable Long-Form Streaming Human Animation in Real-Time
• Abstract summary: 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.
• Score: 26.186924581106087
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Pose-driven human animation synthesizes a video of a target person from a single reference image and a driving pose stream. Real-time generation is essential for interactive applications such as live streaming, telepresence, and virtual avatars, yet diffusion-based systems require minutes to hours per clip, precluding responsive interaction. We present LiveAnimate, to our knowledge the first animation system to combine real-time streaming with stable long-form generation at billion scale, built on a 14B-parameter video Diffusion Transformer (DiT). A two-stage training pipeline first adapts a pretrained bidirectional DiT into a block-causal autoregressive generator through Reference-Anchored Teacher-Forcing Adaptation, and then reduces the sampling budget to three steps through Block-wise Self-Forcing Distillation. To preserve appearance over extended streams, we introduce Pose-Retrieval Sink Attention (PR-Sink), a bounded KV-cache mechanism combining a Static Sink that permanently anchors the first generated block, a Dynamic Sink that holds a pose-retrieved historical block, and a three-slot Rolling Window. When a pose recurs, PR-Sink restores the relevant appearance context without retaining the entire sequence, so memory and per-block latency remain constant regardless of stream duration. Together with Ulysses sequence parallelism and operator fusion, these designs enable 19.63\,FPS streaming inference on two NVIDIA H100 GPUs. On a three-minute benchmark, LiveAnimate maintains nearly constant perceptual quality and identity from the first 30 seconds to the final minute, while prior systems degrade substantially or require hours of offline computation for the same rollout. These results establish a new operating point in quality, latency, and duration for interactive full-body animation.

Related papers

• StreamPI: Streaming Multimodal Temporal Modeling for Vision-Language-Action Models [84.17128030384099]
  StreamPI is a streaming multimodal temporal modeling framework.<n>It equips single-frame VLA with temporal reasoning capability without introducing any additional parameters.<n> Experiments on real-robot tasks spanning memory-dependent and precise perception scenarios, as well as the simulation benchmark LIBERO, demonstrate that StreamPI outperforms pi0.5 across diverse tasks.
  arXiv  Detail & Related papers  (2026-08-26T17:33:19Z)
• 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)
• LiveStarPro: Proactive Streaming Video Understanding with Hierarchical Memory for Long-Horizon Streams [59.485485426790966]
  We introduce LiveStarPro, a live streaming assistant that is designed for proactive video understanding over long-horizon streams.<n>LiveStarPro consistently surpasses existing methods, attaining a 28.9% improvement in semantic correctness.<n>Its streaming key-value cache further yields a 1.58x inference speedup over the same model without caching.
  arXiv  Detail & Related papers  (2026-06-16T11:18:05Z)
• EverAnimate: Minute-Scale Human Animation via Latent Flow Restoration [74.49189147054337]
  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.
  arXiv  Detail & Related papers  (2026-05-14T16:36:34Z)
• AvatarForcing: One-Step Streaming Talking Avatars via Local-Future Sliding-Window Denoising [15.787466786514164]
  AvatarForcing is a one-step streaming diffusion framework that denoises a fixed local-future window with heterogeneous noise levels.<n>Experiments on standard benchmarks and a new 400-video long-form benchmark show strong visual quality and lip synchronization at 34 ms/frame.
  arXiv  Detail & Related papers  (2026-03-15T11:42:07Z)
• FlowAct-R1: Towards Interactive Humanoid Video Generation [37.04996721172613]
  FlowAct-R1 is a framework specifically designed for real-time interactive humanoid video generation.<n>Our framework achieves a stable 25 fps at 480p resolution with a time-to-first-frame (F) of only around 1.5 seconds.
  arXiv  Detail & Related papers  (2026-01-15T06:16:22Z)
• 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)
• Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length [57.458450695137664]
  We present Live Avatar, an algorithm-system co-designed framework for efficient, high-fidelity, and infinite-length avatar generation.<n>Live Avatar is first to achieve practical, real-time, high-fidelity avatar generation at this scale.
  arXiv  Detail & Related papers  (2025-12-04T11:11:24Z)
• StreamDiffusionV2: A Streaming System for Dynamic and Interactive Video Generation [65.90400162290057]
  Generative models are reshaping the live-streaming industry by redefining how content is created, styled, and delivered.<n>Recent advances in video diffusion have markedly improved temporal consistency and sampling efficiency for offline generation.<n>Live online streaming operates under strict service-level objectives (SLOs): time-to-first-frame must be minimal, and every frame must meet a per-frame deadline with low jitter.
  arXiv  Detail & Related papers  (2025-11-10T18:51:28Z)
• MotionStream: Real-Time Video Generation with Interactive Motion Controls [60.403597895657505]
  We present MotionStream, enabling sub-second latency with up to 29 FPS streaming generation on a single GPU.<n>Our approach begins by augmenting a text-to-video model with motion control, which generates high-quality videos that adhere to the global text prompt and local motion guidance, but does not perform inference on the fly.<n>Our models achieve state-of-the-art results in motion following and video quality while being two orders of magnitude faster, uniquely enabling infinite-length streaming.
  arXiv  Detail & Related papers  (2025-11-03T06:37:53Z)
• Lookahead Anchoring: Preserving Character Identity in Audio-Driven Human Animation [75.71558917038838]
  Lookahead Anchoring prevents identity drift during temporal autoregressive generation.<n>It transforms from fixed boundaries into directional beacons.<n>It also enables self-key-framing, where the reference image serves as the lookahead target.
  arXiv  Detail & Related papers  (2025-10-27T17:50:19Z)
• UniAnimate: Taming Unified Video Diffusion Models for Consistent Human Image Animation [53.16986875759286]
  We present a UniAnimate framework to enable efficient and long-term human video generation. We map the reference image along with the posture guidance and noise video into a common feature space. We also propose a unified noise input that supports random noised input as well as first frame conditioned input.
  arXiv  Detail & Related papers  (2024-06-03T10:51:10Z)

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.