🛰️ Daily AI Frontier
‹ back to 2026-08-13

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

Research Multimodal & Generative

Ranking

Overall 87
Content 95
Popularity 69

Observed public metrics from 1 member.

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

Merged summary

TL;DR - LiveAnimate is a 14B-parameter video diffusion system for stable, real-time, pose-driven human animation from a single reference image. It enables long-running interactive applications while keeping memory and latency constant.

  • Converts a bidirectional DiT into a block-causal generator, then distills sampling to three steps.
  • Uses Pose-Retrieval Sink Attention and a bounded KV cache to preserve appearance over long streams.
  • Achieves 19.63 FPS on two NVIDIA H100 GPUs using sequence parallelism and operator fusion.
  • Maintains nearly constant identity and perceptual quality across a three-minute benchmark.

Sources (1)

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

arXiv cs.CV Yuxuan Zhang, Haozhong Xiong, Yubo Huang, Jiayi Song, Jinpeng Yu, Haofan Wang, Jiaming Liu, Ruihua Huang, Liwei Wang 2026-08-12 arXiv:2608.11745
Public signals Hugging Face upvotes 24
Providers: Hugging Face · Upvotes 24 OpenAlex · N/A Publisher · N/A Semantic Scholar · N/A X · N/A Fetched 2026-09-12 14:27:37.607896 UTC

TL;DR - LiveAnimate is a 14B-parameter video diffusion system for stable, real-time, pose-driven human animation from a single reference image. It enables long-running interactive applications while keeping memory and latency constant.

  • Converts a bidirectional DiT into a block-causal generator, then distills sampling to three steps.
  • Uses Pose-Retrieval Sink Attention and a bounded KV cache to preserve appearance over long streams.
  • Achieves 19.63 FPS on two NVIDIA H100 GPUs using sequence parallelism and operator fusion.
  • Maintains nearly constant identity and perceptual quality across a three-minute benchmark.
item →