AptAvatar: Fast and Vivid Long-Form Audio-Driven Video Generation for Production-Ready Avatars

• URL: http://arxiv.org/abs/2607.24013v2
• Date: Wed, 29 Jul 2026 08:53:30 GMT
• Title: AptAvatar: Fast and Vivid Long-Form Audio-Driven Video Generation for Production-Ready Avatars
• Abstract summary: AptAvatar is a long-form audio-driven avatar generation framework that delivers fast and expressive inference.<n>Experiments demonstrate that AptAvatar generates vivid 720p long-form avatar videos with only 2 NFEs, achieving a 60x speedup.
• Score: 8.684276604886032
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Production-ready audio-driven avatar generation requires efficient inference without sacrificing fidelity or motion expressiveness. However, existing acceleration methods often compromise quality through restrictive architectural choices, such as causal attention and short temporal horizons, or by reducing model capacity and resolution. Without such compromises, we propose AptAvatar, a 14B-parameter long-form audio-driven avatar generation framework that delivers fast and expressive inference. For efficiency in production-level applications, AptAvatar addresses the extreme two-step generation challenge. To bridge the gap between the multi-step teacher model and the two-step student model, we introduce Endpoint-Anchored Distribution Distillation. It augments vanilla distribution matching with a dedicated Anchor Score Estimator trained on the trajectory-endpoint distribution defined from a frozen pretrained 4-step bridge generator. This provides an attainable endpoint-level anchor for the evolving two-step student. To improve long-horizon consistency, we further introduce Self-Generated History Replay, which reuses cached outputs from earlier generator checkpoints as history conditions during chunk-wise training. This approximates inference-time conditioning on self-generated histories without costly online rollouts, mitigating quality degradation from accumulated history errors. Extensive experiments demonstrate that AptAvatar generates vivid 720p long-form avatar videos with only 2 NFEs, achieving a 60x speedup while preserving visual fidelity and long-horizon identity. Code is available at https://github.com/TaoLiveAIGC/AptAvatar

Related papers

• Long-Horizon Audio-Visual Generation for Persistent Stories and Interactive Worlds [60.18437892555415]
  We present JoyAI-Echo-1.5, a unified audio-visual generation system with two purpose-built variants.<n>The long-video variant introduces composable cross-shot memory that aggregates visual evidence across multiple prior shots and speaker cues derived from speech-filtered full-shot audio.<n>The world-model variant converts heterogeneous navigation inputs into calibrated metric 6-DoF camera trajectories and injects them through a geometry-aware conditioning pathway.
  arXiv  Detail & Related papers  (2026-08-24T15:31:12Z)
• Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars [16.361849320150863]
  Avatar-Forever is a decoupled parallel training framework for high-quality real-time infinite interactive avatars.<n>It supports audio-driven avatar generation while maintaining identity consistency, motion coherence, and visual fidelity.<n>It enables an end-to-end throughput of high-resolution 768x512 videos at 27.2 FPS on a single H100 GPU.
  arXiv  Detail & Related papers  (2026-08-12T14:29:08Z)
• Omni-LiveAvatar: Minute-Level Real-Time Streaming Joint Audio-Visual Avatar Generation [26.625772912688387]
  We present Omni-LiveAvatar, the first framework for minute-level, real-time streaming joint audio-video avatar generation.<n>Experiments show that Omni-LiveAvatar generates high-quality, synchronized minute-level avatars in real time.
  arXiv  Detail & Related papers  (2026-08-07T15:34:15Z)
• OPSD-V: On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Generators [68.69611976783243]
  OPSD-V is an on-policy self-distillation paradigm for post-training few-step autoregressive (AR) video diffusion models.<n>Key idea is to introduce real long-video data as temporal context during training and use it to provide dense trajectory-level supervision.<n>Experiments show consistent improvements in visual quality, motion dynamics, and VBenchLong scores.
  arXiv  Detail & Related papers  (2026-07-09T17:59:11Z)
• FlowLong: Inference-time Long Video Generation via Manifold-constrained Tweedie Matching [68.01498128172214]
  We propose a novel but simple inference-time approach for long video generation that is architecture-agnostic and requires no additional training.<n>Our method generates long videos via overlapping sliding windows, where predicted clean samples from adjacent windows are blended via emphTweedie matching to enforce both textbfmanifold constraint and temporal consistency across overlap regions.<n>Our method generates videos several times longer than the native window length while outperforming both training-free and autoregressive baselines in temporal consistency and visual quality, and further extends to audio-video joint generation and text-to-3DGS without any
  arXiv  Detail & Related papers  (2026-05-20T08:55:37Z)
• Generate Your Talking Avatar from Video Reference [54.88475181123363]
  Existing talking avatar methods typically adopt an image-to-video pipeline conditioned on a static reference image within the same scene as the target generation.<n>We introduce Talking Avatar generation from Video Reference (TAVR), a novel framework that shifts the paradigm by leveraging cross-scene video inputs.
  arXiv  Detail & Related papers  (2026-04-30T14:22:27Z)
• KlingAvatar 2.0 Technical Report [43.949604396366425]
  Our model effectively addresses the challenges of efficient, multimodally aligned long-form high-resolution video generation.<n>It delivers enhanced visual clarity, realistic lip-teeth rendering with accurate lip synchronization, strong identity preservation, and coherent multimodal instruction following.
  arXiv  Detail & Related papers  (2025-12-15T13:30:51Z)
• JoyAvatar: Real-time and Infinite Audio-Driven Avatar Generation with Autoregressive Diffusion [19.420963062956222]
  JoyAvatar is an audio-driven autoregressive model capable of real-time inference and infinite-length video generation.<n>Our model achieves competitive results in visual quality, temporal consistency, and lip synchronization.
  arXiv  Detail & Related papers  (2025-12-12T10:06:01Z)
• 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)
• StableAvatar: Infinite-Length Audio-Driven Avatar Video Generation [91.45910771331741]
  Current diffusion models for audio-driven avatar video generation struggle to synthesize long videos with natural audio synchronization and identity consistency.<n>This paper presents StableAvatar, the first end-to-end video diffusion transformer that synthesizes infinite-length high-quality videos without post-processing.
  arXiv  Detail & Related papers  (2025-08-11T17:58:24Z)

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.