TurboTalk: Progressive Distillation for One-Step Audio-Driven Talking Avatar Generation

• URL: http://arxiv.org/abs/2604.14580v1
• Date: Thu, 16 Apr 2026 03:19:29 GMT
• Title: TurboTalk: Progressive Distillation for One-Step Audio-Driven Talking Avatar Generation
• Abstract summary: We propose a two-stage progressive distillation framework that effectively compresses a multi-step audio-driven video diffusion model into a single-step generator.<n>Our method achieve single-step generation of video talking avatar, boosting inference speed by 120 times while maintaining high generation quality.
• Score: 48.460504727347036
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Existing audio-driven video digital human generation models rely on multi-step denoising, resulting in substantial computational overhead that severely limits their deployment in real-world settings. While one-step distillation approaches can significantly accelerate inference, they often suffer from training instability. To address this challenge, we propose TurboTalk, a two-stage progressive distillation framework that effectively compresses a multi-step audio-driven video diffusion model into a single-step generator. We first adopt Distribution Matching Distillation to obtain a strong and stable 4-step student, and then progressively reduce the denoising steps from 4 to 1 through adversarial distillation. To ensure stable training under extreme step reduction, we introduce a progressive timestep sampling strategy and a self-compare adversarial objective that provides an intermediate adversarial reference that stabilizes progressive distillation. Our method achieve single-step generation of video talking avatar, boosting inference speed by 120 times while maintaining high generation quality.

Related papers

• LeapTalk: Breaking the Latency-Quality Trade-off in Talking Head Generation [28.818825505825476]
  We propose LeapTalk, a novel framework that achieves stable and real-time talking-head generation with a single forward step.<n>Our method achieves high-fidelity and temporally consistent video generation with only 1 step at up to 200 FPS.
  arXiv  Detail & Related papers  (2026-07-29T14:44:57Z)
• Dynamic-in-Few-Step: Unifying Dynamic Computation and Few-Step Distillation for Efficient Video Generation [24.896148135296198]
  Video Diffusion Models (VDMs) have demonstrated superior generation quality but suffer from prohibitive computational costs.<n>We propose a novel post-training acceleration framework that exploits this redundancy by integrating dynamic structural sparsification directly into the distillation process.
  arXiv  Detail & Related papers  (2026-07-07T13:14:33Z)
• One-Forcing: Towards Stable One-Step Autoregressive Video Generation [48.93167853711741]
  One-Forcing is a simple yet effective approach which augments the DMD objective with an auxiliary GAN loss for high-quality and efficient one-step video generation.<n>One-Forcing achieves a total score of 83.76, establishing state-of-the-art performance among one-step causal video generation methods.
  arXiv  Detail & Related papers  (2026-05-22T10:16:58Z)
• Streaming Autoregressive Video Generation via Diagonal Distillation [50.13573884115673]
  Autoregressive models offer a natural framework for sequential frame synthesis but require heavy computation to achieve high fidelity.<n>We propose Diagonal Distillation to exploit temporal information across both video chunks and denoising steps.<n>Our method generates a 5-second video in 2.61 seconds (up to 31 FPS), achieving a 277.3x speedup over the undistilled model.
  arXiv  Detail & Related papers  (2026-03-10T10:45:24Z)
• GPD: Guided Progressive Distillation for Fast and High-Quality Video Generation [48.965157828225074]
  We propose Guided Progressive Distillation (GPD), a framework that accelerates the diffusion process for fast and high-quality video generation.<n>GPD reduces the number of sampling steps from 48 to 6 while maintaining competitive visual quality on VBench.
  arXiv  Detail & Related papers  (2026-02-02T08:47:33Z)
• Towards One-step Causal Video Generation via Adversarial Self-Distillation [71.30373662465648]
  Recent hybrid video generation models combine autoregressive temporal dynamics with diffusion-based spatial denoising.<n>Our framework produces a single distilled model that flexibly supports multiple inference-step settings.
  arXiv  Detail & Related papers  (2025-11-03T10:12:47Z)
• One-Step Diffusion Policy: Fast Visuomotor Policies via Diffusion Distillation [80.71541671907426]
  OneStep Diffusion Policy (OneDP) is a novel approach that distills knowledge from pre-trained diffusion policies into a single-step action generator. OneDP significantly accelerates response times for robotic control tasks.
  arXiv  Detail & Related papers  (2024-10-28T17:54:31Z)
• Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesis [20.2271205957037]
  Hyper-SD is a novel framework that amalgamates the advantages of ODE Trajectory Preservation and Reformulation. We introduce Trajectory Segmented Consistency Distillation to progressively perform consistent distillation within pre-defined time-step segments. We incorporate human feedback learning to boost the performance of the model in a low-step regime and mitigate the performance loss incurred by the distillation process.
  arXiv  Detail & Related papers  (2024-04-21T15:16:05Z)

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.