Efficient Long-duration Talking Video Synthesis with Linear Diffusion Transformer under Multimodal Guidance

• URL: http://arxiv.org/abs/2411.16748v2
• Date: Mon, 09 Jun 2025 09:18:35 GMT
• Title: Efficient Long-duration Talking Video Synthesis with Linear Diffusion Transformer under Multimodal Guidance
• Authors: Haojie Zhang, Zhihao Liang, Ruibo Fu, Bingyan Liu, Zhengqi Wen, Xuefei Liu, Chenxing Li, Yaling Liang,
• Abstract summary: LetsTalk is a diffusion diffusion TranSformer for Talking video synthesis.<n>Our approach achieves state-of-the-art generation quality, producing temporally coherent and realistic videos.
• Score: 19.590464986176617
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Portrait image animation using audio has rapidly advanced, but challenges remain in efficiently fusing multimodal inputs while ensuring temporal and portrait consistency with minimal computational cost. To address this, we present LetsTalk, a LinEar diffusion TranSformer for Talking video synthesis. LetsTalk incorporates a deep compression autoencoder to obtain efficient latent representations, and a spatio-temporal-aware transformer with efficient linear attention to effectively fuse multimodal information and enhance spatio-temporal consistency. We systematically explore and summarize three fusion schemes, ranging from shallow to deep fusion. We thoroughly analyze their characteristics, applicability, and trade-offs, thereby bridging critical gaps in multimodal conditional guidance. Based on modality differences of image, audio, and video generation, we adopt deep (Symbiotic Fusion) for portrait to ensure consistency, and shallow (Direct Fusion) for audio to align animation with speech while preserving motion diversity. To maintain temporal consistency in long-duration video generation, we propose a memory bank mechanism that preserves inter-clip dependencies, effectively preventing degradation across extended sequences. Furthermore, we develop a noise-regularized training strategy that explicitly compensates for DDPM sampling artifacts, significantly improving the model's robustness in continuous generation scenarios.Our extensive experiments demonstrate that our approach achieves state-of-the-art generation quality, producing temporally coherent and realistic videos with enhanced diversity and liveliness, while maintaining remarkable efficiency through its optimized model design with 8$\times$ fewer parameters.

Related papers

• LoViC: Efficient Long Video Generation with Context Compression [68.22069741704158]
  We introduce LoViC, a DiT-based framework trained on million-scale open-domain videos.<n>At the core of our approach is FlexFormer, an expressive autoencoder that jointly compresses video and text into unified latent representations.
  arXiv  Detail & Related papers  (2025-07-17T09:46:43Z)
• STAGE: A Stream-Centric Generative World Model for Long-Horizon Driving-Scene Simulation [24.86836673853292]
  STAGE is an auto-regressive framework that pioneers hierarchical feature coordination and multiphase optimization for sustainable video synthesis.<n>HTFT enhances temporal consistency between video frames throughout the video generation process.<n>We generated 600 frames of high-quality driving videos on the Nuscenes dataset, which far exceeds the maximum length achievable by existing methods.
  arXiv  Detail & Related papers  (2025-06-16T06:53:05Z)
• SkyReels-Audio: Omni Audio-Conditioned Talking Portraits in Video Diffusion Transformers [25.36460340267922]
  We present SkyReels-Audio, a unified framework for synthesizing high-fidelity and temporally coherent talking portrait videos.<n>Our framework supports infinite-length generation and editing, while enabling diverse and controllable conditioning through multimodal inputs.
  arXiv  Detail & Related papers  (2025-06-01T04:27:13Z)
• AlignDiT: Multimodal Aligned Diffusion Transformer for Synchronized Speech Generation [41.74261260212531]
  multimodal-to-speech task has gained increasing attention due to its wide range of applications, such as film production, dubbing, and virtual avatars. Existing methods still suffer from limitations in speech intelligibility, audio-video synchronization, speech naturalness, and voice similarity to the reference speaker. We propose AlignDiT, a multimodal Aligned Diffusion Transformer that generates accurate, synchronized, and natural-sounding speech from aligned multimodal inputs.
  arXiv  Detail & Related papers  (2025-04-29T10:56:24Z)
• DiVE: Efficient Multi-View Driving Scenes Generation Based on Video Diffusion Transformer [56.98400572837792]
  DiVE produces high-fidelity, temporally coherent, and cross-view consistent multi-view videos.<n>These innovations collectively achieve a 2.62x speedup with minimal quality degradation.
  arXiv  Detail & Related papers  (2025-04-28T09:20:50Z)
• VideoFusion: A Spatio-Temporal Collaborative Network for Mutli-modal Video Fusion and Restoration [26.59510171451438]
  Existing multi-sensor fusion research predominantly integrates complementary from multiple images rather than videos. VideoFusion exploits cross-modal complementarity and temporal dynamics to generate context-temporally coherent videos. Extensive experiments reveal that VideoFusion outperforms existing image-oriented fusion paradigms in sequential scenarios.
  arXiv  Detail & Related papers  (2025-03-30T08:27:18Z)
• Cosh-DiT: Co-Speech Gesture Video Synthesis via Hybrid Audio-Visual Diffusion Transformers [58.86974149731874]
  Cosh-DiT is a Co-speech gesture video system with hybrid Diffusion Transformers. We introduce an audio Diffusion Transformer to synthesize expressive gesture dynamics synchronized with speech rhythms. For realistic video synthesis conditioned on the generated speech-driven motion, we design a visual Diffusion Transformer.
  arXiv  Detail & Related papers  (2025-03-13T01:36:05Z)
• Tuning-Free Multi-Event Long Video Generation via Synchronized Coupled Sampling [81.37449968164692]
  We propose Synchronized Coupled Sampling (SynCoS), a novel inference framework that synchronizes denoising paths across the entire video.<n>Our approach combines two complementary sampling strategies, which ensure seamless local transitions and enforce global coherence.<n>Extensive experiments show that SynCoS significantly improves multi-event long video generation, achieving smoother transitions and superior long-range coherence.
  arXiv  Detail & Related papers  (2025-03-11T16:43:45Z)
• RepVideo: Rethinking Cross-Layer Representation for Video Generation [53.701548524818534]
  We propose RepVideo, an enhanced representation framework for text-to-video diffusion models.<n>By accumulating features from neighboring layers to form enriched representations, this approach captures more stable semantic information.<n>Our experiments demonstrate that our RepVideo not only significantly enhances the ability to generate accurate spatial appearances, but also improves temporal consistency in video generation.
  arXiv  Detail & Related papers  (2025-01-15T18:20:37Z)
• High-fidelity and Lip-synced Talking Face Synthesis via Landmark-based Diffusion Model [89.29655924125461]
  We propose a novel landmark-based diffusion model for talking face generation. We first establish the less ambiguous mapping from audio to landmark motion of lip and jaw. Then, we introduce an innovative conditioning module called TalkFormer to align the synthesized motion with the motion represented by landmarks.
  arXiv  Detail & Related papers  (2024-08-10T02:58:28Z)
• Anchored Diffusion for Video Face Reenactment [17.343307538702238]
  We introduce Anchored Diffusion, a novel method for synthesizing relatively long and seamless videos. We train our model on video sequences with random non-uniform temporal spacing and incorporate temporal information via external guidance. During inference, we leverage the transformer architecture to modify the diffusion process, generating a batch of non-uniform sequences anchored to a common frame.
  arXiv  Detail & Related papers  (2024-07-21T13:14:17Z)
• MultiDiff: Consistent Novel View Synthesis from a Single Image [60.04215655745264]
  MultiDiff is a novel approach for consistent novel view synthesis of scenes from a single RGB image. Our results demonstrate that MultiDiff outperforms state-of-the-art methods on the challenging, real-world datasets RealEstate10K and ScanNet.
  arXiv  Detail & Related papers  (2024-06-26T17:53:51Z)
• Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation [29.87407471246318]
  This research delves into the complexities of synchronizing facial movements and creating visually appealing, temporally consistent animations. Our innovative approach embraces the end-to-end diffusion paradigm and introduces a hierarchical audio-driven visual synthesis module. The proposed hierarchical audio-driven visual synthesis offers adaptive control over expression and pose diversity, enabling more effective personalization tailored to different identities.
  arXiv  Detail & Related papers  (2024-06-13T04:33:20Z)
• FRESCO: Spatial-Temporal Correspondence for Zero-Shot Video Translation [85.29772293776395]
  We introduce FRESCO, intra-frame correspondence alongside inter-frame correspondence to establish a more robust spatial-temporal constraint. This enhancement ensures a more consistent transformation of semantically similar content across frames. Our approach involves an explicit update of features to achieve high spatial-temporal consistency with the input video.
  arXiv  Detail & Related papers  (2024-03-19T17:59:18Z)
• FaceChain-ImagineID: Freely Crafting High-Fidelity Diverse Talking Faces from Disentangled Audio [45.71036380866305]
  We abstract the process of people hearing speech, extracting meaningful cues, and creating dynamically audio-consistent talking faces from a single audio. Specifically, it involves two critical challenges: one is to effectively decouple identity, content, and emotion from entangled audio, and the other is to maintain intra-video diversity and inter-video consistency. We introduce the Controllable Coherent Frame generation, which involves the flexible integration of three trainable adapters with frozen Latent Diffusion Models.
  arXiv  Detail & Related papers  (2024-03-04T09:59:48Z)
• DiffSpeaker: Speech-Driven 3D Facial Animation with Diffusion Transformer [110.32147183360843]
  Speech-driven 3D facial animation is important for many multimedia applications. Recent work has shown promise in using either Diffusion models or Transformer architectures for this task. We present DiffSpeaker, a Transformer-based network equipped with novel biased conditional attention modules.
  arXiv  Detail & Related papers  (2024-02-08T14:39:16Z)
• Lumiere: A Space-Time Diffusion Model for Video Generation [75.54967294846686]
  We introduce a Space-Time U-Net architecture that generates the entire temporal duration of the video at once. This is in contrast to existing video models which synthesize distants followed by temporal super-resolution. By deploying both spatial and (importantly) temporal down- and up-sampling, our model learns to directly generate a full-frame-rate, low-resolution video.
  arXiv  Detail & Related papers  (2024-01-23T18:05:25Z)
• SAiD: Speech-driven Blendshape Facial Animation with Diffusion [6.4271091365094515]
  Speech-driven 3D facial animation is challenging due to the scarcity of large-scale visual-audio datasets. We propose a speech-driven 3D facial animation with a diffusion model (SAiD), a lightweight Transformer-based U-Net with a cross-modality alignment bias between audio and visual to enhance lip synchronization.
  arXiv  Detail & Related papers  (2023-12-25T04:40:32Z)
• Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution [65.91317390645163]
  Upscale-A-Video is a text-guided latent diffusion framework for video upscaling. It ensures temporal coherence through two key mechanisms: locally, it integrates temporal layers into U-Net and VAE-Decoder, maintaining consistency within short sequences. It also offers greater flexibility by allowing text prompts to guide texture creation and adjustable noise levels to balance restoration and generation.
  arXiv  Detail & Related papers  (2023-12-11T18:54:52Z)
• Taming Diffusion Models for Audio-Driven Co-Speech Gesture Generation [41.292644854306594]
  We propose a novel diffusion-based framework, named Diffusion Co-Speech Gesture (DiffGesture) DiffGesture achieves state-of-theart performance, which renders coherent gestures with better mode coverage and stronger audio correlations.
  arXiv  Detail & Related papers  (2023-03-16T07:32:31Z)
• Multimodal Token Fusion for Vision Transformers [54.81107795090239]
  We propose a multimodal token fusion method (TokenFusion) for transformer-based vision tasks. To effectively fuse multiple modalities, TokenFusion dynamically detects uninformative tokens and substitutes these tokens with projected and aggregated inter-modal features. The design of TokenFusion allows the transformer to learn correlations among multimodal features, while the single-modal transformer architecture remains largely intact.
  arXiv  Detail & Related papers  (2022-04-19T07:47:50Z)

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.