Real-time One-Step Diffusion-based Expressive Portrait Videos Generation
Latent diffusion models have made great strides in generating expressive portrait videos with accurate lip-sync and natural motion from a single reference image and audio input. However, these models are far from real-time, often requiring many sampling steps that take minutes to generate even one second of video-significantly limiting practical use. We introduce OSA-LCM (One-Step Avatar Latent Consistency Model), paving the way for real-time diffusion-based avatars. Our method achieves comparable video quality to existing methods but requires only one sampling step, making it more than 10x faster. To accomplish this, we propose a novel avatar discriminator design that guides lip-audio consistency and motion expressiveness to enhance video quality in limited sampling steps. Additionally, we employ a second-stage training architecture using an editing fine-tuned method (EFT), transforming video generation into an editing task during training to effectively address the temporal gap challenge in single-step generation. Experiments demonstrate that OSA-LCM outperforms existing open-source portrait video generation models while operating more efficiently with a single sampling step.
Code (1)
Tasks
Video GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
PersonaLive! Expressive Portrait Image Animation for Live Streaming
Current diffusion-based portrait animation models predominantly focus on enhancing visual quality and expression realism, while overlooking generation latency and real-time performance, which restricts their application …
Video GenerationChatAnyone: Stylized Real-time Portrait Video Generation with Hierarchical Motion Diffusion Model
Real-time interactive video-chat portraits have been increasingly recognized as the future trend, particularly due to the remarkable progress made in text and voice chat technologies. However, existing methods primarily …
GPUVideo GenerationDeX-Portrait: Disentangled and Expressive Portrait Animation via Explicit and Latent Motion Representations
Portrait animation from a single source image and a driving video is a long-standing problem. Recent approaches tend to adopt diffusion-based image/video generation models for realistic and expressive animation. However,…
Video GenerationExpPortrait: Expressive Portrait Generation via Personalized Representation
While diffusion models have shown great potential in portrait generation, generating expressive, coherent, and controllable cinematic portrait videos remains a significant challenge. Existing intermediate signals for por…
FlashPortrait: 6x Faster Infinite Portrait Animation with Adaptive Latent Prediction
Current diffusion-based acceleration methods for long-portrait animation struggle to ensure identity (ID) consistency. This paper presents FlashPortrait, an end-to-end video diffusion transformer capable of synthesizing …