Diffusion Adversarial Post-Training for One-Step Video Generation
The diffusion models are widely used for image and video generation, but their iterative generation process is slow and expansive. While existing distillation approaches have demonstrated the potential for one-step generation in the image domain, they still suffer from significant quality degradation. In this work, we propose Adversarial Post-Training (APT) against real data following diffusion pre-training for one-step video generation. To improve the training stability and quality, we introduce several improvements to the model architecture and training procedures, along with an approximated R1 regularization objective. Empirically, our experiments show that our adversarial post-trained model, Seaweed-APT, can generate 2-second, 1280x720, 24fps videos in real time using a single forward evaluation step. Additionally, our model is capable of generating 1024px images in a single step, achieving quality comparable to state-of-the-art methods.
Code (0)
등록된 구현이 없습니다.
Tasks
Video GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training
Recent advances in diffusion-based video restoration (VR) demonstrate significant improvement in visual quality, yet yield a prohibitive computational cost during inference. While several distillation-based approaches ha…
Image RestorationVideo RestorationMoGAN: Improving Motion Quality in Video Diffusion via Few-Step Motion Adversarial Post-Training
Video diffusion models achieve strong frame-level fidelity but still struggle with motion coherence, dynamics and realism, often producing jitter, ghosting, or implausible dynamics. A key limitation is that the standard …
Video GenerationSF-V: Single Forward Video Generation Model
Diffusion-based video generation models have demonstrated remarkable success in obtaining high-fidelity videos through the iterative denoising process. However, these models require multiple denoising steps during sampli…
DenoisingmodelVideo GenerationPhased One-Step Adversarial Equilibrium for Video Diffusion Models
Video diffusion generation suffers from critical sampling efficiency bottlenecks, particularly for large-scale models and long contexts. Existing video acceleration methods, adapted from image-based techniques, lack a si…
Video GenerationOS-DiffVSR: Towards One-step Latent Diffusion Model for High-detailed Real-world Video Super-Resolution
Recently, latent diffusion models has demonstrated promising performance in real-world video super-resolution (VSR) task, which can reconstruct high-quality videos from distorted low-resolution input through multiple dif…
Image Super-ResolutionVideo Super-Resolution