paper-with-me

홈 › Papers

Diffusion Adversarial Post-Training for One-Step Video Generation

2025-01-14 · Shanchuan Lin, Xin Xia, Yuxi Ren, Ceyuan Yang, Xuefeng Xiao, Lu Jiang

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.

📄 PDF Abstract BibTeX arXiv:2501.08316

Code (0)

등록된 구현이 없습니다.

Tasks

Video Generation

Methods 이 논문이 사용한 방법론

R1 Regularization R_INLINE_MATH_1 Regularization is a regularization technique and gradient penalty for training [generative adversarial…
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training

2025-06-05 · Jianyi Wang, Shanchuan Lin, Zhijie Lin, Yuxi Ren 외

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 Restoration

MoGAN: Improving Motion Quality in Video Diffusion via Few-Step Motion Adversarial Post-Training

2025-11-26 · Haotian Xue, Qi Chen, Zhonghao Wang, Xun Huang 외 arxiv

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 Generation

SF-V: Single Forward Video Generation Model

2024-06-06 · Zhixing Zhang, Yanyu Li, Yushu Wu, Yanwu Xu 외

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 Generation

Phased One-Step Adversarial Equilibrium for Video Diffusion Models

2025-08-28 · Jiaxiang Cheng, Bing Ma, Xuhua Ren, Hongyi Henry Jin 외 arxiv

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 Generation

OS-DiffVSR: Towards One-step Latent Diffusion Model for High-detailed Real-world Video Super-Resolution

2025-09-20 · Hanting Li, Huaao Tang, Jianhong Han, Tianxiong Zhou 외 arxiv

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