mlsanityData to 7 Oct 2026

Diffusion Adversarial Post-Training for One-Step Video Generation

arXiv 2501.08316 ↗First posted 14 Jan 2025cs.CV cs.AI cs.LGcited by 142

On the map: Diffusion models → Video generation

Abstract (arXiv)

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.

Key facts. Cited by 142 papers in the map (data through 7 Oct 2026). Placed in Video generation, one of 14 directions in Diffusion models. Builds on 78 of its 89 references that are in the map. First posted on arXiv 14 Jan 2025.

Builds on

78 of 89 references.

Closest ancestors · 8

Same direction, newest first

  1. 2024OSV: One Step is Enough for High-Quality Image to Video Generation17 Sep
  2. 2024Motion Consistency Model: Accelerating Video Diffusion with Disentangled Motion-Appearance Distillation11 Jun
  3. 2024SF-V: Single Forward Video Generation Model6 Jun
  4. 2024AnimateDiff-Lightning: Cross-Model Diffusion Distillation19 Mar
  5. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets25 Nov
  6. 2023ModelScope Text-to-Video Technical Report12 Aug
  7. 2023AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning10 Jul
  8. 2022MagicVideo: Efficient Video Generation With Latent Diffusion Models20 Nov

Other references · 70

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  7. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  8. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  9. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  10. 2022Scalable Diffusion Models with Transformerscited by 5,931
  11. 2022Classifier-Free Diffusion Guidancecited by 5,717
  12. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
38 more
  1. 2022Flow Matching for Generative Modelingcited by 5,426
  2. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
  3. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  4. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,611
  5. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  6. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  7. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  8. 2023FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioningcited by 2,551
  9. 2023Consistency Modelscited by 1,778
  10. 2023VBench: Comprehensive Benchmark Suite for Video Generative Modelscited by 1,755
  11. 2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,597
  12. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,287
  13. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,207
  14. 2021Alias-Free Generative Adversarial Networkscited by 1,181
  15. 2023One-step Diffusion with Distribution Matching Distillationcited by 978
  16. 2023MVDream: Multi-view Diffusion for 3D Generationcited by 928
  17. 2024WorldSimBench: Towards Video Generation Models as World Simulatorscited by 867
  18. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesiscited by 854
  19. 2023Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inferencecited by 826
  20. 2016Training Deep Nets with Sublinear Memory Costcited by 825
  21. 2023Adversarial Diffusion Distillationcited by 741
  22. 2018Which Training Methods for GANs do actually Converge?cited by 672
  23. 2024Improved Distribution Matching Distillation for Fast Image Synthesiscited by 648
  24. 2023PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallelcited by 641
  25. 2024Movie Gen: A Cast of Media Foundation Modelscited by 614
  26. 2024FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precisioncited by 507
  27. 2023Scaling up GANs for Text-to-Image Synthesiscited by 492
  28. 2023Improved Techniques for Training Consistency Modelscited by 430
  29. 2023InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generationcited by 387
  30. 2023Common Diffusion Noise Schedules and Sample Steps are Flawedcited by 308
  31. 2021StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2cited by 300
  32. 2024Guiding a Diffusion Model with a Bad Version of Itselfcited by 286
  33. 2024Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillationcited by 276
  34. 2024Simplifying, Stabilizing and Scaling Continuous-Time Consistency Modelscited by 276
  35. 2024SDXL-Lightning: Progressive Adversarial Diffusion Distillationcited by 258
  36. 2023Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Modelscited by 232
  37. 2023Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolutioncited by 226
  38. 2023StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesiscited by 212

50 most cited of 70 All 70 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 65; 2026: 77.

142 papers.

Sort:

By area:

  1. 2025Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusioncited by 569
  2. 2025Seedance 1.0: Exploring the Boundaries of Video Generation Modelscited by 247
  3. 2025Seedream 4.0: Toward Next-generation Multimodal Image Generationcited by 233
  4. 2025Rolling Forcing: Autoregressive Long Video Diffusion in Real Timecited by 209
  5. 2025WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modelingcited by 152
  6. 2026Advancing Open-source World Modelscited by 144
  7. 2025OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Modelscited by 127
  8. 2025Phantom: Subject-consistent video generation via cross-modal alignmentcited by 126
  9. 2025CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Modelscited by 97
  10. 2025Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generationcited by 84
  11. 2025Seaweed-7B: Cost-Effective Training of Video Generation Foundation Modelcited by 81
  12. 2025Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistencycited by 81
38 more
  1. 2025Scaling Instruction-Based Video Editing with a High-Quality Synthetic Datasetcited by 76
  2. 2025MotionStream: Real-Time Video Generation with Interactive Motion Controlscited by 71
  3. 2025HunyuanVideo-Avatar: High-Fidelity Audio-Driven Human Animation for Multiple Characterscited by 64
  4. 2025Let Them Talk: Audio-Driven Multi-Person Conversational Video Generationcited by 64
  5. 2026Helios: Real Real-Time Long Video Generation Modelcited by 56
  6. 2025BLIP3o-NEXT: Next Frontier of Native Image Generationcited by 50
  7. 2025SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Trainingcited by 45
  8. 2026Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generationcited by 44
  9. 2025Distribution Matching Distillation Meets Reinforcement Learningcited by 43
  10. 2025FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolutioncited by 40
  11. 2025Adversarial Distribution Matching for Diffusion Distillation Towards Efficient Image and Video Synthesiscited by 39
  12. 2025Decoupled DMD: CFG Augmentation as the Spear, Distribution Matching as the Shieldcited by 38
  13. 2025DreamActor-M1: Holistic, Expressive and Robust Human Image Animation with Hybrid Guidancecited by 36
  14. 2025Sparse-vDiT: Unleashing the Power of Sparse Attention to Accelerate Video Diffusion Transformerscited by 34
  15. 2025DOVE: Efficient One-Step Diffusion Model for Real-World Video Super-Resolutioncited by 30
  16. 2025FlashWorld: High-quality 3D Scene Generation within Secondscited by 30
  17. 2026Transition Matching Distillation for Fast Video Generationcited by 27
  18. 2025StreamAvatar: Streaming Diffusion Models for Real-Time Interactive Human Avatarscited by 24
  19. 2025Geometry-aware 4D Video Generation for Robot Manipulationcited by 23
  20. 2026AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillationcited by 23
  21. 2026Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Modelscited by 23
  22. 2025Dual-Expert Consistency Model for Efficient and High-Quality Video Generationcited by 21
  23. 2025Phased DMD: Few-step Distribution Matching Distillation via Score Matching within Subintervalscited by 21
  24. 2025QVGen: Pushing the Limit of Quantized Video Generative Modelscited by 20
  25. 2025InterActHuman: Multi-Concept Human Animation with Layout-Aligned Audio Conditionscited by 20
  26. 2026minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Modelscited by 19
  27. 2025OmniV2V: Versatile Video Generation and Editing via Dynamic Content Manipulationcited by 18
  28. 2026RealWonder: Real-Time Physical Action-Conditioned Video Generationcited by 18
  29. 2026INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modelingcited by 18
  30. 2025DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencodercited by 15
  31. 2026LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editingcited by 15
  32. 2025Model Reveals What to Cache: Profiling-Based Feature Reuse for Video Diffusion Modelscited by 14
  33. 2025Fast Text-to-Audio Generation with Adversarial Post-Trainingcited by 14
  34. 2025A Survey on Cache Methods in Diffusion Models: Toward Efficient Multi-Modal Generationcited by 14
  35. 2025AccVideo: Accelerating Video Diffusion Model with Synthetic Datasetcited by 13
  36. 2025Hyper-Bagel: A Unified Acceleration Framework for Multimodal Understanding and Generationcited by 13
  37. 2026One-Forcing: Towards Stable One-Step Autoregressive Video Generationcited by 13
  38. 2026ActWorld: From Explorable to Interactive World Model via Action-Aware Memorycited by 13

50 most cited of 142 All 142 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Survey of Video Diffusion Models: Foundations, Implementations, and Applications
  2. 2022VIDM: Video Implicit Diffusion Models
  3. 2023APLA: Additional Perturbation for Latent Noise with Adversarial Training Enables Consistency
  4. 2024Accelerating Video Diffusion Models via Distribution Matching
  5. 2022Truncated Diffusion Probabilistic Models and Diffusion-based Adversarial Auto-Encoders
  6. 2022SinFusion: Training Diffusion Models on a Single Image or Video
  7. 2026Adversarial Training for Pixel Diffusion
  8. 2022Video Diffusion Models