mlsanityData to 7 Oct 2026

Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model

arXiv 2504.08685 ↗First posted 11 Apr 2025cs.CV cs.AIcited by 81

Not on the map. Why?

Cited by 31 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

This technical report presents a cost-efficient strategy for training a video generation foundation model. We present a mid-sized research model with approximately 7 billion parameters (7B) called Seaweed-7B trained from scratch using 665,000 H100 GPU hours. Despite being trained with moderate computational resources, Seaweed-7B demonstrates highly competitive performance compared to contemporary video generation models of much larger size. Design choices are especially crucial in a resource-constrained setting. This technical report highlights the key design decisions that enhance the performance of the medium-sized diffusion model. Empirically, we make two observations: (1) Seaweed-7B achieves performance comparable to, or even surpasses, larger models trained on substantially greater GPU resources, and (2) our model, which exhibits strong generalization ability, can be effectively adapted across a wide range of downstream applications either by lightweight fine-tuning or continue training. See the project page at https://seaweed.video/

Key facts. Cited by 81 papers in the map (data through 7 Oct 2026). Builds on 69 of its 87 references that are in the map. First posted on arXiv 11 Apr 2025.

Builds on

69 of 87 references.

References · 69

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  6. 2024The Llama 3 Herd of Modelscited by 14,192
  7. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  8. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  9. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  10. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  11. 2022Scalable Diffusion Models with Transformerscited by 5,931
  12. 2022Classifier-Free Diffusion Guidancecited by 5,717
38 more
  1. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  2. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
  3. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  4. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  5. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,337
  6. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,151
  7. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  8. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  9. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  10. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  11. 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,536
  12. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,526
  13. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
  14. 2022Video Diffusion Modelscited by 2,280
  15. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,903
  16. 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,725
  17. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  18. 2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,597
  19. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Modelscited by 1,465
  20. 2018Towards Accurate Generative Models of Video: A New Metric & Challengescited by 1,204
  21. 2023ImageBind: One Embedding Space To Bind Them Allcited by 1,162
  22. 2021Video Swin Transformercited by 1,090
  23. 2025Cosmos World Foundation Model Platform for Physical AIcited by 833
  24. 2016Training Deep Nets with Sublinear Memory Costcited by 825
  25. 2023Diffusion Model Alignment Using Direct Preference Optimizationcited by 767
  26. 2018Which Training Methods for GANs do actually Converge?cited by 672
  27. 2023PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallelcited by 641
  28. 2023Language Model Beats Diffusion -- Tokenizer is Key to Visual Generationcited by 633
  29. 2022AudioLM: a Language Modeling Approach to Audio Generationcited by 611
  30. 2023Structure and Content-Guided Video Synthesis with Diffusion Modelscited by 589
  31. 2024LTX-Video: Realtime Video Latent Diffusioncited by 549
  32. 2017Ray: A Distributed Framework for Emerging AI Applicationscited by 516
  33. 2023VideoPoet: A Large Language Model for Zero-Shot Video Generationcited by 479
  34. 2022MAGVIT: Masked Generative Video Transformercited by 341
  35. 2023Photorealistic Video Generation with Diffusion Modelscited by 304
  36. 2024Open-Sora Plan: Open-Source Large Video Generation Modelcited by 286
  37. 2023DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Modelscited by 239
  38. 2023Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolutioncited by 226

50 most cited of 69 All 69 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 57; 2026: 24.

81 papers.

Sort:

By area:

  1. 2025Emerging Properties in Unified Multimodal Pretrainingcited by 855
  2. 2025Seedance 1.0: Exploring the Boundaries of Video Generation Modelscited by 247
  3. 2025Show-o2: Improved Native Unified Multimodal Modelscited by 242
  4. 2025Rolling Forcing: Autoregressive Long Video Diffusion in Real Timecited by 209
  5. 2026Seedance 2.0: Advancing Video Generation for World Complexitycited by 142
  6. 2025SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformercited by 91
  7. 2025Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generationcited by 84
  8. 2025OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generationcited by 73
  9. 2025RewardDance: Reward Scaling in Visual Generationcited by 63
  10. 2025Waver: Wave Your Way to Lifelike Video Generationcited by 52
  11. 2025Captain Cinema: Towards Short Movie Generationcited by 48
  12. 2025SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Trainingcited by 45
38 more
  1. 2025Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representationscited by 44
  2. 2025ATI: Any Trajectory Instruction for Controllable Video Generationcited by 42
  3. 2025TUNA: Taming Unified Visual Representations for Native Unified Multimodal Modelscited by 34
  4. 2025DenseDPO: Fine-Grained Temporal Preference Optimization for Video Diffusion Modelscited by 32
  5. 2025OneStory: Coherent Multi-Shot Video Generation with Adaptive Memorycited by 31
  6. 2025OmniHuman-1.5: Instilling an Active Mind in Avatars via Cognitive Simulationcited by 30
  7. 2025AToken: A Unified Tokenizer for Visioncited by 30
  8. 2025Omni-Effects: Unified and Spatially-Controllable Visual Effects Generationcited by 27
  9. 2026Transition Matching Distillation for Fast Video Generationcited by 27
  10. 2025WorldExplorer: Towards Generating Fully Navigable 3D Scenescited by 26
  11. 2025DreamArt: Generating Interactable Articulated Objects from a Single Imagecited by 25
  12. 2025A Survey of Interactive Generative Videocited by 23
  13. 2025PanoWan: Lifting Diffusion Video Generation Models to 360deg with Latitude/Longitude-aware Mechanismscited by 22
  14. 2025CineTechBench: A Benchmark for Cinematographic Technique Understanding and Generationcited by 21
  15. 2025InterActHuman: Multi-Concept Human Animation with Layout-Aligned Audio Conditionscited by 20
  16. 2025Hierarchical Fine-grained Preference Optimization for Physically Plausible Video Generationcited by 20
  17. 2025ByteMorph: Benchmarking Instruction-Guided Image Editing with Non-Rigid Motionscited by 19
  18. 2025DreamActor-H1: High-Fidelity Human-Product Demonstration Video Generation via Motion-designed Diffusion Transformerscited by 19
  19. 2025Seed3D 1.0: From Images to High-Fidelity Simulation-Ready 3D Assetscited by 19
  20. 2025VINCIE: Unlocking In-context Image Editing from Videocited by 17
  21. 2025Phantom-Data : Towards a General Subject-Consistent Video Generation Datasetcited by 17
  22. 2025MoGA: Mixture-of-Groups Attention for End-to-End Long Video Generationcited by 16
  23. 2025Turbo-VAED: Fast and Stable Transfer of Video-VAEs to Mobile Devicescited by 15
  24. 2025A Survey on Cache Methods in Diffusion Models: Toward Efficient Multi-Modal Generationcited by 14
  25. 2026LIVE: Long-horizon Interactive Video World Modelingcited by 14
  26. 2025X-UniMotion: Animating Human Images with Expressive, Unified and Identity-Agnostic Motion Latentscited by 13
  27. 2025Hyper-Bagel: A Unified Acceleration Framework for Multimodal Understanding and Generationcited by 13
  28. 2025Exploring Diffusion Transformer Designs via Graftingcited by 12
  29. 2025FantasyPortrait: Enhancing Multi-Character Portrait Animation with Expression-Augmented Diffusion Transformerscited by 12
  30. 2025EditMGT: Unleashing Potentials of Masked Generative Transformers in Image Editingcited by 12
  31. 2026Mode Seeking meets Mean Seeking for Fast Long Video Generationcited by 12
  32. 2026Group Editing: Edit Multiple Images in One Gocited by 11
  33. 2025Adversarial Flow Modelscited by 10
  34. 2025Delving into Latent Spectral Biasing of Video VAEs for Superior Diffusabilitycited by 10
  35. 2025LinVideo: A Post-Training Framework towards O(n) Attention in Efficient Video Generationcited by 9
  36. 2025STARFlow-V: End-to-End Video Generative Modeling with Normalizing Flowscited by 9
  37. 2026Preserving Forgery Artifacts: AI-Generated Video Detection at Native Scalecited by 8
  38. 2026Leveraging Verifier-Based Reinforcement Learning in Image Editingcited by 8

50 most cited of 81 All 81 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Aquarius: A Family of Industry-Level Video Generation Models for Marketing Scenarios
  2. 2025LongCat-Video Technical Report
  3. 2025GigaVideo-1: Advancing Video Generation via Automatic Feedback with 4 GPU-Hours Fine-Tuning
  4. 2026Helios: Real Real-Time Long Video Generation Model
  5. 2024DOLLAR: Few-Step Video Generation via Distillation and Latent Reward Optimization
  6. 2024Grid Diffusion Models for Text-to-Video Generation
  7. 2024Video-Infinity: Distributed Long Video Generation
  8. 2026GPD: Guided Progressive Distillation for Fast and High-Quality Video Generation