mlsanityData to 7 Oct 2026

Seedance 1.0: Exploring the Boundaries of Video Generation Models

arXiv 2506.09113 ↗First posted 10 Jun 2025cs.CVcited by 247

On the map: Diffusion models → Video generation

Abstract (arXiv)

Notable breakthroughs in diffusion modeling have propelled rapid improvements in video generation, yet current foundational model still face critical challenges in simultaneously balancing prompt following, motion plausibility, and visual quality. In this report, we introduce Seedance 1.0, a high-performance and inference-efficient video foundation generation model that integrates several core technical improvements: (i) multi-source data curation augmented with precision and meaningful video captioning, enabling comprehensive learning across diverse scenarios; (ii) an efficient architecture design with proposed training paradigm, which allows for natively supporting multi-shot generation and jointly learning of both text-to-video and image-to-video tasks. (iii) carefully-optimized post-training approaches leveraging fine-grained supervised fine-tuning, and video-specific RLHF with multi-dimensional reward mechanisms for comprehensive performance improvements; (iv) excellent model acceleration achieving ~10x inference speedup through multi-stage distillation strategies and system-level optimizations. Seedance 1.0 can generate a 5-second video at 1080p resolution only with 41.4 seconds (NVIDIA-L20). Compared to state-of-the-art video generation models, Seedance 1.0 stands out with high-quality and fast video generation having superior spatiotemporal fluidity with structural stability, precise instruction adherence in complex multi-subject contexts, native multi-shot narrative coherence with consistent subject representation.

Key facts. Cited by 247 papers in the map (data through 7 Oct 2026). Placed in Video generation, one of 14 directions in Diffusion models. Builds on 30 of its 34 references that are in the map. First posted on arXiv 10 Jun 2025.

Builds on

30 of 34 references.

Closest ancestors · 8

Same direction, newest first

  1. 2025Long Context Tuning for Video Generation13 Mar
  2. 2025Training-free and Adaptive Sparse Attention for Efficient Long Video Generation28 Feb
  3. 2025Improving Video Generation with Human Feedback23 Jan
  4. 2025Diffusion Adversarial Post-Training for One-Step Video Generation14 Jan
  5. 2024OnlineVPO: Align Video Diffusion Model with Online Video-Centric Preference Optimization19 Dec
  6. 2024Prompt-A-Video: Prompt Your Video Diffusion Model via Preference-Aligned LLM19 Dec
  7. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer12 Aug
  8. 2023Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation9 Oct

Other references · 22

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  4. 2022Scalable Diffusion Models with Transformerscited by 5,931
  5. 2024Qwen2.5 Technical Reportcited by 4,713
  6. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  7. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  8. 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,536
  9. 2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,597
  10. 2023PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallelcited by 641
  11. 2025Flow-GRPO: Training Flow Matching Models via Online RLcited by 605
  12. 2017Ray: A Distributed Framework for Emerging AI Applicationscited by 516
10 more
  1. 2025DanceGRPO: Unleashing GRPO on Visual Generationcited by 388
  2. 2023Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioningcited by 254
  3. 2023DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Modelscited by 239
  4. 2024Deep Compression Autoencoder for Efficient High-Resolution Diffusion Modelscited by 209
  5. 2024Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesiscited by 153
  6. 2025Seedream 3.0 Technical Reportcited by 146
  7. 2025Seaweed-7B: Cost-Effective Training of Video Generation Foundation Modelcited by 81
  8. 2025Tarsier2: Advancing Large Vision-Language Models from Detailed Video Description to Comprehensive Video Understandingcited by 80
  9. 2025Seedream 2.0: A Native Chinese-English Bilingual Image Generation Foundation Modelcited by 59
  10. 2025RayFlow: Instance-Aware Diffusion Acceleration via Adaptive Flow Trajectoriescited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 88; 2026: 159.

247 papers.

Sort:

By area:

  1. 2025World Simulation with Video Foundation Models for Physical AIcited by 183
  2. 2025WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modelingcited by 152
  3. 2026Advancing Open-source World Modelscited by 144
  4. 2026Seedance 2.0: Advancing Video Generation for World Complexitycited by 142
  5. 2026Cosmos 3: Omnimodal World Models for Physical AIcited by 137
  6. 2026StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developingcited by 103
  7. 2025SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformercited by 91
  8. 2025RELIC: Interactive Video World Model with Long-Horizon Memorycited by 89
  9. 2025Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistencycited by 81
  10. 2025Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillationcited by 75
  11. 2025Seedance 1.5 pro: A Native Audio-Visual Joint Generation Foundation Modelcited by 73
  12. 2025RewardDance: Reward Scaling in Visual Generationcited by 63
38 more
  1. 2025Kling-Omni Technical Reportcited by 60
  2. 2025UniVerse-1: Unified Audio-Video Generation via Stitching of Expertscited by 58
  3. 2025Waver: Wave Your Way to Lifelike Video Generationcited by 52
  4. 2025OpenVE-3M: A Large-Scale High-Quality Dataset for Instruction-Guided Video Editingcited by 50
  5. 2025End-to-End Training for Autoregressive Video Diffusion via Self-Resamplingcited by 45
  6. 2025Are Video Models Ready as Zero-Shot Reasoners? An Empirical Study with the MME-CoF Benchmarkcited by 41
  7. 2025Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigmcited by 41
  8. 2025Omni-Video: Democratizing Unified Video Understanding and Generationcited by 39
  9. 2025In-Context Learning with Unpaired Clips for Instruction-based Video Editingcited by 34
  10. 2025Unified Camera Positional Encoding for Controlled Video Generationcited by 34
  11. 2025MultiShotMaster: A Controllable Multi-Shot Video Generation Frameworkcited by 33
  12. 2025Spatia: Video Generation with Updatable Spatial Memorycited by 33
  13. 2025Trace Anything: Representing Any Video in 4D via Trajectory Fieldscited by 31
  14. 2025OneStory: Coherent Multi-Shot Video Generation with Adaptive Memorycited by 31
  15. 2025OmniHuman-1.5: Instilling an Active Mind in Avatars via Cognitive Simulationcited by 30
  16. 2026Rethinking Video Generation Model for the Embodied Worldcited by 30
  17. 2026LoL: Longer than Longer, Scaling Video Generation to Hourcited by 29
  18. 2025BusterX++: Towards Unified Cross-Modal AI-Generated Content Detection and Explanation with MLLMcited by 28
  19. 2026Transition Matching Distillation for Fast Video Generationcited by 27
  20. 2025Pack and Force Your Memory: Long-form and Consistent Video Generationcited by 26
  21. 2025What about gravity in video generation? Post-Training Newton's Laws with Verifiable Rewardscited by 23
  22. 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
  23. 2025OneReward: Unified Mask-Guided Image Generation via Multi-Task Human Preference Learningcited by 22
  24. 2025Reasoning via Video: The First Evaluation of Video Models' Reasoning Abilities through Maze-Solving Taskscited by 22
  25. 2025V-ReasonBench: Toward Unified Reasoning Benchmark Suite for Video Generation Modelscited by 22
  26. 2025VABench: A Comprehensive Benchmark for Audio-Video Generationcited by 22
  27. 2025PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generationcited by 22
  28. 2025VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoocited by 20
  29. 2025Can World Simulators Reason? Gen-ViRe: A Generative Visual Reasoning Benchmarkcited by 19
  30. 2026SkyReels-V3 Technique Reportcited by 19
  31. 2026Flow caching for autoregressive video generationcited by 19
  32. 2026DreamID-Omni: Unified Framework for Controllable Human-Centric Audio-Video Generationcited by 19
  33. 2025Follow-Your-Preference: Towards Preference-Aligned Image Inpaintingcited by 18
  34. 2025X-Streamer: Unified Human World Modeling with Audiovisual Interactioncited by 16
  35. 2025MoGA: Mixture-of-Groups Attention for End-to-End Long Video Generationcited by 16
  36. 2025DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencodercited by 15
  37. 2025UniVA: Universal Video Agent towards Open-Source Next-Generation Video Generalistcited by 15
  38. 2025Simulating the Visual World with Artificial Intelligence: A Roadmapcited by 15

50 most cited of 247 All 247 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2022Video Diffusion Models
  2. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
  3. 2024From Slow Bidirectional to Fast Autoregressive Video Diffusion Models
  4. 2024Optical-Flow Guided Prompt Optimization for Coherent Video Generation
  5. 2025GigaVideo-1: Advancing Video Generation via Automatic Feedback with 4 GPU-Hours Fine-Tuning
  6. 2024OSV: One Step is Enough for High-Quality Image to Video Generation
  7. 2022MagicVideo: Efficient Video Generation With Latent Diffusion Models
  8. 2024I4VGen: Image as Free Stepping Stone for Text-to-Video Generation