mlsanityData to 7 Oct 2026

HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives

arXiv 2510.20822 ↗First posted 23 Oct 2025cs.CVcited by 51

Not on the map. Why?

Abstract (arXiv)

State-of-the-art text-to-video models excel at generating isolated clips but fall short of creating the coherent, multi-shot narratives, which are the essence of storytelling. We bridge this "narrative gap" with HoloCine, a model that generates entire scenes holistically to ensure global consistency from the first shot to the last. Our architecture achieves precise directorial control through a Window Cross-Attention mechanism that localizes text prompts to specific shots, while a Sparse Inter-Shot Self-Attention pattern (dense within shots but sparse between them) ensures the efficiency required for minute-scale generation. Beyond setting a new state-of-the-art in narrative coherence, HoloCine develops remarkable emergent abilities: a persistent memory for characters and scenes, and an intuitive grasp of cinematic techniques. Our work marks a pivotal shift from clip synthesis towards automated filmmaking, making end-to-end cinematic creation a tangible future. Our code is available at: https://holo-cine.github.io/.

Key facts. Cited by 51 papers in the map (data through 7 Oct 2026). Builds on 45 of its 56 references that are in the map. First posted on arXiv 23 Oct 2025.

Builds on

45 of 56 references.

References · 45

  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. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  5. 2022Scalable Diffusion Models with Transformerscited by 5,931
  6. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  7. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,611
  8. 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,536
  9. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,526
  10. 2022Video Diffusion Modelscited by 2,280
  11. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformercited by 2,198
  12. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 1,765
33 more
  1. 2023VBench: Comprehensive Benchmark Suite for Video Generative Modelscited by 1,755
  2. 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,725
  3. 2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,597
  4. 2024Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusioncited by 634
  5. 2024VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Modelscited by 568
  6. 2023InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generationcited by 488
  7. 2023DynamiCrafter: Animating Open-domain Images with Video Diffusion Priorscited by 463
  8. 2024From Slow Bidirectional to Fast Autoregressive Video Diffusion Modelscited by 401
  9. 2021StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2cited by 300
  10. 2024StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Textcited by 242
  11. 2024StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generationcited by 240
  12. 2020TransNet V2: An effective deep network architecture for fast shot transition detectioncited by 166
  13. 2024SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Accelerationcited by 158
  14. 2024In-Context LoRA for Diffusion Transformerscited by 155
  15. 2023Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-Denoisingcited by 135
  16. 2024ConsistI2V: Enhancing Visual Consistency for Image-to-Video Generationcited by 130
  17. 2023VideoBooth: Diffusion-based Video Generation with Image Promptscited by 124
  18. 2025Fast Video Generation with Sliding Tile Attentioncited by 123
  19. 2025Long Context Tuning for Video Generationcited by 110
  20. 2025One-Minute Video Generation with Test-Time Trainingcited by 100
  21. 2025Mixture of Contexts for Long Video Generationcited by 90
  22. 2024MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequencecited by 85
  23. 2025ConceptMaster: Multi-Concept Video Customization on Diffusion Transformer Models Without Test-Time Tuningcited by 67
  24. 2025Radial Attention: O(nlog n) Sparse Attention with Energy Decay for Long Video Generationcited by 64
  25. 2024VideoStudio: Generating Consistent-Content and Multi-Scene Videoscited by 62
  26. 2025Captain Cinema: Towards Short Movie Generationcited by 48
  27. 2023AutoStory: Generating Diverse Storytelling Images with Minimal Human Effortcited by 38
  28. 2025ShotAdapter: Text-to-Multi-Shot Video Generation with Diffusion Modelscited by 37
  29. 2024DreamFactory: Pioneering Multi-Scene Long Video Generation with a Multi-Agent Frameworkcited by 31
  30. 2025FilMaster: Bridging Cinematic Principles and Generative AI for Automated Film Generationcited by 28
  31. 2025CineTrans: Learning to Generate Videos with Cinematic Transitions via Masked Diffusion Modelscited by 26
  32. 2024TALC: Time-Aligned Captions for Multi-Scene Text-to-Video Generationcited by 25
  33. 2025LongAnimation: Long Animation Generation with Dynamic Global-Local Memorycited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 46.

51 papers.

Sort:

By area:

  1. 2026Advancing Open-source World Modelscited by 144
  2. 2025StoryMem: Multi-shot Long Video Storytelling with Memorycited by 35
  3. 2025MultiShotMaster: A Controllable Multi-Shot Video Generation Frameworkcited by 33
  4. 2025OneStory: Coherent Multi-Shot Video Generation with Adaptive Memorycited by 31
  5. 2026VideoMemory: Toward Consistent Video Generation via Memory Integrationcited by 22
  6. 2026ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytellingcited by 22
  7. 2026Mode Seeking meets Mean Seeking for Fast Long Video Generationcited by 12
  8. 2026ViMax: Agentic Video Generationcited by 11
  9. 2026MSVBench: Towards Human-Level Evaluation of Multi-Shot Video Generationcited by 10
  10. 2026MuSS: A Large-Scale Dataset and Cinematic Narrative Benchmark for Multi-Shot Subject-to-Video Generationcited by 8
  11. 2026CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video Narrativescited by 8
  12. 2026ShotVerse: Advancing Cinematic Camera Control for Text-Driven Multi-Shot Video Creationcited by 7
38 more
  1. 2025SemanticGen: Video Generation in Semantic Spacecited by 6
  2. 2026Script-a-Video: Deep Structured Audio-visual Captions via Factorized Streams and Relational Groundingcited by 6
  3. 2026Efficient Video Diffusion Models: Advancements and Challengescited by 6
  4. 2026EntityBench: Towards Entity-Consistent Long-Range Multi-Shot Video Generationcited by 6
  5. 2026One Sentence, One Drama: Personalized Short-Form Drama Generation via Multi-Agent Systemscited by 6
  6. 2026InfinityStory: Unlimited Video Generation with World Consistency and Character-Aware Shot Transitionscited by 5
  7. 2026EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generationcited by 5
  8. 2026CineDance: Towards Next-Generation Multi-Shot Long-Form Cinematic Audio-Video Generationcited by 5
  9. 2025CoAgent: Collaborative Planning and Consistency Agent for Coherent Video Generationcited by 4
  10. 2026DirectorBench: Diagnosing Long-Form Video Generation with Personalized Multi-Agent Evaluationcited by 4
  11. 2026Echo-Memory: A Controlled Study of Memory in Action World Modelscited by 4
  12. 2026Memento: Reconstruct to Remember for Consistent Long Video Generationcited by 4
  13. 2026GroundShot: Visually Consistent Multi-Shot Long Video Generation via Entity-Grounded Shot Schedulingcited by 4
  14. 2026UnityShots: Memory-Driven Multi-Shot Audio-Video Generation with Boundary-Aware Gatingcited by 4
  15. 2026CineWeaver: Training-Free Reference-Controllable Multi-Shot Long Video Generation for Cinematic Storytellingcited by 4
  16. 2026CANVAS: Continuity-Aware Narratives via Visual Agentic Storyboardingcited by 3
  17. 2026Narrative Weaver: Towards Controllable Long-Range Visual Consistency with Multi-Modal Conditioningcited by 2
  18. 2026SmartDirector: Keyframe-Conditioned Cinematic Video Generation with Narrative Pacing Controlcited by 2
  19. 2026EvoState: Closed-Loop Visual State Management for Long-Form Video Generationcited by 2
  20. 2026FilmWorld: Agentic Novel-to-Film Generation through Dynamic Cinematic World Modelingcited by 2
  21. 2026RECAP-Forcing: Retaining Content Appearances for Long Video Generationcited by 2
  22. 2026DreamShot: Personalized Storyboard Synthesis with Video Diffusion Priorcited by 1
  23. 2026SlotMem: Character-Addressable Internal Memory for Narrative Long Video Generationcited by 1
  24. 2026Vorch-Director: Interactive World Story Model via Noise-Aware Error Rectificationcited by 1
  25. 2026LogiShot: Logically Coherent Cross-Shot Video Generationcited by 1
  26. 2026MSEditor: Toward Consistent Multi-Shot Video Editingcited by 1
  27. 2026SEAM: Shot Entity-Attribute Memory for Consistent Short-Drama Generation at Scalecited by 1
  28. 2026SubjectAnchor: Subject-Aware Memory-to-Video for Multi-Shot Storytellingcited by 1
  29. 2026DCDM: Divide-and-Conquer Diffusion Models for Consistency-Preserving Video Generationcited by 0
  30. 2026StreamWise: Serving Multi-Modal Generation in Real-Time at Scalecited by 0
  31. 2026ShotPlan: Cinematic Video Generation with Learnable Planning Tokencited by 0
  32. 2026ContextMaster: Interactive Multi-Shot Video Creation via Fixed-Budget Sparse Context Routingcited by 0
  33. 2026PersonaShot: Benchmarking Person-Centric Narrative Continuity in Multi-Shot Video Generationcited by 0
  34. 2026DramaChain Bench: An End-to-End Benchmark for Short-Drama Generationcited by 0
  35. 2026The Missing Temporal Link: Temporal Context Routing for Script-Driven Audio-Video Generationcited by 0
  36. 2026Multi-Grid Post-Training for Long-Form Multi-Shot Video Generationcited by 0
  37. 2026DiVA: Enabling Interactive Digital Life Simulation via Video Modelscited by 0
  38. 2026MVAgent: Multi-Agent Video Generation via Consistent Condition Construction and Shot-Level Policy Optimizationcited by 0

50 most cited of 51 All 51 (JSON)