mlsanityData to 14 Oct 2026

Captain Cinema: Towards Short Movie Generation

arXiv 2507.18634 ↗First posted 24 Jul 2025cs.CVcited by 48

Not on the map. Why?

Abstract (arXiv)

We present Captain Cinema, a generation framework for short movie generation. Given a detailed textual description of a movie storyline, our approach firstly generates a sequence of keyframes that outline the entire narrative, which ensures long-range coherence in both the storyline and visual appearance (e.g., scenes and characters). We refer to this step as top-down keyframe planning. These keyframes then serve as conditioning signals for a video synthesis model, which supports long context learning, to produce the spatio-temporal dynamics between them. This step is referred to as bottom-up video synthesis. To support stable and efficient generation of multi-scene long narrative cinematic works, we introduce an interleaved training strategy for Multimodal Diffusion Transformers (MM-DiT), specifically adapted for long-context video data. Our model is trained on a specially curated cinematic dataset consisting of interleaved data pairs. Our experiments demonstrate that Captain Cinema performs favorably in the automated creation of visually coherent and narrative consistent short movies in high quality and efficiency. Project page: https://thecinema.ai

Key facts. Cited by 48 papers in the map (data through 14 Oct 2026). Builds on 49 of its 58 references that are in the map. First posted on arXiv 24 Jul 2025.

Builds on

49 of 58 references.

References · 49

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  4. 2023Visual Instruction Tuningcited by 7,869
  5. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,137
  6. 2022Scalable Diffusion Models with Transformerscited by 6,054
  7. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,386
  8. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
  9. 2022Video Diffusion Modelscited by 2,305
  10. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformercited by 2,261
  11. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 1,778
  12. 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,742
37 more
  1. 2022CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformerscited by 985
  2. 2023EVA-CLIP: Improved Training Techniques for CLIP at Scalecited by 798
  3. 2024Emu3: Next-Token Prediction is All You Needcited by 781
  4. 2024Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusioncited by 681
  5. 2023ModelScope Text-to-Video Technical Reportcited by 658
  6. 2023DataComp: In search of the next generation of multimodal datasetscited by 644
  7. 2024LTX-Video: Realtime Video Latent Diffusioncited by 581
  8. 2024VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Modelscited by 579
  9. 2023VideoCrafter1: Open Diffusion Models for High-Quality Video Generationcited by 535
  10. 2023VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Taskscited by 501
  11. 2023VideoPoet: A Large Language Model for Zero-Shot Video Generationcited by 492
  12. 2022MagicVideo: Efficient Video Generation With Latent Diffusion Modelscited by 465
  13. 2023Generative Multimodal Models are In-Context Learnerscited by 446
  14. 2024SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generationcited by 331
  15. 2023MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Modelcited by 330
  16. 2023Pix2Video: Video Editing using Image Diffusioncited by 320
  17. 2022Scaling Language-Image Pre-training via Maskingcited by 317
  18. 2025VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulnesscited by 315
  19. 2023DreamLLM: Synergistic Multimodal Comprehension and Creationcited by 297
  20. 2024StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generationcited by 247
  21. 2024In-Context LoRA for Diffusion Transformerscited by 158
  22. 2025Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion Modelscited by 143
  23. 2023VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planningcited by 141
  24. 2025Long-Context Autoregressive Video Modeling with Next-Frame Predictioncited by 123
  25. 2025Long Context Tuning for Video Generationcited by 113
  26. 2023Animate-A-Story: Storytelling with Retrieval-Augmented Video Generationcited by 90
  27. 2024MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequencecited by 89
  28. 2023CCEdit: Creative and Controllable Video Editing via Diffusion Modelscited by 82
  29. 2025Seaweed-7B: Cost-Effective Training of Video Generation Foundation Modelcited by 82
  30. 2024MM-Interleaved: Interleaved Image-Text Generative Modeling via Multi-modal Feature Synchronizercited by 80
  31. 2024SEED-Story: Multimodal Long Story Generation with Large Language Modelcited by 73
  32. 2024Vlogger: Make Your Dream A Vlogcited by 70
  33. 2024VideoTetris: Towards Compositional Text-to-Video Generationcited by 51
  34. 2023LivePhoto: Real Image Animation with Text-guided Motion Controlcited by 44
  35. 2025VideoAuteur: Towards Long Narrative Video Generationcited by 18
  36. 2023Style-A-Video: Agile Diffusion for Arbitrary Text-based Video Style Transfercited by 14
  37. 2025HiTVideo: Hierarchical Tokenizers for Enhancing Text-to-Video Generation with Autoregressive Large Language Modelscited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 18; 2026: 30.

48 papers.

Sort:

By area:

  1. 2025Mixture of Contexts for Long Video Generationcited by 95
  2. 2026Helios: Real Real-Time Long Video Generation Modelcited by 65
  3. 2025HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narrativescited by 54
  4. 2025MemFlow: Flowing Adaptive Memory for Consistent and Efficient Long Video Narrativescited by 45
  5. 2025StoryMem: Multi-shot Long Video Storytelling with Memorycited by 40
  6. 2025MultiShotMaster: A Controllable Multi-Shot Video Generation Frameworkcited by 36
  7. 2025OneStory: Coherent Multi-Shot Video Generation with Adaptive Memorycited by 35
  8. 2025MoGA: Mixture-of-Groups Attention for End-to-End Long Video Generationcited by 18
  9. 2026Mode Seeking meets Mean Seeking for Fast Long Video Generationcited by 12
  10. 2025FilmWeaver: Weaving Consistent Multi-Shot Videos with Cache-Guided Autoregressive Diffusioncited by 10
  11. 2026CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video Narrativescited by 10
  12. 2025BIFE: Better Interaction, Fewer Errors for Minute-Long Video Generationcited by 9
36 more
  1. 2026Script-a-Video: Deep Structured Audio-visual Captions via Factorized Streams and Relational Groundingcited by 8
  2. 2025LAMIC: Layout-Aware Multi-Image Composition via Scalability of Multimodal Diffusion Transformercited by 7
  3. 2026CineScene: Implicit 3D as Effective Scene Representation for Cinematic Video Generationcited by 7
  4. 2026ShotVerse: Advancing Cinematic Camera Control for Text-Driven Multi-Shot Video Creationcited by 7
  5. 2026EntityBench: Towards Entity-Consistent Long-Range Multi-Shot Video Generationcited by 6
  6. 2026CineDance: Towards Next-Generation Multi-Shot Long-Form Cinematic Audio-Video Generationcited by 6
  7. 2026UnityShots: Memory-Driven Multi-Shot Audio-Video Generation with Boundary-Aware Gatingcited by 6
  8. 2025PhyDetEx: Detecting and Explaining the Physical Plausibility of T2V Modelscited by 5
  9. 2026Memento: Reconstruct to Remember for Consistent Long Video Generationcited by 5
  10. 2026GroundShot: Visually Consistent Multi-Shot Long Video Generation via Entity-Grounded Shot Schedulingcited by 5
  11. 2025TempoMaster: Efficient Long Video Generation via Next-Frame-Rate Predictioncited by 4
  12. 2025View-Consistent Diffusion Representations for 3D-Consistent Video Generationcited by 4
  13. 2025AutoRefiner: Improving Autoregressive Video Diffusion Models via Reflective Refinement Over the Stochastic Sampling Pathcited by 4
  14. 2026Camera Artist: A Multi-Agent Framework for Cinematic Language Storytelling Video Generationcited by 4
  15. 2026HorizonDrive: Self-Corrective Autoregressive World Model for Long-horizon Driving Simulationcited by 4
  16. 2025Generative Photographic Control for Scene-Consistent Video Cinematic Editingcited by 3
  17. 2025Video4Spatial: Towards Visuospatial Intelligence with Context-Guided Video Generationcited by 3
  18. 2026EM-Vid: Training-Free Entity-Centric Memory for Efficient and Consistent Multi-Shot Video Generationcited by 3
  19. 2025VideoVerse: Does Your T2V Generator Have World Model Capability to Synthesize Videos?cited by 2
  20. 2025Bridging Your Imagination with Audio-Video Generation via a Unified Directorcited by 2
  21. 2026VisionCreator: A Native Visual-Generation Agentic Model with Understanding, Thinking, Planning and Creationcited by 2
  22. 2026Narrative Weaver: Towards Controllable Long-Range Visual Consistency with Multi-Modal Conditioningcited by 2
  23. 2026COMIC: Agentic Sketch Comedy Generationcited by 2
  24. 2026SmartDirector: Keyframe-Conditioned Cinematic Video Generation with Narrative Pacing Controlcited by 2
  25. 2026EvoState: Closed-Loop Visual State Management for Long-Form Video Generationcited by 2
  26. 2026Towards Error-Free Long Video Generationcited by 2
  27. 2026VisionCreator-R1: A Reflection-Enhanced Native Visual-Generation Agentic Modelcited by 1
  28. 2026DreamShot: Personalized Storyboard Synthesis with Video Diffusion Priorcited by 1
  29. 2026Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videoscited by 1
  30. 2026Agentic Visual Generation: From Generative Models to Agentic Controlcited by 1
  31. 2026SubjectAnchor: Subject-Aware Memory-to-Video for Multi-Shot Storytellingcited by 1
  32. 2026DeltaCam: Differential Intrinsic Camera Modeling for Video Generationcited by 0
  33. 2026LCG: Long-Context Consistent Image Generation with Sparse Relational Attentioncited by 0
  34. 2026ShotPlan: Cinematic Video Generation with Learnable Planning Tokencited by 0
  35. 2026MirrorWorld: Taming Video Diffusion Models for Mirror Reflection Generationcited by 0
  36. 2026Multi-Grid Post-Training for Long-Form Multi-Shot Video Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023MovieFactory: Automatic Movie Creation from Text using Large Generative Models for Language and Images
  2. 2025FilMaster: Bridging Cinematic Principles and Generative AI for Automated Film Generation
  3. 2026CamPilot: A Multi-Agent Cinematic Assistant for Camera-Controlled Movie Generation
  4. 2023SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction
  5. 2025Automated Movie Generation via Multi-Agent CoT Planning
  6. 2025Fine-Tuning Open Video Generators for Cinematic Scene Synthesis: A Small-Data Pipeline with LoRA and Wan2.1 I2V
  7. 2024MovieBench: A Hierarchical Movie Level Dataset for Long Video Generation
  8. 2026CineWeaver: Training-Free Reference-Controllable Multi-Shot Long Video Generation for Cinematic Storytelling