# DramaDirector: Geometry-Guided Short Drama Generation

arXiv: https://arxiv.org/abs/2606.24107 · HTML: https://mlsanity.com/paper/2606.24107/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 31 references that are in the map.
- First posted on arXiv 23 Jun 2026.

## Builds on (most cited first, 20 of 20)

- [Effective Whole-body Pose Estimation with Two-stages Distillation](https://mlsanity.com/paper/2307.15880/) (2023)
- [Video Diffusion Alignment via Reward Gradients](https://mlsanity.com/paper/2407.08737/) (2024)
- [Automated Movie Generation via Multi-Agent CoT Planning](https://mlsanity.com/paper/2503.07314/) (2025)
- [Of Human Criteria and Automatic Metrics: A Benchmark of the Evaluation of Story Generation](https://mlsanity.com/paper/2208.11646/) (2022)
- [OneStory: Coherent Multi-Shot Video Generation with Adaptive Memory](https://mlsanity.com/paper/2512.07802/) (2025)
- [ComfyBench: Benchmarking LLM-based Agents in ComfyUI for Autonomously Designing Collaborative AI Systems](https://mlsanity.com/paper/2409.01392/) (2024)
- [Gen-Searcher: Reinforcing Agentic Search for Image Generation](https://mlsanity.com/paper/2603.28767/) (2026)
- [FilMaster: Bridging Cinematic Principles and Generative AI for Automated Film Generation](https://mlsanity.com/paper/2506.18899/) (2025)
- [STAGE: Storyboard-Anchored Generation for Cinematic Multi-shot Narrative](https://mlsanity.com/paper/2512.12372/) (2025)
- [VideoAuteur: Towards Long Narrative Video Generation](https://mlsanity.com/paper/2501.06173/) (2025)
- [UniVA: Universal Video Agent towards Open-Source Next-Generation Video Generalist](https://mlsanity.com/paper/2511.08521/) (2025)
- [Multi-RAG: A Multimodal Retrieval-Augmented Generation System for Adaptive Video Understanding](https://mlsanity.com/paper/2505.23990/) (2025)
- [Patho-AgenticRAG: Towards Multimodal Agentic Retrieval-Augmented Generation for Pathology VLMs via Reinforcement Learning](https://mlsanity.com/paper/2508.02258/) (2025)
- [DreamRunner: Fine-Grained Compositional Story-to-Video Generation with Retrieval-Augmented Motion Adaptation](https://mlsanity.com/paper/2411.16657/) (2024)
- [ShoulderShot: Generating Over-the-Shoulder Dialogue Videos](https://mlsanity.com/paper/2508.07597/) (2025)
- [VideoStir: Understanding Long Videos via Spatio-Temporally Structured and Intent-Aware RAG](https://mlsanity.com/paper/2604.05418/) (2026)
- [SkyScript-100M: 1,000,000,000 Pairs of Scripts and Shooting Scripts for Short Drama](https://mlsanity.com/paper/2408.09333/) (2024)
- [mRAG: Elucidating the Design Space of Multi-modal Retrieval-Augmented Generation](https://mlsanity.com/paper/2505.24073/) (2025)
- [Beyond Direct Generation: A Decomposed Approach to Well-Crafted Screenwriting with LLMs](https://mlsanity.com/paper/2510.23163/) (2025)
- [VisionCreator-R1: A Reflection-Enhanced Native Visual-Generation Agentic Model](https://mlsanity.com/paper/2603.08812/) (2026)

## Built on by (most cited first, 2 of 2)

- [SAGE: Self-Evolving Storyboard Skills via Attribution-Guided Rule Evolution](https://mlsanity.com/paper/2608.17468/) (2026)
- [DramaChain Bench: An End-to-End Benchmark for Short-Drama Generation](https://mlsanity.com/paper/2609.00646/) (2026)

## Abstract (arXiv)

Short dramas, with their rapid shot rhythms, dialogue-driven focus shifts, and demanding cinematographic grounding, pose challenges that prompt-level or text-only video generation pipelines struggle to meet. We study plot-to-short-drama generation, where a global plot and local context are transformed into visually grounded multi-shot videos. We propose DramaDirector, a geometry-grounded framework that lets the planner borrow cinematographic geometry from a gallery of real short-drama shots indexed by depth and pose. DramaDirector decouples each shot into static visual and dynamic narrative conditions, trains the planner with schema-constrained SFT and GRPO under a learned text-visual alignment reward, and retrieves depth-pose references to guide first-frame generation and image-to-video synthesis. We also introduce DramaBoard, a benchmark built from 35 live-action dramas, 2.8K episodes, and 81K shots, with structured storyboards and multi-dimensional evaluation protocols. Experiments show that DramaDirector improves over representative multi-agent and video generation baselines on faithfulness, consistency, and controllability. Our code is released at: https://github.com/iLearn-Lab/DramaDirector