# Lights, Camera, Consistency: A Multistage Pipeline for Character-Stable AI Video Stories

arXiv: https://arxiv.org/abs/2512.16954 · HTML: https://mlsanity.com/paper/2512.16954/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 22 references that are in the map.
- First posted on arXiv 17 Dec 2025.

## Builds on (most cited first, 10 of 10)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation](https://mlsanity.com/paper/2212.11565/) (2022)
- [CoTracker: It is Better to Track Together](https://mlsanity.com/paper/2307.07635/) (2023)
- [Image Segmentation Using Text and Image Prompts](https://mlsanity.com/paper/2112.10003/) (2021)
- [EvalCrafter: Benchmarking and Evaluating Large Video Generation Models](https://mlsanity.com/paper/2310.11440/) (2023)
- [DirecT2V: Large Language Models are Frame-Level Directors for Zero-Shot Text-to-Video Generation](https://mlsanity.com/paper/2305.14330/) (2023)

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

- [SEAM: Shot Entity-Attribute Memory for Consistent Short-Drama Generation at Scale](https://mlsanity.com/paper/2608.22725/) (2026)
- [Memory-Guided B-Roll Generation from User Video Collections](https://mlsanity.com/paper/2610.01884/) (2026)

## Abstract (arXiv)

Generating long, cohesive video stories with consistent characters is a significant challenge for current text-to-video AI. We introduce a method that approaches video generation in a filmmaker-like manner. Instead of creating a video in one step, our proposed pipeline first uses a large language model to generate a detailed production script. This script guides a text-to-image model in creating consistent visuals for each character, which then serve as anchors for a video generation model to synthesize each scene individually. Our baseline comparisons validate the necessity of this multi-stage decomposition; specifically, we observe that removing the visual anchoring mechanism results in a catastrophic drop in character consistency scores (from 7.99 to 0.55), confirming that visual priors are essential for identity preservation. Furthermore, we analyze cultural disparities in current models, revealing distinct biases in subject consistency and dynamic degree between Indian vs Western-themed generations.