CineLOG: A Training Free Approach for Cinematic Long Video Generation

TL;DR

CineLOG introduces a new dataset and a multi-stage pipeline for cinematic long video generation, enabling fine-grained control over camera and genre attributes without training from scratch.

Contribution

The paper presents a balanced, high-quality dataset with detailed annotations and a novel multi-stage generation pipeline that improves control and coherence in cinematic video synthesis.

Findings

Outperforms state-of-the-art models in adhering to cinematic instructions

Produces coherent multi-shot sequences with smooth transitions

Maintains high visual quality in generated videos

Abstract

Controllable video synthesis is a central challenge in computer vision, yet current models struggle with fine grained control beyond textual prompts, particularly for cinematic attributes like camera trajectory and genre. Existing datasets often suffer from severe data imbalance, noisy labels, or a significant simulation to real gap. To address this, we introduce CineLOG, a new dataset of 5,000 high quality, balanced, and uncut video clips. Each entry is annotated with a detailed scene description, explicit camera instructions based on a standard cinematic taxonomy, and genre label, ensuring balanced coverage across 17 diverse camera movements and 15 film genres. We also present our novel pipeline designed to create this dataset, which decouples the complex text to video (T2V) generation task into four easier stages with more mature technology. To enable coherent, multi shot sequences, we introduce a novel Trajectory Guided Transition Module that generates smooth spatio-temporal interpolation. Extensive human evaluations show that our pipeline significantly outperforms SOTA end to end T2V models in adhering to specific camera and screenplay instructions, while maintaining professional visual quality. All codes and data are available at https://cine-log.pages.dev.