Saved in:
Bibliographic Details
Main Authors: Cheng, Shihan, Kulkarni, Nilesh, Hyde, David, Smirnov, Dmitriy
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.17844
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Fine-tuning large-scale text-to-video diffusion models to add new generative controls, such as those over physical camera parameters (e.g., shutter speed or aperture), typically requires vast, high-fidelity datasets that are difficult to acquire. In this work, we propose a data-efficient fine-tuning strategy that learns these controls from sparse, low-quality synthetic data. We show that not only does fine-tuning on such simple data enable the desired controls, it actually yields superior results to models fine-tuned on photorealistic "real" data. Beyond demonstrating these results, we provide a framework that justifies this phenomenon both intuitively and quantitatively.