DreamLoop: Controllable Cinemagraph Generation from a Single Photograph

TL;DR

DreamLoop is a novel framework that generates high-quality, controllable cinemagraphs from a single photograph without requiring specialized training data, enabling flexible and intuitive scene animations.

Contribution

It introduces a new method that adapts a general video diffusion model for cinemagraph generation with control over motion and seamless looping, without needing cinemagraph-specific training data.

Findings

Produces high-quality, complex cinemagraphs.

Outperforms existing approaches in quality and control.

Enables flexible, user-guided scene animations.

Abstract

Cinemagraphs, which combine static photographs with selective, looping motion, offer unique artistic appeal. Generating them from a single photograph in a controllable manner is particularly challenging. Existing image-animation techniques are restricted to simple, low-frequency motions and operate only in narrow domains with repetitive textures like water and smoke. In contrast, large-scale video diffusion models are not tailored for cinemagraph constraints and lack the specialized data required to generate seamless, controlled loops. We present DreamLoop, a controllable video synthesis framework dedicated to generating cinemagraphs from a single photo without requiring any cinemagraph training data. Our key idea is to adapt a general video diffusion model by training it on two objectives: temporal bridging and motion conditioning. This strategy enables flexible cinemagraph generation. During inference, by using the input image as both the first- and last- frame condition, we enforce a seamless loop. By conditioning on static tracks, we maintain a static background. Finally, by providing a user-specified motion path for a target object, our method provides intuitive control over the animation's trajectory and timing. To our knowledge, DreamLoop is the first method to enable cinemagraph generation for general scenes with flexible and intuitive controls. We demonstrate that our method produces high-quality, complex cinemagraphs that align with user intent, outperforming existing approaches.