iMontage: Unified, Versatile, Highly Dynamic Many-to-many Image Generation

TL;DR

iMontage is a versatile framework that adapts pre-trained video models for high-quality, dynamic, many-to-many image generation and editing, combining temporal coherence with rich content diversity.

Contribution

The paper introduces iMontage, a unified approach that repurposes video models for diverse image generation tasks without compromising their original motion priors.

Findings

Achieves high-quality, temporally coherent image sets.

Supports a wide range of image editing and generation tasks.

Produces scenes with unprecedented dynamic range.

Abstract

Pre-trained video models learn powerful priors for generating high-quality, temporally coherent content. While these models excel at temporal coherence, their dynamics are often constrained by the continuous nature of their training data. We hypothesize that by injecting the rich and unconstrained content diversity from image data into this coherent temporal framework, we can generate image sets that feature both natural transitions and a far more expansive dynamic range. To this end, we introduce iMontage, a unified framework designed to repurpose a powerful video model into an all-in-one image generator. The framework consumes and produces variable-length image sets, unifying a wide array of image generation and editing tasks. To achieve this, we propose an elegant and minimally invasive adaptation strategy, complemented by a tailored data curation process and training paradigm. This approach allows the model to acquire broad image manipulation capabilities without corrupting its invaluable original motion priors. iMontage excels across several mainstream many-in-many-out tasks, not only maintaining strong cross-image contextual consistency but also generating scenes with extraordinary dynamics that surpass conventional scopes. Find our homepage at: https://kr1sjfu.github.io/iMontage-web/.