DreaMontage: Arbitrary Frame-Guided One-Shot Video Generation

TL;DR

DreaMontage is a novel framework for one-shot video generation that produces seamless, expressive, and long-duration videos guided by arbitrary frames, overcoming previous limitations in visual coherence and cinematic quality.

Contribution

It introduces a comprehensive approach combining a lightweight conditioning mechanism, high-quality dataset, and a segment-wise autoregressive strategy for improved one-shot video synthesis.

Findings

Achieves visually striking, coherent one-shot videos.

Enhances success rate and usability with Tailored DPO scheme.

Enables long-duration video generation with memory-efficient inference.

Abstract

The "one-shot" technique represents a distinct and sophisticated aesthetic in filmmaking. However, its practical realization is often hindered by prohibitive costs and complex real-world constraints. Although emerging video generation models offer a virtual alternative, existing approaches typically rely on naive clip concatenation, which frequently fails to maintain visual smoothness and temporal coherence. In this paper, we introduce DreaMontage, a comprehensive framework designed for arbitrary frame-guided generation, capable of synthesizing seamless, expressive, and long-duration one-shot videos from diverse user-provided inputs. To achieve this, we address the challenge through three primary dimensions. (i) We integrate a lightweight intermediate-conditioning mechanism into the DiT architecture. By employing an Adaptive Tuning strategy that effectively leverages base training data, we unlock robust arbitrary-frame control capabilities. (ii) To enhance visual fidelity and cinematic expressiveness, we curate a high-quality dataset and implement a Visual Expression SFT stage. In addressing critical issues such as subject motion rationality and transition smoothness, we apply a Tailored DPO scheme, which significantly improves the success rate and usability of the generated content. (iii) To facilitate the production of extended sequences, we design a Segment-wise Auto-Regressive (SAR) inference strategy that operates in a memory-efficient manner. Extensive experiments demonstrate that our approach achieves visually striking and seamlessly coherent one-shot effects while maintaining computational efficiency, empowering users to transform fragmented visual materials into vivid, cohesive one-shot cinematic experiences.