FFP-300K: Scaling First-Frame Propagation for Generalizable Video Editing

TL;DR

This paper introduces FFP-300K, a large-scale dataset and a novel framework for first-frame propagation in video editing, enabling more robust, guidance-free, and high-quality controllable video edits with improved temporal stability.

Contribution

The paper presents a new large-scale dataset FFP-300K and a guidance-free FFP framework with adaptive positional encoding and self-distillation, advancing the robustness and quality of video editing methods.

Findings

Outperforms existing models on EditVerseBench with higher scores.

Achieves better temporal stability and appearance preservation.

Demonstrates effectiveness of the dataset and novel architecture in real-world tasks.

Abstract

First-Frame Propagation (FFP) offers a promising paradigm for controllable video editing, but existing methods are hampered by a reliance on cumbersome run-time guidance. We identify the root cause of this limitation as the inadequacy of current training datasets, which are often too short, low-resolution, and lack the task diversity required to teach robust temporal priors. To address this foundational data gap, we first introduce FFP-300K, a new large-scale dataset comprising 300K high-fidelity video pairs at 720p resolution and 81 frames in length, constructed via a principled two-track pipeline for diverse local and global edits. Building on this dataset, we propose a novel framework designed for true guidance-free FFP that resolves the critical tension between maintaining first-frame appearance and preserving source video motion. Architecturally, we introduce Adaptive Spatio-Temporal RoPE (AST-RoPE), which dynamically remaps positional encodings to disentangle appearance and motion references. At the objective level, we employ a self-distillation strategy where an identity propagation task acts as a powerful regularizer, ensuring long-term temporal stability and preventing semantic drift. Comprehensive experiments on the EditVerseBench benchmark demonstrate that our method significantly outperforming existing academic and commercial models by receiving about 0.2 PickScore and 0.3 VLM score improvement against these competitors.