VAST 1.0: A Unified Framework for Controllable and Consistent Video Generation

TL;DR

VAST 1.0 introduces a two-stage framework that transforms text into storyboards and then generates high-quality, temporally consistent videos, enabling precise control over scene dynamics and coherence.

Contribution

The paper presents VAST, a novel unified framework that decouples text understanding from video generation for improved control and quality in video synthesis.

Findings

Outperforms existing methods in visual quality

Achieves higher temporal coherence and scene control

Sets new standards on the VBench benchmark

Abstract

Generating high-quality videos from textual descriptions poses challenges in maintaining temporal coherence and control over subject motion. We propose VAST (Video As Storyboard from Text), a two-stage framework to address these challenges and enable high-quality video generation. In the first stage, StoryForge transforms textual descriptions into detailed storyboards, capturing human poses and object layouts to represent the structural essence of the scene. In the second stage, VisionForge generates videos from these storyboards, producing high-quality videos with smooth motion, temporal consistency, and spatial coherence. By decoupling text understanding from video generation, VAST enables precise control over subject dynamics and scene composition. Experiments on the VBench benchmark demonstrate that VAST outperforms existing methods in both visual quality and semantic expression, setting a new standard for dynamic and coherent video generation.