VidSketch: Hand-drawn Sketch-Driven Video Generation with Diffusion Control

TL;DR

VidSketch is a novel method that enables high-quality, controllable video animation generation from hand-drawn sketches and text prompts, addressing the limitations of static image-focused approaches.

Contribution

It introduces a Level-Based Sketch Control Strategy and a TempSpatial Attention mechanism to improve control and spatiotemporal consistency in video generation from sketches.

Findings

Achieves high-quality video animations from sketches and text prompts.

Enhances spatiotemporal coherence in generated videos.

Provides adjustable control for users with different drawing skills.

Abstract

With the advancement of generative artificial intelligence, previous studies have achieved the task of generating aesthetic images from hand-drawn sketches, fulfilling the public's needs for drawing. However, these methods are limited to static images and lack the ability to control video animation generation using hand-drawn sketches. To address this gap, we propose VidSketch, the first method capable of generating high-quality video animations directly from any number of hand-drawn sketches and simple text prompts, bridging the divide between ordinary users and professional artists. Specifically, our method introduces a Level-Based Sketch Control Strategy to automatically adjust the guidance strength of sketches during the generation process, accommodating users with varying drawing skills. Furthermore, a TempSpatial Attention mechanism is designed to enhance the spatiotemporal consistency of generated video animations, significantly improving the coherence across frames. You can find more detailed cases on our official website.