leeyeel/Sketch2Motion

convert photo or sketch to motion video

What it solves

It converts static images—such as doodles, photos, or sketches—into smooth, animated drawing videos. This allows users to transform a still image into a visual sequence that looks like it is being drawn in real-time.

How it works

The project uses a pipeline that converts an input image into an SVG vector graphic using Potrace. It then utilizes the Manim animation engine to render the SVG into an MP4 video. For color images, the system quantizes the image into a set number of colors, traces each color layer separately, and renders them accordingly.

Who it’s for

Content creators and designers who want to create drawing animations from existing images without manually animating them.

Highlights

  • Image-to-Video Pipeline: Automates the process from image to sketch to SVG to animated MP4.
  • Customizable Animation: Users can adjust the duration, scale, subpath delay, and drawing styles (linear, smooth, there_and_back, wiggle).
  • Color Support: Optional color-preserving SVG and video generation via a color quantization pipeline.
  • User-Friendly Interface: Includes a Gradio-based web interface for easy configuration and generation.

Related

  • Project
    luxonis/depthai-ros

    A ROS integration for Luxonis OAK cameras, enabling the use of hardware-accelerated AI and depth perception in robotic systems.

  • Project
    beixiaocai/rebucca

    A multi-channel video analysis platform that combines YOLO detection and LLM verification to provide structured alarms for security and monitoring.

  • Project
    lartpang/PyIRSTDMetrics

    A lightweight Python library for analyzing the performance of infrared small target detection models using pixel-level, target-level, and hybrid metrics.

  • Project
    Artoriuz/ArtCNN

    A collection of Single Image Super-Resolution models optimized for upscaling and cleaning anime content, offering both real-time and high-quality non-real-time options.