OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Image & Video AI

Anime2Sketch

Anime2Sketch is a Python image-processing application that uses pretrained computer-vision weights to extract sketch or line-art results from illustrations, anime art, manga and hand-drawn images. Its repository provides a test script for file or directory inputs, adjustable input resizing and a chosen output directory, as well as Docker instructions for mounted image folders.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Anime2Sketch — OpenViST project profile in Image & Video AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Anime2Sketch when you have images to convert into sketch or line-art outputs and can install its Python dependencies, obtain the pretrained weights and provide suitable CPU or NVIDIA GPU resources.

Who it is for

  • Illustrators who want sketch or line-art versions of image files.
  • Users processing anime, manga or illustration collections through a Python script.
  • Developers adding an image-to-sketch preprocessing stage to a local workflow.

Documented uses

  • Extract sketch or line-art outputs from image files or directories.
  • Choose an input resize and output location for image processing.
  • Run image conversion through a Docker workflow with mounted input and output folders.
Before you choose

Requirements & limits

The repository is public and released under the MIT License. The documented workflow requires Python packages and downloaded pretrained weights; no account step is described.

  • The tool supports both a single image file and a directory as the test input.
  • The documented default input resize is 512 × 512, due to memory limits.
  • A separate artifact-free weight option is described for dark or low-contrast images.
  • The repository documents Linux, macOS and Docker, with CPU or NVIDIA GPU plus CUDA and cuDNN listed as compute options.
  • Training instructions are directed to the separate AODA project.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Run the pretrained image-to-sketch script

Process an image file or directory and save sketch outputs to a chosen folder.

Before you start

  • Linux or macOS, Python 3, Pillow and PyTorch; alternatively, Docker.
  • Install dependencies with pip install -r requirements.txt.
  • Download pretrained weights and place them in the repository’s weights/ folder.
  • A CPU or an NVIDIA GPU with CUDA and cuDNN.
  • An input file or directory and an output directory.

Steps

  1. Install the required packages using the repository’s requirements file.

  2. Download the pretrained weights and put them in weights/.

  3. Run the command below, substituting the input and output paths.

    Documented command
    python3 test.py --dataroot /your_input/dir --load_size 512 --output_dir /your_output/dir

Expected outcome

The script processes the specified image file or directory and writes results to the chosen output directory.

Guide limitations

  • The documented default resize is 512 × 512 because of memory limits; the README does not specify other resource requirements or output-quality guarantees.
  • CPU-only Docker use requires removing GPU options and editing the Dockerfile command and Makefile run line.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
14 October 2026
Original website title
Mukosame/Anime2Sketch · Official homepage title · retained in its source language
How we review sourcesSuggest a correction