Mukosame/Anime2Sketch

A sketch extractor for anime/illustration.

What it solves

Anime2Sketch is designed to extract clean sketches or line art from visual content, specifically targeting illustration, anime art, and manga. It helps artists and creators convert colored images, hand-drawn photos, or messy freehand sketches into simplified, clean line drawings.

How it works

The tool is an application based on a deep learning model described in the paper "Adversarial Open Domain Adaptation for Sketch-to-Photo Synthesis." It uses pretrained weights to process input images, resizing them to a manageable size (default 512x512) to handle memory limits during inference.

Who it’s for

This project is for digital artists, anime enthusiasts, and manga creators who need to automate the process of extracting line art from existing artwork or cleaning up hand-drawn sketches.

Highlights

  • Versatile Input: Works on a wide range of styles including illustrations, anime art, and manga.
  • Multiple Model Versions: Includes a standard version and an "artifact-free" version specifically for dark or low-contrast images.
  • Deployment Options: Supports running via Python scripts, Docker for easier environment setup, or a Gradio web demo.
  • Broad Utility: Capable of turning hand-drawn photos into clean line art and simplifying existing freehand sketches.

Related

  • Project
    storytold/artcraft

    ArtCraft is a desktop IDE that lets artists build 2‑D or 3‑D scenes and then fill them with AI‑generated images, video, audio, meshes and worlds. It offers visual tools for compositing, pose transfer, background removal, and prompt‑driven generation, supporting a catalog of 62 built‑in models plus external providers like Midjourney and Sora. Available for Windows/macOS (Linux from source), it targets creators who want repeatable, controllable AI art workflows.

  • Project
    Comfy-Org/ComfyUI_frontend

    ComfyUI_frontend is the official browser/Electron UI for the ComfyUI AI workflow engine. It offers a node‑graph editor, mask editor, queue/history view, multilingual UI, and a JavaScript extension API for custom panels, commands, keybindings, and toast messages. Releases follow a 2‑week dev → 2‑week freeze cycle, with daily nightlies available via a launch flag.

  • Project
    rupeshs/fastsdcpu

    A high-performance implementation of Stable Diffusion optimized for CPUs, utilizing OpenVINO and Latent Consistency Models to enable near real-time image generation.

  • Project
    SegFault42/HeliosGen

    HeliosGen is an open‑source desktop app (macOS released, Windows/Linux pending) that provides a visual, node‑based canvas for building and running AI image and video generation pipelines. It works locally, sending requests to the kie.ai API (or optionally a Codex CLI) and stores all data on the user’s machine. Features include multi‑model support, reference images, parallel/sequential execution, and a real‑time history. The app is built with Tauri 2 (Rust) and a Next.js/React front‑end, uses SQLite for local persistence, and is MIT‑licensed.