Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/ollm/opencomic-ai-models/llms.txt

Use this file to discover all available pages before exploring further.

opencomic-ai-models packages the AI model weights used by OpenComic AI and exposes a single resolved filesystem path so your application can locate models at runtime — no manual file management required. The package ships models for three processing pipelines: image upscaling, JPEG artifact removal, and halftone descreening.

Installation

Add the package to your project via npm and learn about the export formats available.

Quickstart

Get up and running in minutes with a complete, working code example.

Upscale Models

Explore all bundled upscaling models — RealESRGAN, RealCUGAN, Waifu2x, and more.

Artifact Removal

Remove JPEG compression artifacts with custom-trained and community models.

Descreen Models

Eliminate halftone patterns from scanned comic pages and printed media.

Integration Guide

Connect model paths to upscayl, RealCUGAN, and Waifu2x binaries in your pipeline.

What’s included

1

Install the package

Install opencomic-ai-models from GitHub via npm. The package ships model weights directly in the models/ directory.
2

Import and resolve the path

Import the default export and read the path property. This gives you an absolute filesystem path to the bundled models directory.
3

Pass the path to your upscaler

Provide the resolved models path to your upscaler binary (upscayl, realcugan-ncnn-vulkan, or waifu2x-ncnn-vulkan) as the model directory argument.
4

Choose a model and process images

Pick a model ID for your use case — upscaling, artifact removal, or descreening — and run your image processing pipeline.
Model weights are licensed under CC BY 4.0, separate from the MIT-licensed source code. See the Licenses guide for attribution requirements.

Build docs developers (and LLMs) love