# chaiNNer-org/chaiNNer

A node-based image processing GUI aimed at making chaining image processing tasks easy and customizable. Born as an AI upscaling application, chaiNNer has grown into an extremely flexible and powerful programmatic image processing application.

Repository: https://github.com/chaiNNer-org/chaiNNer
Canonical: https://ross.abutalabs.com/products/chainner
Homepage: https://chaiNNer.app
Language: Python
License: GPL-3.0
License Family: copyleft
Last push: 2026-07-31T20:27:38+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 95, release rhythm 53, longevity 100
- inputs: {"age_days": 1821, "days_push": 33, "days_rel": 315, "gap_med": 3, "n_releases_24m": 2}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5994, forks 369 (observed 2026-08-28T04:09:34.067872+00:00)

## What it is
chaiNNer is a free, open-source, node-based desktop application for building image processing pipelines by connecting nodes on a canvas. Originally built for AI upscaling with super-resolution models, it has grown into a flexible programmatic image editor supporting PyTorch, NCNN, ONNX, and TensorRT backends.

## Use cases
- upscale images with AI super-resolution models
- build custom image processing pipelines without coding
- generate normal maps from game textures
- batch process images with chained operations
- upscale pixel art with HQ2x or Eagle algorithms
- restore faces in upscaled images
- convert and save DDS textures with BC compression
- split and merge spritesheets for processing

## When to choose
- you want to run community-trained upscaling models like ESRGAN or SPAN without writing code
- you need a visual, customizable image processing workflow with full pipeline control
- you work with game textures, normal maps, or spritesheets and need PBR-aware tooling
- you want a cross-platform free alternative to scripted image processing

## When to avoid
- you only need simple one-off edits like cropping or filters in a standard image editor
- you prefer writing scripts over visual node graphs
- you need a headless or server-side batch solution rather than a desktop GUI
- you require non-image media processing like audio or text

## Facets
- artifact type: application
- maturity: active
- function: image-processing, gui, machine-learning, workflow-automation
- domain: image-processing, machine-learning, graphics, cross-platform
- platform: windows, python
- tags: node-based-editor, ai-upscaling, super-resolution, visual-programming, image-pipeline, esrgan, pytorch, onnx, ncnn, texture-processing, pixel-art, macos, linux, desktop

## Member repositories
- chaiNNer-org/chaiNNer (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:34.067872+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:49:50.821229+00:00, confidence not recorded.
  - readme: https://github.com/chaiNNer-org/chaiNNer (fetched 2026-08-28T04:09:34.067872+00:00, sha 41b616805a7e)
  - homepage: https://chaiNNer.app (fetched 2026-08-29T08:45:49.916357+00:00, sha 45428b539edc)
- Data as of 2026-08-30T08:39:29.467469+00:00.