chaiNNer-org/chaiNNer

Health v2 · maintenance only

Adoption not part of the score

5994 stars · 369 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

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

application · maturity active

image-processing gui machine-learning workflow-automation image-processing machine-learning graphics cross-platform windows python node-based-editor ai-upscaling super-resolution visual-programming image-pipeline esrgan pytorch onnx ncnn texture-processing pixel-art macos linux desktop

Member repositories

For agents

markdown · JSON · MCP: product_card(name="chaiNNer-org/chaiNNer")