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. ChaiNNer gives you a level of customization of your image processing workflow that very few others do. Cross-platform for Windows, macOS, and Linux.
Build processing pipelines by dragging and connecting nodes in an intuitive visual interface. Full control over your workflow with incredibly complex tasks just by connecting a few nodes together.
Full suite of image processing operations including filters, color adjustments, transforms, blending, and effects. Automate any task you can do in traditional image editing software.
Leverage community-trained AI upscaling models with support for PyTorch, NCNN, ONNX, and TensorRT. Use architectures like ESRGAN, SPAN, OmniSR, and many more.
Built-in type system and real-time validation ensure your chains are correct. Catch errors before processing while maintaining flexibility.
Full GPU support for Nvidia (CUDA/TensorRT), AMD (ROCm/NCNN), Apple Silicon (MPS), and Intel (NCNN). CPU fallback for all frameworks.
Process entire folders of images or video frames through your chains, or automate with command-line interface (CLI) support for integration into larger workflows.
No existing Python installation needed. ChaiNNer downloads an isolated integrated Python build and manages all dependencies automatically.
Runs on Windows, macOS, and Linux. Available as an installer or portable zip for all platforms.
chaiNNer's intuitive node-based interface makes complex image processing simple
