chaiNNer-org/chaiNNer
ChaiNNer
chaiNNer is a GPU-accelerated AI image upscaling application that uses a visual node-based interface for constructing image processing pipelines. At its core, it provides a node-based visual programming environment where users connect processing nodes in a directed acyclic graph, with a graph execution scheduler that traverses the pipeline in topological order. The application includes an iterator-based batch processing system that automatically applies the same pipeline to multiple files, and a model format conversion pipeline that transforms neural network models between PyTorch, ONNX, and NCNN formats.
The application distinguishes itself through its plugin-based node architecture, where each image operation is encapsulated as a self-contained node with typed inputs and outputs that can be dynamically loaded. It supports cross-framework model conversion for use on different GPU hardware, and includes a neural network dependency manager that installs and configures runtimes without requiring system-level Python modifications. Custom AI model integration allows users to parse and incorporate various upscaling network architectures directly into the processing pipeline.
Beyond its core upscaling capabilities, chaiNNer provides image property adjustment, background removal using pre-trained neural network models, and the ability to chain multiple image operations in a flexible sequence. The visual node pipeline editor enables users to build reusable processing workflows by dragging handles between nodes, with pipeline execution showing animated progress and providing pause or stop controls.
Features
- Visual Node Editors - Provides a visual node-based interface for constructing image processing pipelines by connecting nodes in a directed acyclic graph.
- Batch Image Processing - Applies the same sequence of image operations to multiple files at once using iterator nodes in a visual pipeline.
- Pipeline-Based Batch Upscalers - Processes multiple images through a visual pipeline by connecting iterator nodes to apply the same upscaling operations to each file.
- GPU-Accelerated Inference - Provides GPU-accelerated neural network inference for image upscaling through hardware-accelerated compute backends.
- File-Based Pipeline Iterators - Implements iterator-based batch processing that automatically applies the same pipeline to multiple files.
- Batch Image Processors - Processes multiple files through a visual pipeline using iterator nodes for uniform operations.
- AI Upscaling - Applies neural network models to increase image resolution with GPU acceleration and batch processing support.
- Image Processing Pipelines - Chains multiple image operations including AI upscaling and adjustments in a visual pipeline.
- Node-Based Image Processing - Builds custom image processing workflows by connecting nodes in a visual graph, enabling chaining of operations like upscaling and filtering.
- Topological Order Executors - Ships a graph execution scheduler that traverses the node pipeline in topological order for image processing.
- Visual Pipeline Builders - Ships a graphical interface for constructing reusable image processing pipelines by connecting nodes.
- Cross-Framework Model Conversion - Transforms models between PyTorch, ONNX, and NCNN formats for use on different GPU hardware.
- Custom Model Integrations - Parses and integrates various upscaling network architectures directly into the visual processing pipeline.
- Model Format Converters - Transforms PyTorch and ONNX models into NCNN format for cross-platform GPU inference.
- Model Format Converters - Converts neural network models between PyTorch, ONNX, and NCNN formats using a chain of transformation nodes.
- PyTorch-ONNX-NCNN Converters - Transforms neural network models between PyTorch, ONNX, and NCNN formats for cross-platform GPU inference.
- Visual Pipeline Executions - Executes connected node pipelines with animated progress and pause/stop controls.
- Plugin-Based Architectures - Encapsulates each image operation as a self-contained plugin node with typed inputs and outputs that can be dynamically loaded.
- Image Property Adjusters - Provides nodes for adjusting brightness, contrast, and color balance within a visual pipeline.
- Herramientas de desarrollo - Node-based GUI for image processing and AI upscaling.
