explaingit

chainner-org/chainner

5,787PythonAudience · designerComplexity · 2/5Setup · easy

TLDR

A desktop visual editor where you connect blocks called nodes to build image-processing workflows, no coding needed. Great for AI upscaling, batch editing, and video frame processing.

Mindmap

mindmap
  root((chaiNNer))
    Visual Editor
      Drag and drop nodes
      Connect with wires
      Color coded data types
    AI Upscaling
      PyTorch models
      TensorRT support
      NCNN for AMD GPUs
    Image Processing
      Apply filters
      Batch folder runs
      Save outputs
    Video Support
      Frame by frame
      Load Video node
      Stop and pause controls
    Easy Setup
      No Python needed
      Built in dependency manager
      Windows Mac Linux
    GPU Support
      Nvidia acceleration
      Apple Silicon
      CPU fallback
Click or tap to explore — scroll the page freely

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

Things people build with this

USE CASE 1

Upscale blurry or low-resolution images using AI models without writing any code.

USE CASE 2

Batch process an entire folder of images through the same workflow in one click.

USE CASE 3

Extract and process video frames one by one using a visual pipeline.

USE CASE 4

Chain together filters, AI models, and save steps in a drag-and-drop canvas.

Tech stack

PythonPyTorchNCNNONNXTensorRT

Getting it running

Difficulty · easy Time to first run · 30min

Download and run the installer for your OS, no Python required. chaiNNer sets up its own Python environment on first launch. Pick your AI framework from the built-in manager.

License not mentioned in the explanation.

In plain English

chaiNNer is a desktop application for processing images using a visual, node-based editor. Instead of writing code or working through fixed menus, you build a workflow by dragging blocks called nodes onto a canvas and connecting them with wires. Each node does one specific job, such as loading an image, applying a filter, running an AI model, or saving a result. You chain them together to describe the full sequence of operations you want to run. The project started as an AI image upscaling tool, meaning it was built to take a small or blurry image and produce a larger, sharper version using a trained neural network model. It has since grown into a more general image processing application, though upscaling remains a common use case. To do AI-based work, you first choose a framework from a built-in dependency manager. chaiNNer supports four options: PyTorch, NCNN, ONNX, and TensorRT. Nvidia GPU owners typically get the best performance from PyTorch or TensorRT. AMD GPU owners on any platform can use NCNN, and AMD users on Linux can also use PyTorch via a separate driver path. Apple Silicon Macs use PyTorch with a different acceleration method. A CPU-only fallback is available on any machine if no supported GPU is present. You do not need Python installed on your system before starting. chaiNNer downloads and manages its own isolated Python environment on first launch, so it will not interfere with anything else. Installation is a standard download-and-run package for Windows, macOS, or Linux. Batch processing is built in. A Load Images node processes an entire folder of images in one run. A Load Video node works through video files frame by frame. The editor shows visual feedback during a run by animating the connections between nodes, and a toolbar provides stop and pause controls. Nodes are color-coded by the type of data they pass, which makes it straightforward to see which outputs can connect to which inputs.

Copy-paste prompts

Prompt 1
How do I set up a simple workflow to upscale a folder of images using an AI model in chaiNNer?
Prompt 2
Which AI framework should I choose in chaiNNer if I have an Nvidia GPU versus an AMD GPU?
Prompt 3
How do I process a video file frame by frame in chaiNNer and save the results?
Prompt 4
What types of nodes are available in chaiNNer and how do I connect them to build a pipeline?
Prompt 5
Does chaiNNer work without a GPU, and how do I set it up on a Mac with Apple Silicon?
Open on GitHub → Explain another repo

← chainner-org on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.