Presets
Save a subgraph as a reusable, parameterized preset — and reuse built-in model templates.
Custom Nodes
Add new node behavior by dropping a Python file into custom_nodes/ — hot-reloadable, no frontend changes.
Plugins
Install plugin packs of educational nodes, and learn how to write and publish your own.
Device Backends
How CodefyUI selects and falls back across CPU, CUDA, MPS, and ROCm — plus the experimental native-MLX inference spike.
API Reference
The CodefyUI backend REST and WebSocket endpoints — nodes, presets, graphs, plugins, models, images, and execution outputs.
Architecture
How CodefyUI is put together — backend-authoritative node definitions, WebSocket execution, topological scheduling, and the registry/plugin system.