ComfyUI and rgthree-comfy
About ComfyUI
Comfy-Org/ComfyUI
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
Supports diverse generative models across image, video, audio, and 3D modalities with intelligent memory management and GPU offloading for low-VRAM systems. The architecture uses an asynchronous queue system with incremental execution—only re-computing workflow nodes that have changed—and integrates LoRAs, ControlNets, and model merging capabilities. Extensible through custom nodes and external API providers, while maintaining fully offline operation for core functionality.
About rgthree-comfy
rgthree/rgthree-comfy
Making ComfyUI more comfortable!
Provides a curated set of custom nodes including advanced rerouting with directional layout, context-passing "pipes" for cleaner data flow, multi-LoRA loading with per-LoRA toggling, and integrated prompt editing with embedding/LoRA dropdown selection. Installs as a ComfyUI custom node package that extends the node library while maintaining interoperability with standard nodes through unified input/output patterns. Includes UX enhancements like keyboard-navigable bookmarks, image comparison tools, and configurable settings via `rgthree_config.json` to toggle features without conflicts.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work