ComfyUI and comfyui-inpaint-nodes
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 comfyui-inpaint-nodes
Acly/comfyui-inpaint-nodes
Nodes for better inpainting with ComfyUI: Fooocus inpaint model for SDXL, LaMa, MAT, and various other tools for pre-filling inpaint & outpaint areas.
Provides specialized pre- and post-processing nodes including mask expansion/shrinkage, content-aware fill algorithms (Telea, Navier-Stokes), and lightweight inpaint models (LaMa, MAT) for seamless edge blending. The architecture uses a dual-output VAE encoding node to efficiently support variable denoise strengths while maintaining compatibility with SDXL checkpoints patched via Fooocus's lightweight inpaint adapter. Integrates tightly with ComfyUI's KSampler and conditioning pipeline, with optional OpenCV backend for advanced fill modes.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work