comfyui-tooling-nodes and comfyui-inpaint-nodes
These are ecosystem siblings—one provides backend infrastructure for external tool integration while the other provides specialized inpainting nodes that can be consumed by those external tools through the shared ComfyUI platform.
About comfyui-tooling-nodes
Acly/comfyui-tooling-nodes
Nodes for using ComfyUI as a backend for external tools. Send and receive images directly without filesystem upload/download.
Implements in-memory image transport via base64 embedding or HTTP/WebSocket APIs, eliminating filesystem dependencies. Extends ComfyUI with attention-based region masking for precise spatial control over text prompts, and flexible tile-based processing for VRAM-efficient batch workflows. Includes auxiliary nodes for local text translation, NSFW filtering, and model inspection via HTTP endpoints.
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