comfyui-tooling-nodes  by Acly

ComfyUI extension for external tooling integration

Created 2 years ago
551 stars

Top 58.0% on SourcePulse

GitHubView on GitHub
Project Summary

This repository provides custom nodes and API extensions for ComfyUI, enabling its use as a backend for external tools. It facilitates direct image and model transfer without filesystem overhead, targeting developers and power users seeking programmatic control over ComfyUI workflows.

How It Works

The core innovation is bypassing ComfyUI's default filesystem-based image exchange. Nodes like Load Image (Base64) and Send Image (WebSocket) allow direct data transfer via base64 encoding or WebSockets, respectively. This streamlines integration by eliminating intermediate file operations. The project also introduces advanced features like region-based attention masking for targeted prompt application and a flexible tiling system for efficient VRAM usage and per-tile workflow customization.

Quick Start & Requirements

  • Install by cloning the repository into ComfyUI's custom_nodes directory: git clone https://github.com/Acly/comfyui-tooling-nodes.git
  • Requires ComfyUI installation.
  • Translation nodes require pip install argostranslate or pip install -r requirements.txt. Models are downloaded on first use.
  • See ComfyUI installation for ComfyUI setup.

Highlighted Details

  • Direct Image Transfer: Send/receive images via WebSocket or Base64, avoiding filesystem bottlenecks.
  • Region Attention Masking: Apply text prompts to specific image areas for more controlled generation.
  • Flexible Tiling: Split images into tiles with configurable padding and blending for custom per-tile processing.
  • API Extensions: Includes endpoints for model inspection, language listing, text translation, and model uploading.

Maintenance & Community

  • Maintained by Acly.
  • No explicit community links (Discord/Slack) or roadmap are provided in the README.

Licensing & Compatibility

  • The repository does not explicitly state a license in the README.

Limitations & Caveats

  • The lack of a specified license may pose compatibility issues for commercial or closed-source projects.
  • The NSFW filter is noted as imperfect, with potential for explicit content to bypass it.
Health Check
Last Commit

4 weeks ago

Responsiveness

1 day

Pull Requests (30d)
0
Issues (30d)
0
Star History
16 stars in the last 30 days

Explore Similar Projects

Starred by Deepak Pathak Deepak Pathak(Cofounder of Skild AI; Professor at CMU), Travis Fischer Travis Fischer(Founder of Agentic), and
8 more.

sygil-webui by Sygil-Dev

0.0%
8k
Web UI for Stable Diffusion
Created 3 years ago
Updated 2 months ago
Starred by Dan Abramov Dan Abramov(Core Contributor to React; Coauthor of Redux, Create React App), Patrick von Platen Patrick von Platen(Author of Hugging Face Diffusers; Research Engineer at Mistral), and
57 more.

stable-diffusion by CompVis

0.1%
71k
Latent text-to-image diffusion model
Created 3 years ago
Updated 1 year ago
Feedback? Help us improve.