rookiestar28/ComfyUI-OpenClaw

Your own personal AIGC Factory. Any picture. Any reel. The Comfy way. ©️

ComfyUI-OpenClaw is a custom node pack for ComfyUI (the popular node-based AI image generation tool) that turns ComfyUI into a secure, automatable, remotely-controllable platform. It adds:

  • LLM-assisted nodes — planner, refiner, vision, and batch variants that use an LLM (like DeepSeek or Ollama) to help design or refine image-generation workflows.
  • A built-in UI panel — an "OpenClaw" sidebar inside ComfyUI for operator controls.
  • A Remote Admin Console — a mobile-friendly web page (/openclaw/admin) so you can manage ComfyUI from your phone or another device.
  • An HTTP automation API — webhooks, scheduled triggers, approval flows, presets, and a model manager, all protected by authentication.
  • Messaging platform connectors — control ComfyUI from Discord, Telegram, WhatsApp, LINE, WeChat, KakaoTalk, Slack, or Feishu/Lark via a sidecar process that bridges chat messages to the HTTP API.

Security is the core differentiator. Unlike convenience-first automation packs, this one is fail-closed by design: admin actions require tokens, webhooks are deny-by-default unless HMAC auth is configured, outbound LLM calls are SSRF-protected, secrets are stored server-side in an encrypted file (never browser storage), and multi-tenant mode isolates tenants strictly. It also ships a threat model, security checklist, and deployment guides.

How it works: The pack is cloned into ComfyUI's custom_nodes folder. It registers its own routes into the same Python server process that ComfyUI already runs, so there's no separate service to manage. LLM keys are set via environment variables (or an encrypted server-side store for localhost-only use). A connector sidecar handles the messaging-platform bridges.

Typical use cases: automating image-generation pipelines, running ComfyUI from a phone, approving jobs via chat, or deploying ComfyUI in production with hardened access controls.

Related

  • Project
    Comfy-Org/ComfyUI-Manager

    ComfyUI‑Manager is an extension for the visual AI‑pipeline UI ComfyUI. It adds a “Manager” panel that lets users browse, install, update, enable/disable, and remove custom node packages and model files from a curated registry or local cache. Features include one‑click installs, snapshot‑based environment restore, workflow sharing to external sites, component copy‑&‑paste, a CLI tool for head‑less use, and extensive configuration (security level, network mode, pip/uv handling). It streamlines handling the large ecosystem of community‑made nodes that power Stable‑Diffusion image generation in ComfyUI.

  • Project
    heshengtao/comfyui_LLM_party

    A comprehensive set of ComfyUI nodes for building LLM workflows, enabling the integration of AI agents, RAG, and VLMs into visual image generation pipelines.

  • Project
    Comfy-Org/comfy-cli

    comfy‑cli is a Python command‑line tool that installs, launches, and manages ComfyUI (an open‑source generative‑media engine). It handles environment setup, custom‑node installation, model downloads, workflow execution, and can offload jobs to the hosted Comfy Cloud service. Features include fast `uv`‑based dependency resolution, JSON‑structured output for LLM agents, shell completion, and utilities for testing PRs and managing background servers.

  • Project
    HuangYuChuh/ComfyUI_Skills_OpenClaw

    An agent-friendly bridge that turns ComfyUI workflows into callable skills for AI agents via a CLI and schema-based parameter mapping.

  • Project
    clawdotnet/openclaw.net

    OpenClaw.NET is a .NET‑native AI‑agent runtime and gateway. It provides a NativeAOT‑compatible executable, a web‑based chat/admin UI, OpenAI‑compatible APIs, 80+ built‑in tool adapters, multi‑channel support (Slack, Telegram, etc.), and first‑class integration with cloud and local LLM providers (OpenAI, Claude, Gemini, DeepSeek, Ollama, embedded Gemma‑4). Optional governance features let you audit and approve high‑risk tool actions. The project is aimed at developers who want a self‑hosted, observable AI‑agent platform that runs on Windows, macOS, or Linux.