comfyui-runpod-agent

Queue ComfyUI prompts and manage workflows on RunPod via OpenClaw agents.

Updated Mar 7, 2026
One-click install
npx skills add https://github.com/huivrotiki/antigravity-code-workspace-copy --skill comfyui-runpod-agent
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: comfyui-runpod-agent
Source: https://github.com/huivrotiki/antigravity-code-workspace-copy/tree/main/02-Skills/comfyui-runpod-agent
Command: npx skills add https://github.com/huivrotiki/antigravity-code-workspace-copy --skill comfyui-runpod-agent

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, and includes scripts (resource) and references (resource) components.

What problem does it solve?

OpenClaw users need a reliable bridge to execute ComfyUI image-generation workflows on RunPod, enabling automation, status monitoring, and batch processing without manual pod management.

Core Features & Use Cases

  • Connects OpenClaw agents to a RunPod-hosted ComfyUI instance for prompt queuing and workflow execution.
  • Monitors GPU usage and system status while running image generation tasks.
  • Supports batch processing and workflow templating to scale generation pipelines.
  • Provides endpoints and integration details for REST and Telegram-based control.

Quick Start

Start by deploying a RunPod ComfyUI pod, configure COMFYUI_ENDPOINT and API key, then create an OpenClaw comfyui-runpod-agent to begin queuing prompts.

Frequently Asked Questions about comfyui-runpod-agent

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate ComfyUI image generation workflows on RunPod?

Automating ComfyUI image generation on RunPod requires an OpenClaw 2.0 agent to queue prompts and manage workflows via the ComfyUI RunPod proxy endpoints. This enables automated prompt queuing, workflow templating, and batch processing without manual pod management.

Can I monitor GPU usage while running ComfyUI batch processing tasks?

Monitoring GPU usage during ComfyUI batch processing is supported through the OpenClaw agent integration. It connects to your RunPod deployment to track system status and GPU utilization while image generation tasks are actively running.

Do I need an OpenClaw system to use the comfyui-runpod-agent?

An OpenClaw 2.0 system is required to function, as the agent acts as a bridge connecting OpenClaw agents to your RunPod-hosted ComfyUI instance. You also need access to configured ComfyUI RunPod proxy endpoints and a valid API key.

How do I queue prompts in ComfyUI deployed on a RunPod pod?

Queuing prompts in ComfyUI on RunPod involves deploying a pod, configuring the COMFYUI_ENDPOINT and API key, then creating an OpenClaw comfyui-runpod-agent to begin submitting and executing image generation workflows automatically.

Does the ComfyUI RunPod agent support Telegram-based control for workflow execution?

Telegram-based control for workflow execution is supported alongside REST endpoints. The agent provides integration details for both control methods, allowing you to queue prompts and manage ComfyUI workflows remotely.

What are the limitations of using OpenClaw agents for RunPod ComfyUI workflow templating?

Limitations include a strict dependency on the requests library and requiring a pre-existing OpenClaw 2.0 system. Workflow templating and batch processing cannot function without properly configured ComfyUI RunPod proxy endpoints and valid API access.