comfyui

Orchestrates ComfyUI image, video and audio generation workflows via REST/WebSocket.

Updated May 23, 2026

Search Tags:#automation #workflow #multimodal #image-generation #audio-generation #video-generation #comfyui

Ready to run

npx skills add https://github.com/zengbaocheng/hermes-tech-hub --skill comfyui-zengbaocheng

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: comfyui
Source: https://github.com/zengbaocheng/hermes-tech-hub/tree/main/creative/comfyui
Command: npx skills add https://github.com/zengbaocheng/hermes-tech-hub --skill comfyui-zengbaocheng

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Hermes 的 ComfyUI 多媒体生成技能将 Agent 与 ComfyUI 的交互完整封装，用户仅需一句话即可在本地触发图片、视频和音频的自动生成与工作流编排。

Core Features & Use Cases

出图：通过 ComfyUI 工作流实现高质量图片生成。
出视频：结合 AnimateDiff、Wan、HunyuanVideo 等流程生成连贯视频。
出音频：整合 AudioCraft 工作流生成音频内容。
工作流链式调用：支持从生成 -> 放大 -> 局部重绘等自动化链路。

Quick Start

Install and enable the comfyui skill in Hermes, and describe your media task in one sentence to trigger generation.

Frequently Asked Questions about comfyui

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

FAQPage Schema

How do I automate image and video generation through a local ComfyUI workflow?▼

You can automate local ComfyUI multimedia generation by using a single-entry workflow skill that triggers image, video, and audio creation directly from a text prompt.

Can I chain multiple ComfyUI workflows together for tasks like upscaling and inpainting?▼

Yes, chained workflows are supported, allowing you to automate end-to-end media pipelines from initial generation through upscaling to localized redrawing.

Does this approach support video generation using AnimateDiff and HunyuanVideo models?▼

Video generation is fully supported by integrating AnimateDiff, Wan, and HunyuanVideo workflows to produce coherent video sequences automatically.

What is the best way to coordinate multiple local ComfyUI instances for media generation?▼

Multi-instance coordination is handled natively, orchestrating REST and WebSocket communication to manage concurrent media generation tasks across local deployments.

Do I need a locally deployed ComfyUI environment to use this multimedia generation workflow?▼

A local ComfyUI deployment is required, as the orchestration skill communicates with your local instance via REST and WebSocket APIs to execute workflows.

Can I generate audio content using AudioCraft workflows through ComfyUI?▼

Yes, audio generation is supported by integrating AudioCraft workflows, enabling you to produce audio content through the same automated workflow orchestration.