skills.rest
heysuhas
heysuhasCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

comfyui

Execute image, video, and audio generation workflows via ComfyUI REST and WebSocket APIs.

2|1|Updated Jul 14, 2026
Search Tags:#automation#workflow#generative-ai#video-generation#stable-diffusion#comfyui
One-click install
npx skills add https://github.com/heysuhas/hermes_cli --skill comfyui-heysuhas
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: comfyui
Source: https://github.com/heysuhas/hermes_cli/tree/main/skills/creative/comfyui
Command: npx skills add https://github.com/heysuhas/hermes_cli --skill comfyui-heysuhas

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill bridges the gap between the powerful, node-based ComfyUI engine and automated AI workflows, allowing you to execute complex generative pipelines without manual UI interaction.

Core Features & Use Cases

  • Workflow Execution: Run image, video, and audio generation workflows via REST/WebSocket APIs.
  • Lifecycle Management: Automate installation, server startup, and dependency management using the official comfy-cli.
  • Use Case: Automatically generate a batch of 50 variations of a product image using a specific Flux or SDXL workflow, injecting unique prompts and seeds for each run.

Quick Start

Use the comfyui skill to run the workflow file named flux_dev_txt2img.json with the prompt a futuristic city skyline at sunset.

Frequently Asked Questions about comfyui

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

FAQPage Schema
How do I automate stable diffusion workflows without manual UI interaction?▼

You can execute stable diffusion workflows via the ComfyUI REST and WebSocket APIs to run generative pipelines without manual UI interaction. This enables programmatic image, video, and audio generation.

Can I run batch image generation with different prompts and seeds locally?▼

Yes, you can run batch image generation locally by injecting unique prompts and seeds for each run via parameter injection. This requires comfy-cli for environment setup and Python scripts for monitoring.

Do I need comfy-cli to manage server lifecycle for ComfyUI workflows?▼

Yes, you need comfy-cli to automate the ComfyUI server lifecycle including installation, server startup, and dependency management. This ensures custom node dependencies are resolved for local or cloud-hosted instances.

What's the best way to execute SDXL or Flux workflows via REST APIs?▼

The best way to execute SDXL or Flux workflows via REST APIs is by using Python-based scripts to monitor the WebSocket connection and manage output handling. This bridges the node-based engine and automated workflows.

How does parameter injection work for generative AI video workflows?▼

Parameter injection for generative AI video workflows works by passing unique prompts and seeds into your workflow files before execution via the REST API. This allows customized generation runs without manual UI configuration.

Related Skills

Explore More Design & Creative Skills→
paxlabs-incpaxlabs-inc
7

comfyui

Execute generative AI workflows via ComfyUI REST and WebSocket APIs.

Community
Advanced
yethikrishnayethikrishna

media

Generate images, videos, and speech from JSON prompts via Bash tools.

Community
Intermediate
partme-aipartme-ai
610

stable-diffusion

Guide Stable Diffusion model selection, prompt engineering, and parameter configuration for image generation.

Official
Intermediate
mainza-aimainza-ai
83

google-genai-media

Integrate Google GenAI media generation and editing into apps via Vertex AI and AI Studio.

Community
Advanced