Leaderboard/Media/comfyui-workflow-skill
Last commit on April 9, 2026·Created on April 4, 2026

LingyiChen-AI/comfyui-workflow-skill

Writes ComfyUI node graphs from a description of the media you want.
Combined rank
#563
across all skills
In Media
#32
category rank
Stars
409
+4.1% in last 7d
Forks
60
0.0% in last 7d
Watchers
0
0 watchers in last 7d
Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of recent attention, adoption, and active maintenance.
TL;DR

This skill converts natural language descriptions into ready-to-run ComfyUI workflow JSON, covering txt2img, video generation, upscaling, audio, and 3D mesh pipelines. It helps AI-assisted creators, ComfyUI developers, and automation engineers skip manual node wiring, with 34 built-in templates and explicit support for ControlNet, LoRA, and LLM integration for script-to-video production.

WHO IT'S FOR
ComfyUI power users
generate workflows from natural language
AI content creators
build image and video generation pipelines
AI agent / automation builders
integrate ComfyUI workflows into agent pipelines
AI researchers and developers
experiment with multiple model architectures
Repository contents

1 skill file

Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.

Use this skill

Follow the documented setup, then try a first task.

See the repository for installation instructions.

Open repository instructions ↗

Give it something to do.

Suggested first task

Generate a basic text-to-image workflow

Uses ComfyUI Workflow Generator

  • Model name or family
  • Positive prompt
  • Negative prompt
  • Resolution
  • Sampling steps
  • CFG value
  • Sampler

Check the repository for this skill’s setup.

Use the ComfyUI Workflow Generator skill to create a small, ready-to-import ComfyUI txt2img workflow JSON. I will provide the model, positive and negative prompts, resolution, steps, CFG, and sampler. If any of those details are missing, suggest a common configuration before generating the workflow.
SKILL.md · Checked Sep 18, 2026