comfyui

Automate image, video, and audio generation with ComfyUI workflows.

Updated Sep 28, 2021

Search Tags:#image generation #audio generation #video generation #ai models #comfyui

Ready to run

npx skills add https://github.com/XyHalcyon/config-files --skill comfyui-xyhalcyon

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: comfyui
Source: https://github.com/XyHalcyon/config-files/tree/main/hermes/skills/creative/comfyui
Command: npx skills add https://github.com/XyHalcyon/config-files --skill comfyui-xyhalcyon

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires comfy-cli, comfyui, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill automates the generation of images, video, and audio content using ComfyUI, a powerful tool for creative workflows.

Core Features & Use Cases

Image Generation: Create images with Stable Diffusion, SDXL, Flux, SD3, etc.
Video Generation: Generate video content using AnimateDiff, Hunyuan, Wan, AudioCraft, etc.
Audio Generation: Create audio content with various AI models.
Use Case: Imagine you want to create a short video featuring a futuristic cityscape. Use this Skill to generate the images, then combine them into a video using ComfyUI's tools.

Quick Start

Generate a text-to-image with ComfyUI:

python3 scripts/run_workflow.py --workflow workflows/sd15_txt2img.json --args '{"prompt": "a futuristic cityscape", "seed": 42}' --output-dir ./outputs

Frequently Asked Questions about comfyui

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

FAQPage Schema

How do I automate image generation with Stable Diffusion and SDXL workflows?▼

You can automate image generation using Stable Diffusion, SDXL, or Flux by executing ComfyUI workflows via script. Pass your prompt and parameters to the workflow JSON to output the generated images.

Can I generate video content using AnimateDiff and Hunyuan models?▼

Yes, you can generate video content using models like AnimateDiff and Hunyuan. The automation executes ComfyUI workflows that process your prompts to output the final video file.

Does ComfyUI automation work on macOS, Linux, and Windows?▼

Yes, ComfyUI automation is compatible with macOS, Linux, and Windows. It relies on comfy-cli to manage the lifecycle and execute generation workflows consistently across these operating systems.

Do I need comfy-cli installed to run audio generation workflows?▼

Yes, you need comfy-cli and ComfyUI installed to run audio generation workflows. comfy-cli manages the ComfyUI lifecycle and executes the workflow scripts needed to generate audio content.

What is the best way to run a text-to-image workflow from the command line?▼

The best way to run a text-to-image workflow from the command line is using the run_workflow.py script. Provide your workflow JSON path, prompt arguments, and output directory to execute the generation task.