comfyui

Configure ComfyUI workflows for image and video generation.

602|12|Updated Apr 22, 2026
One-click install
npx skills add https://github.com/video-production-buddy/video-production-buddy --skill comfyui-video-production-buddy
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: comfyui
Source: https://github.com/video-production-buddy/video-production-buddy/tree/main/.agents/local/skills/comfyui
Command: npx skills add https://github.com/video-production-buddy/video-production-buddy --skill comfyui-video-production-buddy

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Users integrating ComfyUI with Video Production Buddy often struggle with server setup, selecting the right workflow for their hardware, handling missing models or custom nodes, and correctly configuring output nodes and LoRAs to get usable video or image outputs without wasted render time.

Core Features & Use Cases

  • Workflow Selection Guidance: Choose between bundled workflows and custom community workflows, with specific recommendations for 8GB-12GB GPUs to avoid VRAM errors.
  • Setup and Configuration Support: Step-by-step instructions for ComfyUI server setup, model placement, LoRA stack configuration, and output node selection to ensure successful job submission.
  • Structured Error Handling: Clear troubleshooting steps for common failures including missing models, missing custom nodes, server unavailability, and render timeouts to minimize rework.
  • Use Case: If you want to run a community Wan 2.1 1.3B quantized video generation workflow on a 8GB GPU, this skill guides you to pick the correct low-VRAM workflow, place required models in the right directories, and select the proper output node to retrieve your final video clip.

Quick Start

Use the comfyui skill to generate a 10-second video clip with your custom low-VRAM Wan 2.1 workflow by providing the workflow JSON, output node ID, and your desired prompt text.

Frequently Asked Questions about comfyui

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

FAQPage Schema
How do I import a custom community workflow into ComfyUI without getting missing model or custom node errors?

To import a custom ComfyUI workflow without errors, you need structured placement of required models in the correct directories and proper resolution of missing custom nodes. This skill provides step-by-step guidance for workflow provenance tracking and error handling to ensure successful job submission.

Can I run Wan 2.1 video generation workflows on an 8GB GPU without hitting VRAM errors?

Yes, you can run Wan 2.1 video generation on an 8GB GPU by selecting a low-VRAM workflow configuration. This skill provides specific recommendations for 8GB-12GB GPUs, such as using quantized 1.3B models, to avoid VRAM errors during video generation.

What is the correct output node selection for retrieving a final video clip from a ComfyUI render job?

Correct output node selection for retrieving a final video clip requires specifying the proper output node ID within your workflow JSON. This skill guides you through output node configuration to ensure you successfully retrieve your generated video or image outputs.

How do I set up a LoRA stack in ComfyUI for image and video generation?

Setting up a LoRA stack in ComfyUI requires step-by-step configuration of your model placement and stack settings. This skill offers setup and configuration support to correctly configure LoRA stacks and ensure successful render job submission.

Why does my ComfyUI local or cloud render job timeout, and how do I recover?

ComfyUI render jobs timeout due to server unavailability or improper configuration during local and cloud rendering. This skill provides timeout recovery steps and server connectivity validation to minimize rework and ensure reliable job execution.

What's the best way to validate ComfyUI server connectivity before submitting a video generation job?

The best way to validate ComfyUI server connectivity is to run a server connectivity check before submitting your video generation job. This skill satisfies requirements for server validation, ensuring your environment is ready for bundled workflow execution.