> ## Documentation Index
> Fetch the complete documentation index at: https://docs.flowscale.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# What is ComfyUI?

> Build sophisticated GenAI applications without coding using visual workflows and production deployment

## What is ComfyUI?

ComfyUI is a visual programming interface for building AI workflows using drag-and-drop nodes. Create sophisticated image, video, text, and audio generation workflows without coding. FlowScale AI deploys these workflows as production APIs.

{/* Image Description for Team: Split-screen screenshot showing ComfyUI workspace with complex workflow on left and clean API interface on right with transformation arrows */}

<Frame>
  <img src="https://mintcdn.com/flowscaleai/_NiiTj7mXdWDjGF6/images/glossary/comfyui_default_state.png?fit=max&auto=format&n=_NiiTj7mXdWDjGF6&q=85&s=08e5b0f7a2fcc7bb9790d8bbf2725c6c" alt="Clean overview of ComfyUI workspace showing the visual programming interface with sample nodes, connections, and basic workflow structure. Emphasizes the drag-and-drop nature and node-based architecture" width="1918" height="862" data-path="images/glossary/comfyui_default_state.png" />
</Frame>

## Core Capabilities

<Frame>
  <img src="https://mintcdn.com/flowscaleai/_NiiTj7mXdWDjGF6/images/glossary/comfyui-workflow-example.png?fit=max&auto=format&n=_NiiTj7mXdWDjGF6&q=85&s=fd904203eb1a8dcdd6f23735cd803cfc" alt="ComfyUI workspace showing multiple connected node chains for text, image, and video processing with clear data flow between AI models" width="1918" height="868" data-path="images/glossary/comfyui-workflow-example.png" />
</Frame>

<CardGroup cols={2}>
  <Card title="Beyond Images" icon="sparkles">
    Build complex workflows for **images, videos, audio, and text generation**—all in one interface
  </Card>

  <Card title="Complex Logic Made Simple" icon="brain">
    Create conditional workflows, multi-step pipelines, and advanced AI operations without coding
  </Card>

  <Card title="Drag-and-Drop Power" icon="hand">
    Each block (called a *node*) does one specialized job—combine them to build enterprise-grade GenAI solutions
  </Card>

  <Card title="Universal Compatibility" icon="globe">
    Works with any AI model, custom nodes, and runs anywhere—Windows, macOS, Linux, or cloud
  </Card>
</CardGroup>

Key features:

* **Visual Programming**: Connect nodes instead of writing code
* **Multi-modal**: Support for images, videos, audio, and text
* **Real-time Editing**: Modify workflows and see results instantly
* **Community Extensions**: Thousands of custom nodes available

## FlowScale AI Integration

FlowScale AI converts ComfyUI workflows into production APIs with auto-scaling infrastructure, monitoring, and security.

<CardGroup cols={2}>
  <Card title="Visual Development" icon="palette">
    Build complex workflows without coding
  </Card>

  <Card title="Production Deployment" icon="rocket">
    Deploy as scalable APIs and web interfaces
  </Card>

  <Card title="Managed Infrastructure" icon="server">
    Auto-scaling GPUs and monitoring
  </Card>

  <Card title="Complete Solution" icon="stack">
    From prototype to production without code
  </Card>
</CardGroup>

## Use Cases

<CardGroup cols={2}>
  <Card title="AI Art Platform" icon="image">
    **ComfyUI**: Multi-style image generation with LoRA switching
    **FlowScale**: Web playground where users generate custom art via simple prompts
  </Card>

  <Card title="Video Processing API" icon="video">
    **ComfyUI**: Video-to-video transformation with face swapping
    **FlowScale**: REST API that processes uploaded videos and returns results
  </Card>

  <Card title="Content Creation Tool" icon="pen-nib">
    **ComfyUI**: Text-to-image + upscaling + background removal pipeline
    **FlowScale**: Web app for marketers to create social media content
  </Card>

  <Card title="Custom AI Chatbot" icon="robot">
    **ComfyUI**: Multi-model text generation with memory and context
    **FlowScale**: Embeddable chat widget for websites
  </Card>
</CardGroup>

## Workflow Structure

Workflows consist of connected nodes that process data:

<Steps>
  <Step title="Input nodes">
    Load models and define prompts
  </Step>

  <Step title="Processing nodes">
    Apply samplers, upscalers, and transformations
  </Step>

  <Step title="Output nodes">
    Save or display results
  </Step>
</Steps>

## Key Concepts

| Term                   | Think of it as...        | Why it matters                                                       |
| ---------------------- | ------------------------ | -------------------------------------------------------------------- |
| **Node**               | A single LEGO® brick     | Does one job (e.g., "Load model")                                    |
| **Workflow**           | The finished LEGO® set   | Runs the whole image pipeline. Saved as `.json`                      |
| **Model / Checkpoint** | A cookbook               | Holds all the AI knowledge—whether for images, text, video, or audio |
| **Custom Node**        | A fan-made LEGO® piece   | Community add-ons—try new ideas without waiting for official updates |
| **Pod (FlowScale)**    | A line cook in the cloud | Executes your workflow on a rented GPU                               |

## Basic Workflow Example

<Steps>
  <Step title="Load Model">
    Choose your AI model (SDXL for images, LLaMA for text, etc.)
  </Step>

  <Step title="Add Input">
    Enter your text prompt
  </Step>

  <Step title="Configure Processing">
    Set parameters like steps, strength, and sampling method
  </Step>

  <Step title="Process Output">
    Convert output to desired format
  </Step>

  <Step title="Save Results">
    Output saved to results folder
  </Step>
</Steps>

## Essential Terms

<AccordionGroup>
  <Accordion title="Prompt">
    Text that describes the image you want
  </Accordion>

  <Accordion title="Checkpoint">
    The big file that stores the AI model's brain
  </Accordion>

  <Accordion title="Sampler">
    The method that slowly sharpens the noisy blob into a picture
  </Accordion>

  <Accordion title="LoRA">
    A small add-on file that teaches the model a new style or character
  </Accordion>

  <Accordion title="Pod (FlowScale)">
    A cloud worker that runs your workflow
  </Accordion>
</AccordionGroup>

## Learning Resources

<Card title="ComfyUI Official Documentation" icon="external-link" href="https://docs.comfy.org" color="#60a5fa">
  Comprehensive guides and API references for mastering ComfyUI
</Card>