Skip to main content

Documentation

Documentation/Interface Quickstart

Interface Quickstart

ModelPilot deploys models with user-friendly web interfaces. Learn how to use ComfyUI for image/video and OpenWebUI for text models.

ComfyUI for Image & Video

ComfyUI is a powerful node-based interface for image and video generation. It provides visual workflow editing with full control over the generation process.

Getting Started with ComfyUI

  1. Access your deployment - Click the "Open UI" button on your dashboard
  2. Load the default workflow - Most deployments come with a pre-loaded workflow
  3. Enter your prompt - Find the text input node (usually labeled "CLIP Text Encode")
  4. Click Queue Prompt - The generate button in the top-right corner
  5. View your result - Output appears in the preview node when complete

Key ComfyUI Features

Node-Based Workflows

Connect nodes to build custom generation pipelines. Right-click to add new nodes.

Workflow Import/Export

Save workflows as JSON files. Share or back up your custom setups.

Custom Nodes

Extend functionality with community nodes. ModelPilot auto-installs required nodes.

Queue Management

Queue multiple generations. Monitor progress in the queue panel.

Common ComfyUI Tips

  • Seed Control: Set a specific seed for reproducible results, or use -1 for random
  • Steps: More steps = higher quality but slower. 20-30 is usually good
  • CFG Scale: Higher values follow prompts more strictly (7-12 typical)
  • Save Workflows: Use the menu to save your workflow before making changes

OpenWebUI for Text Models

OpenWebUI provides a ChatGPT-like interface for text generation models. It includes conversation history, multiple chats, and advanced features.

Getting Started with OpenWebUI

  1. Access your deployment - Click "Open UI" on your dashboard
  2. Create an account - First-time access requires creating a local account
  3. Start chatting - Type your message and press Enter or click Send
  4. Create new chats - Click "New Chat" to start fresh conversations

Key OpenWebUI Features

Conversation History

All chats are saved and searchable. Access previous conversations from the sidebar.

Model Selection

Switch between available models using the dropdown. Different models have different capabilities.

System Prompts

Customize model behavior with system prompts. Set personality or specific instructions.

File Upload

Upload documents for the model to analyze. Supported formats include PDF, TXT, and more.

OpenWebUI Tips

  • Temperature: Lower = more focused, higher = more creative (adjust in settings)
  • Context Length: Models remember recent messages. Long chats may need new threads
  • Keyboard Shortcuts: Shift+Enter for new lines, Enter to send
  • Export: Export conversations as markdown or JSON from the chat menu

API Access

Both interfaces also expose APIs for programmatic access:

Text Models (Ollama API)

https://your-pod-id-11434.proxy.runpod.net

Compatible with Ollama client libraries and OpenAI SDK.

Image Models (ComfyUI API)

https://your-pod-id-8188.proxy.runpod.net

REST API for queuing workflows and retrieving results.

See our API Documentation for detailed integration guides.

Ready to try?

Try our free demo to experience ComfyUI, or deploy your own model from the Model Catalog.