​

ModelChat Guide

​

Quick Start

​

Basic Setup

1. Join our Discord Server
2. Navigate to #model-chat
3. Use /private to start a private channel
4. Use /model to start an invite only private thread
5. Follow the in-channel guide using /model_help for detailed instructions

​

Available Features

​

Text Generation

• Access advanced language models through private channels
• Support for context-aware interactions
• Real-time text generation and responses
• Optimized for various use cases and applications

​

Media Generation

/text_to_video    # Generate videos from text descriptions
/text_to_image    # Create images from text prompts
/image_to_video   # Convert static images to video
/text_to_sfx      # Generate audio effects and music
/text_to_speech   # Generate spoken audio from text files
/speech_to_text   # Generate Speech-to-Text Transcriptions and Captions

​

Sound Generation

/text_to_sfx      # Create custom sound effects and music
                  # Parameters:
                  # - description: What to generate
                  # - duration: Length of audio

​

Creating Multimodal Prompts

​

Step-by-Step Guide

1. Start a private channel using /private
2. Activate a model using /model
3. Upload your media (images, video, markdown etc..)
4. Add your text prompt
5. Submit for processing
6. Make multi-turn prompts.

​

Best Practices

• Provide clear, detailed descriptions
• Create a detailed Spec prompt for your desired outcome
• Combine different media types for better context
• Review generated content before finalizing
• Use appropriate models for specific tasks

​

Help & Reference

​

Command Documentation

/model_help     # ModelChat assistance
/media_help     # MediaGen features
/audio_help     # AudioGen capabilities

​

Support Options

• Discord: Message @StreamPod AI directly
• Support Channel: Visit #general-support
• Website: StreamPod AI
• Email: support@streampod.ai

​

Advanced Usage

​

Model Selection

• Choose models based on your specific needs
• Consider factors like:
  • Task complexity
  • Output requirements
  • Processing speed
  • Quality expectations

​

Integration Tips

• Combine multiple commands for complex outputs
• Use intermediate results for refined generations
• Leverage model-specific features for optimal results
• Test different prompt structures for best outcomes