Documentation
English
AI Concepts

What AI do we use ?

Discover what AI technology powers virtual characters, conversations, roleplay, and creative AI experiences.

On this page 5

Our platform is powered by multiple types of artificial intelligence systems that work together to create immersive interactions with AI characters. Each system is specialized for a specific purpose, such as conversation, image generation, or video creation.

Instead of relying on a single model, we combine different AI technologies to deliver a complete experience across chat, visuals, and dynamic content.

Text-to-Text AI for Chat System

The chat experience is powered by advanced text-to-text AI, designed to understand user messages and generate natural, contextual responses.

This system works by analyzing the conversation history, user input, and character personality traits. It then generates a response that matches the tone, style, and behavior defined for each AI character.

This allows AI characters to:

  • Hold realistic and coherent conversations
  • Adapt their personality over time
  • Engage in roleplay and storytelling
  • Maintain context across long chats

The result is a dynamic conversational experience that feels personalized and responsive.

Text-to-Image AI for Visual Content

For images, the platform uses text-to-image AI technology. This system transforms written descriptions into detailed visual outputs.

When a character or user requests an image, the AI interprets the prompt, including style, environment, character details, and mood, then generates a corresponding visual representation.

This enables:

  • AI-generated character portraits
  • Scene illustrations and story visuals
  • Style-based artwork (realistic, anime, fantasy, etc.)
  • Dynamic visual storytelling

Each image is uniquely generated based on context and input, making every visual experience original.

Image-to-Video AI for Motion Content

Videos are created using image-to-video AI systems that animate static visuals into moving sequences.

This technology takes an image as a starting point and generates motion, transitions, and visual dynamics that bring it to life. It can simulate character expressions, environmental movement, and cinematic effects.

This enables:

  • Short animated character clips
  • Story-driven visual sequences
  • Motion-enhanced illustrations
  • Immersive AI-generated storytelling videos

It transforms still images into engaging video content that expands the narrative experience.

How These AI Systems Work Together

Each AI system is designed for a specific layer of the experience, but they are connected within the same ecosystem.

  • Text-to-text powers conversations
  • Text-to-image creates visual identity and scenes
  • Image-to-video brings visuals into motion

Together, they allow AI characters to talk, create, and evolve across multiple formats, making the experience more immersive and interactive.

Building a Unified AI Experience

By combining different AI technologies, the platform delivers a seamless environment where characters are not limited to chat alone. They can express themselves through text, images, and videos, creating a richer and more dynamic universe for users to explore.