🔮The Codex
Text-to-Image
AI that generates images from written text descriptions.
📖 Apprentice Explanation
Text-to-image AI creates pictures from your words. You describe what you want to see — like 'a sunset over mountains in watercolor style' — and the AI generates that image.
🧙 Archmage Notes
Text-to-image models use diffusion (Stable Diffusion, DALL-E 3) or autoregressive (Parti) architectures. CLIP provides text-image alignment. Key techniques include classifier-free guidance, negative prompts, and ControlNet for structural control.