AI Models

CLIP (Contrastive Language-Image Pre-training)

An AI model that understands both images and text, connecting visual concepts with words. CLIP helps video generators understand what your text prompts describe visually.

Usage Example

Videz uses CLIP-based understanding to match your text prompts with visual concepts. When you write 'cyberpunk city,' CLIP helps the AI understand this refers to neon lights and futuristic architecture.