Current defaults
Why did we select these models?
Models
119+ video, image, audio and language models, tested on the same prompts and picked by the Glif agent.
Example eval
Beer closeup condensation
Preserves the exact can design from the reference (label, colors, red 'glif' wordmark) at macro distance. Condensation and droplets look physically real; wordmark stays crisp and legible.
Compare models
Video Generation
Models for video generation · 62 models
Image Generation
Models for creating images · 37 models
Audio Generation
Models for speech and audio · 18 models
Language models (LLMs)
Large language models for text, vision, and reasoning · 2 models
