Ask a Question

Prefer a chat interface with context about you and your work?

Chameleon: Mixed-Modal Early-Fusion Foundation Models

Chameleon: Mixed-Modal Early-Fusion Foundation Models

We present Chameleon, a family of early-fusion token-based mixed-modal models capable of understanding and generating images and text in any arbitrary sequence. We outline a stable training approach from inception, an alignment recipe, and an architectural parameterization tailored for the early-fusion, token-based, mixed-modal setting. The models are evaluated on a …