Glossary: Vision and Image Generation
Patch, patches
Also written: patch, patches
A small square of an image that becomes one visual token: 28 × 28 pixels for Claude, 32 × 32 for current OpenAI models.
Glossary: Vision and Image Generation
Also written: patch, patches
A small square of an image that becomes one visual token: 28 × 28 pixels for Claude, 32 × 32 for current OpenAI models.