# Image Analysis

Some multimodal[^1] text models can recognize various objects, scenes, references, and artistic styles in an image. It would be somewhat inaccurate to duplicate their description here, as they are not specialized Vision models in the classical sense. You can read more about this functionality in the **Capabilities** section, specifically in the [Vision in Text Models (Image-to-Text)](https://docs.aimlapi.com/capabilities/image-to-text-vision) article.

[^1]: **Multimodal models** can process and understand multiple types of input, such as text and images, rather than just one.