Can i send image as input to foundation model for the model to reference?
Asked on 06/12/2025
1 search
The Foundation Models framework introduced by Apple at WWDC allows developers to use on-device large language models for various tasks. However, the context provided does not mention the capability to send images as input to the foundation model for reference. The framework primarily focuses on text-based tasks such as text extraction, summarization, and content generation.
For image-related tasks, Apple provides the Vision framework, which is designed to understand the content of images and videos. If you are interested in image analysis, you might want to explore the Vision framework as mentioned in the session Discover machine learning & AI frameworks on Apple platforms.
If you have more specific questions about the capabilities of the Foundation Models framework or other Apple frameworks, feel free to ask!
Explore prompt design & safety for on-device foundation models
Design generative AI experiences that leverage the strengths of the Foundation Models framework. We’ll start by showing how to design prompts for the on-device large language model at the core of Apple Intelligence. Then, we’ll introduce key ideas around AI safety, and offer concrete strategies to make your generative AI features safe, reliable, and delightful.
Discover machine learning & AI frameworks on Apple platforms
Tour the latest updates to machine learning and AI frameworks available on Apple platforms. Whether you are an app developer ready to tap into Apple Intelligence, an ML engineer optimizing models for on-device deployment, or an AI enthusiast exploring the frontier of what is possible, we’ll offer guidance to help select the right tools for your needs.
Platforms State of the Union
Discover the newest advancements on Apple platforms.