--- title: Building AI features using Foundation Models. Multimodal... description: Apple's Foundation Models framework now supports multimodal input, allowing images (and other files) to be passed alongside text prompts. The post walks... canonical: https://daily.dev/posts/building-ai-features-using-foundation-models-multimodal-input--rspctzfvk twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Building AI features using Foundation Models. Multimodal input. | daily.dev og:description: Apple's Foundation Models framework now supports multimodal input, allowing images (and other files) to be passed alongside text prompts. The post walks... og:url: https://daily.dev/posts/building-ai-features-using-foundation-models-multimodal-input--rspctzfvk og:image: https://api.daily.dev/og/posts/rsPcTZfvk.png og:image:alt: Building AI features using Foundation Models. Multimodal input. og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Building AI features using Foundation Models. Multimodal input. **[Swift with Majid](https://daily.dev/sources/swiftwithmajid)** · 3 min read · 0 upvotes · 0 comments ## Summary Apple's Foundation Models framework now supports multimodal input, allowing images (and other files) to be passed alongside text prompts. The post walks through building a plate-scanning feature using a Generable struct (PlateClassification) and the new Attachment type, which can be created from a URL, pixel buffer, CGImage, or CIImage, and used with PromptBuilder inside a LanguageModelSession to get structured nutritional analysis from an image. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How do I pass an image to Apple's Foundation Models framework in Swift? Use the new Attachment type introduced with multimodal input support, which can be created from a URL, pixel buffer, CGImage, or CIImage. Pass it inside a PromptBuilder closure alongside text instructions to the respond function on a LanguageModelSession, for example combining a string instruction with Attachment(imageURL: imageURL) to get a structured result back. _Developers adding vision-based AI features to Swift apps can track framework updates like this on daily.dev._ ### What is the Generable macro used for in Apple Foundation Models? The Generable macro defines a structured output type that the Foundation Model should return, using @Guide annotations to describe each property in plain language. For example, a PlateClassification struct with boolean fields like sugar, protein, fiber, and saturatedFat tells the model exactly what structured data to extract from an image, such as a photo of a meal. _Those building structured AI outputs in Swift apps follow framework changes like this via daily.dev._ ## Similar posts on daily.dev - [Building AI features using Foundation Models. Streaming.](https://daily.dev/posts/building-ai-features-using-foundation-models-streaming--znaaejkcr) · Swift with Majid · 0 upvotes · 0 comments - [Apple’s Foundation Models and Why They’re Different From Other AI Providers](https://daily.dev/posts/apple-s-foundation-models-and-why-they-re-different-from-other-ai-providers-2gck4h5yv) · Medium · 1 upvotes · 0 comments - [How developers are using Apple’s local AI models with iOS 26](https://daily.dev/posts/how-developers-are-using-apple-s-local-ai-models-with-ios-26-f1svjq7kq) · TechCrunch · 0 upvotes · 0 comments --- Tags: [#ios](https://daily.dev/tags/ios), [#swift](https://daily.dev/tags/swift), [#local-ai](https://daily.dev/tags/local-ai), [#multimodal](https://daily.dev/tags/multimodal) [View this post on daily.dev](https://daily.dev/posts/building-ai-features-using-foundation-models-multimodal-input--rspctzfvk) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Building AI features using Foundation Models. Multimodal input.","url":"https://daily.dev/posts/building-ai-features-using-foundation-models-multimodal-input--rspctzfvk","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/building-ai-features-using-foundation-models-multimodal-input--rspctzfvk"},"datePublished":"2026-09-01T16:31:12.108Z","dateModified":"2026-09-01T16:47:11.934Z","description":"Apple's Foundation Models framework now supports multimodal input, allowing images (and other files) to be passed alongside text prompts. The post walks...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/900ea4f8d00165bea84465cb77f990c3?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/900ea4f8d00165bea84465cb77f990c3?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Swift with Majid","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Swift with Majid","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/7f8a6f70d695454391dcd7dcd91679b2","url":"https://daily.dev/sources/swiftwithmajid"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/building-ai-features-using-foundation-models-multimodal-input--rspctzfvk","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ios,swift,local-ai,multimodal","timeRequired":"PT3M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Swift with Majid","item":"https://daily.dev/sources/swiftwithmajid"},{"@type":"ListItem","position":3,"name":"Building AI features using Foundation Models. Multimodal input."}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/building-ai-features-using-foundation-models-multimodal-input--rspctzfvk#faq","mainEntity":[{"@type":"Question","name":"How do I pass an image to Apple's Foundation Models framework in Swift?","acceptedAnswer":{"@type":"Answer","text":"Use the new Attachment type introduced with multimodal input support, which can be created from a URL, pixel buffer, CGImage, or CIImage. Pass it inside a PromptBuilder closure alongside text instructions to the respond function on a LanguageModelSession, for example combining a string instruction with Attachment(imageURL: imageURL) to get a structured result back. Developers adding vision-based AI features to Swift apps can track framework updates like this on daily.dev."}},{"@type":"Question","name":"What is the Generable macro used for in Apple Foundation Models?","acceptedAnswer":{"@type":"Answer","text":"The Generable macro defines a structured output type that the Foundation Model should return, using @Guide annotations to describe each property in plain language. For example, a PlateClassification struct with boolean fields like sugar, protein, fiber, and saturatedFat tells the model exactly what structured data to extract from an image, such as a photo of a meal. Those building structured AI outputs in Swift apps follow framework changes like this via daily.dev."}}]} ```