Visual Intelligence
Visual Intelligence lets you search for objects and content within photos using Apple Intelligence on-device vision models.
Why It Exists
Finding specific photos in a large library is time-consuming and difficult. Visual Intelligence addresses the need for smart photo search and object identification using natural language descriptions and visual recognition.
How It Works
Visual Intelligence uses Apple Intelligence on-device vision models to understand and identify objects, text, and scenes within photos. Users can search their photo library by describing what they want to find (e.g., a red bicycle or a receipt from last month). The feature also provides detailed information about objects in photos, including products, landmarks, and artwork. Visual search integrates into the Photos app and Camera app, leveraging the Apple Neural Engine for fast, private on-device processing.
Everyday Use Cases
- Find a photo of your red bicycle from last summer
- Search for all receipts in your photo library
- Identify a landmark you photographed while traveling
- Get product details from a photo of an item in a store
User Workflow
- Open Photos app
- Tap the search bar
- Enter a text description or select a recognized object
- Visual Intelligence searches on-device using Apple Neural Engine
- Browse matching results
- Tap a result to view the full photo
AI Processing Flow
On-device Apple Intelligence vision model analyzes photo content, creates semantic embeddings, and indexes objects, text, and scenes using the Apple Neural Engine. No photo content is sent to cloud servers. Search queries are matched against the on-device index.
Inputs / Outputs
Inputs:
- Photo library content
- Text search queries
- Camera input
- On-device AI model
Outputs:
- Matching photos
- Object recognition labels
- Scene descriptions
- Product or landmark information
Known Limitations
- Requires iOS 18.1 or later
- Requires A17 Pro or M-series chip
- Recognition accuracy varies by lighting and image quality
- Indexing large libraries may take time
Unsupported Scenarios
- Does not work on devices without Apple Neural Engine
- Cannot identify content in DRM-protected photos
- May misidentify objects in low-quality or unusual lighting conditions
Performance Notes
Photo indexing runs during low-power idle periods. Search results appear in under 2 seconds for most queries. On-device processing ensures privacy with no impact on battery during normal use.
Available On
Shows where this feature is available and how its AI processing works on each platform. Availability may vary by device.
| Platform | Execution | Offline | Cloud | OS / Software |
|---|---|---|---|---|
| Apple Intelligence | Local | Yes | No - on-device | iOS 18.1+ (iPhone 15 Pro/16+), iPadOS 18.1+ (M2/M3 iPad+), macOS 15.1+ (M-series Mac+), Requires Photos app or Camera app integration |
Research Status
Confidence and verification reflect how complete documentation is. Fields may show Not assessed or Not yet verified while research is ongoing - this flags gaps, not product deficiencies.
| Research Status | Verified |
| Confidence | High |
| First introduced | 2024-09-09 |
| Last updated | 2026-08-16 |
| Last verified | 2026-08-16 |
Research Notes
Source: Apple Developer Documentation / WWDC 2024. Visual Intelligence is part of Apple Intelligence, available on iOS 18.1 and later. Uses on-device processing exclusively for privacy. Previously known as Visual Look Up.
Details
| Vendor | Apple |
| AI Platform | Apple Intelligence |
| Category | Vision |
Capability Mapping
This feature maps to canonical capability family: Visual Understanding.
Canonical capability: Visual Understanding.
- Visual Understanding - Interprets what is in view and provides contextual understanding or actions.
Grounded in 4 device(s) on Apple Intelligence.
Related Features
- Circle to Search - Cross-platform equivalent
- AI Camera Engine - Complementary
This page describes platform-level capability; not device-level support for any specific product.