Practical overview
When it fits
Use it when building a Flutter mobile feature that needs YOLO inference from a live camera or a single image, and the model can be used with the Android or iOS runtime path documented by the plugin.
Who it is for
- Flutter developers adding YOLO-based computer vision to Android or iOS apps.
- Mobile app teams choosing between live-camera and single-image inference workflows.
Documented uses
- Process camera frames for real-time object detection and other supported vision tasks.
- Run a YOLO prediction on image bytes within a mobile app.
- Use an official model ID or integrate a custom model with the documented platform runtime.
Requirements & limits
- Choose
YOLOViewfor live-camera inference andYOLOfor single-image inference. - Official model assets are downloaded on first use and cached in app storage; the app package need not carry those large model files.
- Custom model runtime differs by platform: LiteRT (TFLite) on Android and Core ML on iOS.
- The README lists an opt-in Qualcomm NPU route for QNN models on Snapdragon hardware.
- The repository specifies the AGPL-3.0 license.
Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.
Set up the YOLO Flutter package
Add the plugin dependency to a Flutter project and fetch its package dependencies.
Before you start
- A Flutter project with its dependency configuration available.
Steps
Add
ultralytics_yolo: ^0.6.16underdependenciesin the project’spubspec.yaml.Run
flutter pub get.
Expected outcome
The plugin is declared as a project dependency and Flutter fetches the package dependencies.
Guide limitations
- This setup recipe does not cover building, permissions, model selection or running inference.
Sources & review
Source record details
- Source availability
- Active
- Sources checked
- 13 October 2026
- Original website title
- ultralytics/yolo-flutter-app · Official homepage title · retained in its source language

