yolo-flutter-app

English | 简体中文

🚀 YOLO Flutter - Ultralytics Official Plugin

Ultralytics YOLO Flutter is the official plugin for running YOLO models in Flutter apps on iOS and Android. It supports detection, instance segmentation, semantic segmentation, depth estimation, classification, pose, and OBB on both platforms, with two simple entry points:

• YOLO for single-image inference
• YOLOView for real-time camera inference

The main goal is simple integration: use an official model ID, or drop in your own exported model and let the plugin resolve task metadata for you.

  

✨ Features

• Official Ultralytics plugin for Flutter
• One Dart API for Android and iOS
• Metadata-first model loading with official model download and caching
• Real-time camera inference and single-image inference
• Controls for thresholds, accelerator selection, and result streaming
• YOLO26 and YOLO11 model families supported

⚡ Quick Start

Install the package:

Package: https://pub.dev/packages/ultralytics_yolo

dependencies:
  ultralytics_yolo: ^0.7.2

flutter pub get

Start with the default official model:

import 'package:ultralytics_yolo/ultralytics_yolo.dart';

final modelId = YOLO.defaultOfficialModel() ?? 'yolo26n';

YOLOView(
  modelPath: modelId,
  onResult: (results) {
    for (final r in results) {
      debugPrint('${r.className}: ${r.confidence}');
    }
  },
)

For single-image inference:

final yolo = YOLO(modelPath: 'yolo26n');
await yolo.loadModel();
final results = await yolo.predict(imageBytes);

▶️ Example App | 📖 Installation Guide | ⚡ Quick Start Guide

Import models from Ultralytics Platform

In your model’s Export tab, click the QR button on a completed LiteRT export (or Core ML for iPhone), then open the app, tap the QR button in the bottom toolbar, and point the existing camera preview at the code. While scanning, the camera dims around a viewfinder; tap Cancel or the QR button again to return to live inference. Use LiteRT with FP32 or W8A32 precision for Android, or Core ML for iPhone; exports must use batch 1 and static input shapes. The example app previews the model before downloading and adds it to the Models picker for selection, removal, and offline use. Tap the active model’s name to choose a Custom import or any Official model from compact task rows with size choices. The header shows the task, with a Custom marker for imports, above the model name. The Custom section also provides a Scan QR row with a help button for the Platform export guide. Core AI import links open in the native iOS app.

Import links authorize one export for 24 hours. Anyone with the link can download it during that time; installed models keep working after the link expires. Each export installs separately, even when model names match. App-link handling belongs to the example app; the plugin’s resolver and model picker remain usable with your own download source.

📦 Model Loading

The plugin supports three model flows.

1. Official model IDs

Use the default official model or a specific official ID and let the plugin handle download and caching:

final yolo = YOLO(modelPath: YOLO.defaultOfficialModel() ?? 'yolo26n');

Call YOLO.officialModels() to see which official IDs are available on the current platform. Official assets are downloaded on first use and cached in app storage, so the app package does not carry large model files.

Official assets are maintained as GitHub release assets:

The Flutter resolver uses the LiteRT release for Android and the Core ML release for Apple platforms. Every mobile asset uses a fixed 224 × 224 classification input or 640 × 640 input for every other task. These release tags are intentionally pinned for reproducible first-use downloads. See the model guide for the official export matrix, URL patterns, and model properties.

Core ML (.mlpackage) remains the default. Core AI (.aimodel) is an opt-in for iOS 27 and later devices: pass an .aimodel path, an .aimodel.zip Flutter asset, or an .aimodel.zip URL. It is not available on earlier iOS versions or in the iOS Simulator. The Ultralytics iOS app exposes the same opt-in as a Settings toggle (off by default). The official opt-in assets are the .aimodel.zip files on the yolo-ios-app v8.3.0 release; see the yolo-ios-app performance record for the trade-offs.

final yolo = YOLO(modelPath: 'https://github.com/ultralytics/yolo-ios-app/releases/download/v8.3.0/yolo26n.aimodel.zip');

2. Your own exported model

Pass your own exported YOLO model as a local path or Flutter asset path:

final yolo = YOLO(modelPath: 'assets/models/my-finetuned-model.tflite');

If the exported model includes embedded metadata, the plugin infers task and class labels automatically — it reads Ultralytics’ appended-ZIP metadata, with a standard TFLite (FlatBuffers) metadata fallback — so drag-and-drop custom models auto-detect. If metadata is missing, pass task explicitly.

final yolo = YOLO(
  modelPath: 'assets/models/my-finetuned-model.tflite',
  task: YOLOTask.detect,
);

3. Remote model URL

Pass an http or https URL and the plugin will download it into app storage before loading it.

4. Qualcomm NPU models (Android, opt-in)

Android ships with LiteRT (TFLite) and that remains the default — nothing changes for existing apps, and the QNN support adds zero bytes to your build. Any model path ending in _qnn.onnx (a Qualcomm QNN context binary exported with yolo export model=yolo26n.pt format=qnn nms=None imgsz=640, or imgsz=224 for classification) is routed to the Hexagon NPU through the ONNX Runtime QNN Execution Provider instead. Export with ultralytics>=8.4.188: earlier releases running onnxruntime-qnn 2.4 or newer write context binaries that fail to load here with Input name not found. nms=None selects raw one-to-many outputs for Android-side NMS.

Running QNN models requires a Snapdragon device with a Hexagon HTP (Snapdragon 8 Gen 2 or newer for the official _v73 assets; _v81 targets Snapdragon 8 Elite Gen 5) and three additions to your app’s android/app/build.gradle:

android {
    packagingOptions {
        jniLibs {
            useLegacyPackaging = true // the Hexagon DSP loader needs real .so files, not APK-mmapped ones
        }
    }
}

dependencies {
    implementation 'com.microsoft.onnxruntime:onnxruntime-android-qnn:1.29.0'
    implementation 'com.qualcomm.qti:qnn-runtime:2.51.0' // newer than the AAR's bundled QAIRT; required for the latest Snapdragons
}

final yolo = YOLO(
  modelPath: 'https://github.com/ultralytics/yolo-flutter-app/releases/download/v0.7.0/yolo26n_v73_qnn.onnx',
  task: YOLOTask.detect,
);

Without the Gradle opt-in, loading a _qnn.onnx model fails with a clear error and TFLite models are unaffected. The bundled example app follows the same opt-in — it ships without the QNN runtime to keep its download small, so build it with ENABLE_QNN=1 (e.g. ENABLE_QNN=1 flutter run --release) to test the NPU path on a device. See the performance guide for measured CPU/GPU/NPU numbers and tuning notes.

🧭 Official vs. Custom

For official models, start with YOLO.defaultOfficialModel() or YOLO.officialModels(). For custom models, start with the exported file you actually plan to ship.

📥 Using Your Own Model

For custom models, keep the app-side setup minimal.

• Android native assets: place .tflite files in android/app/src/main/assets
• Flutter assets on Android: place .tflite files in assets/models/
• iOS bundle: drag .mlpackage or .mlmodel into ios/Runner.xcworkspace
• Flutter assets on iOS: place .mlpackage.zip files in assets/models/

Then point modelPath at that file or asset path.

Official asset maintenance

The Android TFLite release assets are generated by scripts/export-tflite-models.py. The script defines the official YOLO26 task/size matrix, w8a32 export settings (int8 weights, FP32 activations — dynamic-range, so no calibration data is needed), optional one-shot TFLite inference verification, and optional GitHub release upload.

Run it on Linux x86 or macOS with Python ≥3.10:

uv venv --python 3.12 .venv
uv pip install --torch-backend cpu "ultralytics-opencv-headless[export-litert]>=8.4.188"
uv run python scripts/export-tflite-models.py --verify

Use --upload --repo ultralytics/yolo-flutter-app --tag v0.7.0 to replace the existing .tflite assets. Export QNN with Ultralytics using the same task-specific imgsz. Core ML assets are generated by ../yolo-ios-app/scripts/export-models.py and hosted on the existing iOS v8.3.0 release.

Android inference runs on LiteRT 2.x through an automatic GPU -> CPU accelerator ladder. w8a32 assets are the official download artifacts (the smallest GPU-compatible litert format); the GPU delegate compiles the whole graph on supported devices and otherwise falls back to CPU. GPU coverage still depends on the device driver and graph, so confirm delegate placement on your target hardware (the GPU delegate runs the graph in FP16):

# Requires ultralytics>=8.4.142
from ultralytics import YOLO

YOLO("yolo26n.pt").export(format="litert", nms=None, imgsz=640)
# Classification models use imgsz=224.

🎯 Choosing an API

Use YOLO when you already have image bytes and want one prediction at a time:

final yolo = YOLO(modelPath: 'yolo26n');
await yolo.loadModel();
final results = await yolo.predict(imageBytes);

Use YOLOView when you want live camera inference:

final controller = YOLOViewController();

YOLOView(
  modelPath: 'yolo26n',
  controller: controller,
  onResult: (results) {},
)

await controller.switchModel('assets/models/custom.tflite', YOLOTask.detect);

Use YOLOShowcase when you want the complete Ultralytics camera UI:

YOLOShowcase(
  initialTask: YOLOTask.detect,
  initialModelSize: 'n',
  onCapture: (bytes) {},
)

🔄 Migrating From 0.3.x UI APIs

Version 0.4.0 removes the old Dart-side overlay/control layer. Camera detections are rendered natively by YOLOView; Flutter now owns only the surrounding app controls.

🧩 Recommended Patterns

📚 Documentation

🤝 Community & Support

• 💬 Questions? Discord | Forums | GitHub Issues
• 🐛 Found a bug? Report it here
• 💡 Feature request? Let us know

💡 Contribute

Ultralytics thrives on community collaboration, and we deeply value your contributions! Whether it’s bug fixes, feature enhancements, or documentation improvements, your involvement is crucial. Please review our Contributing Guide for detailed insights on how to participate. We also encourage you to share your feedback through our Survey. A heartfelt thank you 🙏 goes out to all our contributors!

📄 License

Ultralytics offers two licensing options to accommodate diverse needs:

• AGPL-3.0 License: Ideal for students, researchers, and enthusiasts passionate about open-source collaboration. This OSI-approved license promotes knowledge sharing and open contribution. See the LICENSE file for details.
• Enterprise License: Designed for commercial applications, this license permits seamless integration of Ultralytics software and AI models into commercial products and services, bypassing the open-source requirements of AGPL-3.0. For commercial use cases, please inquire about an Enterprise License.

🔗 Related Resources

Native iOS Development

If you’re interested in using YOLO models directly in iOS applications with Swift (without Flutter), check out our dedicated iOS repository:

👉 Ultralytics YOLO iOS App - A native iOS application for real-time detection, instance segmentation, semantic segmentation, depth estimation, classification, pose estimation, and OBB detection with Ultralytics YOLO models.

This repository provides:

• Pure Swift implementation for iOS
• Direct Core ML integration
• Native iOS UI components
• Example code for various YOLO tasks
• Optimized for iOS performance

📮 Contact

Encountering issues or have feature requests related to Ultralytics YOLO? Please report them via GitHub Issues. For broader discussions, questions, and community support, join our Discord server!