Google's ML Kit for Flutter is a set of Flutter plugins that enable Flutter apps to use Google's standalone ML Kit.

Feature	Plugin	Source Code	Android	iOS
Barcode Scanning	google_mlkit_barcode_scanning		✅	✅
Face Detection	google_mlkit_face_detection		✅	✅
Image Labeling	google_mlkit_image_labeling		✅	✅
Object Detection and Tracking	google_mlkit_object_detection		✅	✅
Text Recognition	google_mlkit_text_recognition		✅	✅
Text Recognition V2	google_mlkit_text_recognition		✅	✅
Digital Ink Recognition	google_mlkit_digital_ink_recognition		✅	✅
Pose Detection	google_mlkit_pose_detection		✅	✅
Selfie Segmentation	google_mlkit_selfie_segmentation		✅	✅

Feature	Plugin	Source Code	Android	iOS
Language Identification	google_mlkit_language_id		✅	✅
On-Device Translation	google_mlkit_translation		✅	✅
Smart Reply	google_mlkit_smart_reply		✅	✅
Entity Extraction	google_mlkit_entity_extraction		✅	✅

• Minimum iOS Deployment Target: 10.0
• Xcode 13 or newer
• Swift 5
• ML Kit only supports 64-bit architectures (x86_64 and arm64). Check this list to see if your device has the required device capabilities.

Since ML Kit does not support 32-bit architectures (i386 and armv7), you need to exclude amrv7 architectures in Xcode in order to run flutter build ios or flutter build ipa. More info here.

Go to Project > Runner > Building Settings > Excluded Architectures > Any SDK > armv7

Then your Podfile should look like this:

# add this line:
$iOSVersion = '10.0'

post_install do |installer|
  # add these lines:
  installer.pods_project.build_configurations.each do |config|
    config.build_settings["EXCLUDED_ARCHS[sdk=*]"] = "armv7"
    config.build_settings['IPHONEOS_DEPLOYMENT_TARGET'] = $iOSVersion
  end
  
  installer.pods_project.targets.each do |target|
    flutter_additional_ios_build_settings(target)
    
    # add these lines:
    target.build_configurations.each do |config|
      if Gem::Version.new($iOSVersion) > Gem::Version.new(config.build_settings['IPHONEOS_DEPLOYMENT_TARGET'])
        config.build_settings['IPHONEOS_DEPLOYMENT_TARGET'] = $iOSVersion
      end
    end
    
  end
end

Notice that the minimum IPHONEOS_DEPLOYMENT_TARGET is 10.0, you can set it to something newer but not older.

• minSdkVersion: 21
• targetSdkVersion: 29

When Migrating from ML Kit for Firebase read this guide.

For Android details read this.

For iOS details read this.

Google's standalone ML Kit library does have any direct dependency with Firebase. As designed by Google, you do not need to include Firebase in your project in order to use ML Kit. However, some ML Kit APIs have the possibility to be used with Custom Models, that means that the default models can be replaced with custom TensorFlow Lite models.

The plugins that allow Custom Models are:

• google_mlkit_image_labeling
• google_mlkit_object_detection

When creating these plugins we tried to remove the Firebase dependency as much as possible. However, when wrapping them for Flutter, we realized that Firebase is needed in order to download the model, pass it to the detector and expose its functionality to be used in Flutter.

A Flutter plugin includes all of its dependencies in your project even thought you are only consuming some APIs of the plugin. For that reason those plugins always require you to configure Firebase even though you are not using Custom Models in your project.

We could remove the Custom Models and do not expose that functionality in Flutter, but that will deprive some developers the opportunity to use them. If you find a way to manage those dependencies feel free to contribute with your pull request.

To setup Firebase for your project check this links:

• Add Firebase to your Android project
• Add Firebase to your iOS project

Also please note that in latest versions, google_ml_kit has become an umbrella plugin including all the plugin listed in Features. For that reason you will need to configure Firebase in your project if using google_ml_kit. We recommend you start using the plugins listed in Features rather than using google_ml_kit, otherwise you will be including unnecessary dependencies in your project.

Find the example app here.

Contributions are welcome. In case of any problems look at existing issues, if you cannot find anything related to your problem then open an issue. Create an issue before opening a pull request for non trivial fixes. In case of trivial fixes open a pull request directly.