Understand and use safety settings

You can use safety settings to adjust the likelihood of getting responses that may be considered harmful. By default, safety settings block content with medium and/or high probability of being unsafe content across all dimensions.

Jump to Gemini safety settings Jump to Imagen safety settings

Safety settings for Gemini models

Click your Gemini API provider to view provider-specific content and code on this page. Gemini Developer API Vertex AI Gemini API

Learn more about safety settings for Gemini models in the Gemini Developer API documentation.

Note: Safety settings aren't applicable if you're using the Gemini Live API.

Swift

You configure SafetySettings when you create a GenerativeModel instance.

Example with one safety setting:

import FirebaseAI

// Specify the safety settings as part of creating the `GenerativeModel` instance
let model = FirebaseAI.firebaseAI(backend: .googleAI()).generativeModel(
  modelName: "GEMINI_MODEL_NAME",
  safetySettings: [
    SafetySetting(harmCategory: .harassment, threshold: .blockOnlyHigh)
  ]
)

// ...

Example with multiple safety settings:

import FirebaseAI

let harassmentSafety = SafetySetting(harmCategory: .harassment, threshold: .blockOnlyHigh)
let hateSpeechSafety = SafetySetting(harmCategory: .hateSpeech, threshold: .blockMediumAndAbove)

// Specify the safety settings as part of creating the `GenerativeModel` instance
let model = FirebaseAI.firebaseAI(backend: .googleAI()).generativeModel(
  modelName: "GEMINI_MODEL_NAME",
  safetySettings: [harassmentSafety, hateSpeechSafety]
)

// ...

Kotlin

You configure SafetySettings when you create a GenerativeModel instance.

Example with one safety setting:

import com.google.firebase.vertexai.type.HarmBlockThreshold
import com.google.firebase.vertexai.type.HarmCategory
import com.google.firebase.vertexai.type.SafetySetting

// Specify the safety settings as part of creating the `GenerativeModel` instance
val model = Firebase.ai(backend = GenerativeBackend.googleAI()).generativeModel(
    modelName = "GEMINI_MODEL_NAME",
    safetySettings = listOf(
        SafetySetting(HarmCategory.HARASSMENT, HarmBlockThreshold.ONLY_HIGH)
    )
)

// ...

Example with multiple safety settings:

import com.google.firebase.vertexai.type.HarmBlockThreshold
import com.google.firebase.vertexai.type.HarmCategory
import com.google.firebase.vertexai.type.SafetySetting

val harassmentSafety = SafetySetting(HarmCategory.HARASSMENT, HarmBlockThreshold.ONLY_HIGH)
val hateSpeechSafety = SafetySetting(HarmCategory.HATE_SPEECH, HarmBlockThreshold.MEDIUM_AND_ABOVE)

// Specify the safety settings as part of creating the `GenerativeModel` instance
val model = Firebase.ai(backend = GenerativeBackend.googleAI()).generativeModel(
    modelName = "GEMINI_MODEL_NAME",
    safetySettings = listOf(harassmentSafety, hateSpeechSafety)
)

// ...

Java

You configure SafetySettings when you create a GenerativeModel instance.

SafetySetting harassmentSafety = new SafetySetting(HarmCategory.HARASSMENT,
HarmBlockThreshold.ONLY_HIGH);

// Specify the safety settings as part of creating the `GenerativeModel` instance
GenerativeModelFutures model = GenerativeModelFutures.from(
        FirebaseAI.getInstance(GenerativeBackend.googleAI())
                .generativeModel(
                  /* modelName */ "IMAGEN_MODEL_NAME",
                  /* generationConfig is optional */ null,
                  Collections.singletonList(harassmentSafety)
                );
);

// ...

Example with multiple safety settings:

SafetySetting harassmentSafety = new SafetySetting(HarmCategory.HARASSMENT,
HarmBlockThreshold.ONLY_HIGH);

SafetySetting hateSpeechSafety = new SafetySetting(HarmCategory.HATE_SPEECH,
HarmBlockThreshold.MEDIUM_AND_ABOVE);

// Specify the safety settings as part of creating the `GenerativeModel` instance
GenerativeModelFutures model = GenerativeModelFutures.from(
        FirebaseAI.getInstance(GenerativeBackend.googleAI())
                .generativeModel(
                  /* modelName */ "IMAGEN_MODEL_NAME",
                  /* generationConfig is optional */ null,
                  List.of(harassmentSafety, hateSpeechSafety)
                );
);

// ...

Web

You configure SafetySettings when you create a GenerativeModel instance.

Example with one safety setting:

import { HarmBlockThreshold, HarmCategory, getAI, getGenerativeModel, GoogleAIBackend } from "firebase/ai";

// ...

const ai = getAI(firebaseApp, { backend: new GoogleAIBackend() });

const safetySettings = [
  {
    category: HarmCategory.HARM_CATEGORY_HARASSMENT,
    threshold: HarmBlockThreshold.BLOCK_ONLY_HIGH,
  },
];

// Specify the safety settings as part of creating the `GenerativeModel` instance
const model = getGenerativeModel(ai, { model: "GEMINI_MODEL_NAME", safetySettings });

// ...

Example with multiple safety settings:

import { HarmBlockThreshold, HarmCategory, getAI, getGenerativeModel, GoogleAIBackend } from "firebase/ai";

// ...

const ai = getAI(firebaseApp, { backend: new GoogleAIBackend() });

const safetySettings = [
  {
    category: HarmCategory.HARM_CATEGORY_HARASSMENT,
    threshold: HarmBlockThreshold.BLOCK_ONLY_HIGH,
  },
  {
    category: HarmCategory.HARM_CATEGORY_HATE_SPEECH,
    threshold: HarmBlockThreshold.BLOCK_MEDIUM_AND_ABOVE,
  },
];

// Specify the safety settings as part of creating the `GenerativeModel` instance
const model = getGenerativeModel(ai, { model: "GEMINI_MODEL_NAME", safetySettings });

// ...

Dart

You configure SafetySettings when you create a GenerativeModel instance.

Example with one safety setting:

// ...

final safetySettings = [
  SafetySetting(HarmCategory.harassment, HarmBlockThreshold.high)
];

// Specify the safety settings as part of creating the `GenerativeModel` instance
final model = FirebaseAI.googleAI().generativeModel(
  model: 'GEMINI_MODEL_NAME',
  safetySettings: safetySettings,
);

// ...

Example with multiple safety settings:

// ...

final safetySettings = [
  SafetySetting(HarmCategory.harassment, HarmBlockThreshold.high),
  SafetySetting(HarmCategory.hateSpeech, HarmBlockThreshold.high),
];

// Specify the safety settings as part of creating the `GenerativeModel` instance
final model = FirebaseAI.googleAI().generativeModel(
  model: 'GEMINI_MODEL_NAME',
  safetySettings: safetySettings,
);

// ...

Unity

You configure SafetySettings when you create a GenerativeModel instance.

Example with one safety setting:

// ...

// Specify the safety settings as part of creating the `GenerativeModel` instance
var ai = FirebaseAI.GetInstance(FirebaseAI.Backend.GoogleAI());
var model = ai.GetGenerativeModel(
  modelName: "GEMINI_MODEL_NAME",
  safetySettings: new SafetySetting[] {
    new SafetySetting(HarmCategory.Harassment, SafetySetting.HarmBlockThreshold.OnlyHigh)
  }
);

// ...

Example with multiple safety settings:

// ...

var harassmentSafety = new SafetySetting(HarmCategory.Harassment, SafetySetting.HarmBlockThreshold.OnlyHigh);
var hateSpeechSafety = new SafetySetting(HarmCategory.HateSpeech, SafetySetting.HarmBlockThreshold.MediumAndAbove);

// Specify the safety settings as part of creating the `GenerativeModel` instance
var ai = FirebaseAI.GetInstance(FirebaseAI.Backend.GoogleAI());
var model = ai.GetGenerativeModel(
  modelName: "GEMINI_MODEL_NAME",
  safetySettings: new SafetySetting[] { harassmentSafety, hateSpeechSafety }
);

// ...

Safety settings for Imagen models

Click your Gemini API provider to view provider-specific content and code on this page. Gemini Developer API Vertex AI Gemini API

Learn about all the supported safety settings and their available values for Imagen models in the Google Cloud documentation.

Swift

You configure ImagenSafetySettings when you create an ImagenModel instance.

import FirebaseAI

// Specify the safety settings as part of creating the `ImagenModel` instance
let model = FirebaseAI.firebaseAI(backend: .googleAI()).imagenModel(
  modelName: "IMAGEN_MODEL_NAME",
  safetySettings: ImagenSafetySettings(
    safetyFilterLevel: .blockLowAndAbove,
    personFilterLevel: .allowAdult
  )
)

// ...

Kotlin

You configure ImagenSafetySettings when you create an ImagenModel instance.

// Specify the safety settings as part of creating the `ImagenModel` instance
val model = Firebase.ai(backend = GenerativeBackend.googleAI()).imagenModel(
  modelName = "IMAGEN_MODEL_NAME",
  safetySettings = ImagenSafetySettings(
    safetyFilterLevel = ImagenSafetyFilterLevel.BLOCK_LOW_AND_ABOVE,
    personFilterLevel = ImagenPersonFilterLevel.BLOCK_ALL
  )
)

// ...

Java

You configure ImagenSafetySettings when you create an ImagenModel instance.

// Specify the safety settings as part of creating the `ImagenModel` instance
ImagenModelFutures model = ImagenModelFutures.from(
        FirebaseAI.getInstance(GenerativeBackend.googleAI())
                .imagenModel(
                  /* modelName */ "IMAGEN_MODEL_NAME",
                  /* imageGenerationConfig */ null);
);

// ...

Web

You configure ImagenSafetySettings when you create an ImagenModel instance.

// ...

const ai = getAI(firebaseApp, { backend: new GoogleAIBackend() });

// Specify the safety settings as part of creating the `ImagenModel` instance
const model = getImagenModel(
  ai,
  {
    model: "IMAGEN_MODEL_NAME",
    safetySettings: {
      safetyFilterLevel: ImagenSafetyFilterLevel.BLOCK_LOW_AND_ABOVE,
      personFilterLevel: ImagenPersonFilterLevel.ALLOW_ADULT,
    }
  }
);

// ...

Dart

You configure ImagenSafetySettings when you create an ImagenModel instance.

// ...

// Specify the safety settings as part of creating the `ImagenModel` instance
final model = FirebaseAI.googleAI().imagenModel(
  model: 'IMAGEN_MODEL_NAME',
  safetySettings: ImagenSafetySettings(
    ImagenSafetyFilterLevel.blockLowAndAbove,
    ImagenPersonFilterLevel.allowAdult,
  ),
);

// ...

Unity

Using Imagen is not yet supported for Unity, but check back soon!

Other options to control content generation

• Learn more about prompt design so that you can influence the model to generate output specific to your needs.
• Configure model parameters to control how the model generates a response. For Gemini models, these parameters include max output tokens, temperature, topK, and topP. For Imagen models, these include aspect ratio, person generation, watermarking, etc.
• Set system instructions to steer the behavior of the model. This feature is like a preamble that you add before the model gets exposed to any further instructions from the end user.
• Pass a response schema along with the prompt to specify a specific output schema. This feature is most commonly used when generating JSON output, but it can also be used for classification tasks (like when you want the model to use specific labels or tags).