FirebaseVertexAI Framework Reference

ImagenSafetyFilterLevel

@available(iOS 15.0, macOS 12.0, tvOS 15.0, watchOS 8.0, *)
public struct ImagenSafetyFilterLevel : ProtoEnum, Sendable

A filter level controlling how aggressively to filter sensitive content.

Text prompts provided as inputs and images (generated or uploaded) through Imagen on Vertex AI are assessed against a list of safety filters, which include ‘harmful categories’ (for example, violence, sexual, derogatory, and toxic). This filter level controls how aggressively to filter out potentially harmful content from responses. See the safetySetting documentation and the Responsible AI and usage guidelines for more details.

• blockLowAndAbove

  The most aggressive filtering level; most strict blocking.

  Declaration

  Swift

  public static let blockLowAndAbove: ImagenSafetyFilterLevel

• blockMediumAndAbove

  Blocks some problematic prompts and responses.

  Declaration

  Swift

  public static let blockMediumAndAbove: ImagenSafetyFilterLevel

• blockOnlyHigh

  Reduces the number of requests blocked due to safety filters.

  Important

  This may increase objectionable content generated by Imagen.

  Declaration

  Swift

  public static let blockOnlyHigh: ImagenSafetyFilterLevel

• blockNone

  The least aggressive filtering level; blocks very few problematic prompts and responses.

  Important

  Access to this feature is restricted and may require your use case to be reviewed and approved by Cloud support.

  Declaration

  Swift

  public static let blockNone: ImagenSafetyFilterLevel