VisionGenerativeModelParams

Next id: 34

Fields
sampleCount integer

Number of output images.

sampleImageSize string

The size of output images. If empty, will use default size 1024 for imagen 2 and 3 models, 1K for Imagen 4 models. Supported size: 64, 256, 512, 1024, 2048, and 4096 for imagen 2 and 3 models. 1K, 2K (case-insensitive) for Imagen 4 models.

storageUri string

The gcs bucket where to save the generated images.

negativePrompt string

Optional field in addition to the text content. Negative prompts can be explicitly stated here to help generate the images.

seed integer

The RNG seed. If RNG seed is exactly same for each request with unchanged inputs, the prediction results will be consistent. Otherwise, a random RNG seed will be used each time to produce a different result.

mode string

The parameter to specify editing mode. Currently support: -- interactive -- upscale

model
(deprecated)
string

Select underlying model to do the generation. Only listed models are supported: -- muse -- imagen

aspectRatio string

Optional generation mode parameter that controls aspect ratio. Supported ratios include: -- 1:1 (default, square) -- 5:4 (frame and print) -- 3:2 (print photography) -- 7:4 (TV screens and smartphone screens) -- 4:3 (TV) -- 16:9 (landscape) -- 9:16 (portrait)

guidanceScale number

Optional editing mode parameter that controls the strength of the prompt. Suggested values are: -- 0-9 (low strength) -- 10-20 (medium strength) -- 21+ (high strength)

enablePersonFaceFilter
(deprecated)
boolean

Whether to enable person/face rai filtering. Default to be false.

disablePersonFace
(deprecated)
boolean
safetySetting string

Different safety setting applying various restricness in generating images. Case insensitive. Levels are: block_low_and_above block_medium_and_above block_only_high block_none

Deprecated values respectively are: block_most block_some block_few block_fewest

raiLevel
(deprecated)
integer
enableChildFilter
(deprecated)
boolean

Whether to enable child rai filtering. Default to be true. This requires users are allowlisted. Otherwise, this value will be ignored.

disableChild
(deprecated)
boolean
personGeneration string

Whether allow to generate person images, and restrict to specific ages. Supported values are: dont_allow allow_adult allowAll

sampleImageStyle string

Optional. The pre-defined style for generated images. No styles will be applied if this field is empty of unspecified. Possible values could be: - photograph - digital_art - landscape - sketch - watercolor - cyberpunk - pop_art

includeRaiReason boolean

Whether to include the reason why generated images are filtered

isProductImage boolean

Whether use self background editing for product images.

controlNetConfig object (ControlNetConfig)

Configurations for ControlNet conditions.

imageOutputOptions
(deprecated)
object (ImageOutputOptions)

Output configuration.

outputOptions object (ImageOutputOptions)
upscaleConfig object (UpscaleConfig)

Configurations for upscaling API.

editConfig object (EditConfig)

Configurations for editing API (imagegeneration@{003, 004})

editConfigV6 object (EditConfigV6)

Configurations for editing API for imagegeneration@006

editMode enum (EditMode)

Configurations for edit mode in imagen 3 capability.

language string

Language which the prompt language is in The supported values are: - auto (Autodetect language) - en (English) - ko (Korean) - ja (Japanese) - hi (Hindi)

includeSafetyAttributes boolean

Whether to include the safety attributes scores for both input and output.

modelVariant string

The size variant of the model. Only supported in imagegeneration@004 for now. enum: - large - medium - v1_large - v1_1 - v1_1_turbo

addWatermark boolean

Whether to add SynthID watermark to generated images. Default value: false.

genSelfieConfig object (GenSelfieConfig)

Configurations for GenSelfie API.

showRaiErrorCodes boolean

Show rai error codes instead of messgaes

enhancePrompt boolean

Whether to use the new prompt rewriting logic.

JSON representation
{
  "sampleCount": integer,
  "sampleImageSize": string,
  "storageUri": string,
  "negativePrompt": string,
  "seed": integer,
  "mode": string,
  "model": string,
  "aspectRatio": string,
  "guidanceScale": number,
  "enablePersonFaceFilter": boolean,
  "disablePersonFace": boolean,
  "safetySetting": string,
  "raiLevel": integer,
  "enableChildFilter": boolean,
  "disableChild": boolean,
  "personGeneration": string,
  "sampleImageStyle": string,
  "includeRaiReason": boolean,
  "isProductImage": boolean,
  "controlNetConfig": {
    object (ControlNetConfig)
  },
  "imageOutputOptions": {
    object (ImageOutputOptions)
  },
  "outputOptions": {
    object (ImageOutputOptions)
  },
  "upscaleConfig": {
    object (UpscaleConfig)
  },
  "editConfig": {
    object (EditConfig)
  },
  "editConfigV6": {
    object (EditConfigV6)
  },
  "editMode": enum (EditMode),
  "language": string,
  "includeSafetyAttributes": boolean,
  "modelVariant": string,
  "addWatermark": boolean,
  "genSelfieConfig": {
    object (GenSelfieConfig)
  },
  "showRaiErrorCodes": boolean,
  "enhancePrompt": boolean
}