Generate video response.
The generates samples.
raiMediaFilteredCountinteger
Returns if any videos were filtered due to RAI policies.
raiMediaFilteredReasons[]string
Returns rai failure reasons if any.
| JSON representation |
|---|
{
"generatedSamples": [
{
object ( |
Media
Media.
Image
Image.
encodingstring
Image encoding, encoded as "image/png" or "image/jpg".
RAI scores for generated image.
RAI info for image.
Semantic filter info for image.
textstring
Text/Expanded text input for imagen.
Image size. The size of the image. Can be self reported, or computed from the image bytes.
contentUnion type
content can be only one of the following:Raw bytes.
A base64-encoded string.
uristring
Path to another storage (typically Google Cloud Storage).
| JSON representation |
|---|
{ "encoding": string, "imageRaiScores": { object ( |
ImageRAIScores
RAI scores for generated image returned.
agileWatermarkDetectionScorenumber
Agile watermark score for image.
| JSON representation |
|---|
{ "agileWatermarkDetectionScore": number } |
RaiInfo
Next id: 6
raiCategories[]string
List of rai categories' information to return
scores[]number
List of rai scores mapping to the rai categories. Rounded to 1 decimal place.
blockedEntities[]string
List of blocked entities from the blocklist if it is detected.
modelNamestring
The model name used to indexing into the RaiFilterConfig map. Would either be one of imagegeneration@002-006, imagen-3.0-... api endpoint names, or internal names used for mapping to different filter configs (genselfie, ai_watermark) than its api endpoint.
| JSON representation |
|---|
{ "raiCategories": [ string ], "scores": [ number ], "blockedEntities": [ string ], "modelName": string } |
SemanticFilterResponse
passedSemanticFilterboolean
This response is added when semantic filter config is turned on in EditConfig. It reports if this image is passed semantic filter response. If passedSemanticFilter is false, the bounding box information will be populated for user to check what caused the semantic filter to fail.
Class labels of the bounding boxes that failed the semantic filtering. Bounding box coordinates.
| JSON representation |
|---|
{
"passedSemanticFilter": boolean,
"namedBoundingBoxes": [
{
object ( |
NamedBoundingBox
x1number
x2number
y1number
y2number
classes[]string
entities[]string
scores[]number
| JSON representation |
|---|
{ "x1": number, "x2": number, "y1": number, "y2": number, "classes": [ string ], "entities": [ string ], "scores": [ number ] } |
ImageSize
Image size.
widthinteger
heightinteger
channelsinteger
| JSON representation |
|---|
{ "width": integer, "height": integer, "channels": integer } |
Video
Video
encodingstring
Video encoding, for example "video/mp4".
textstring
Text/Expanded text input for Help Me Write.
contentUnion type
content can be only one of the following:Raw bytes.
A base64-encoded string.
uristring
Path to another storage (typically Google Cloud Storage).
encodedVideostring
Base 64 encoded video bytes.
| JSON representation |
|---|
{ "encoding": string, "text": string, // content "video": string, "uri": string, "encodedVideo": string // Union type } |