Index
-
GenerateVideoResponse(message) -
Image(message) -
Image.ImageSize(message) -
ImageRAIScores(message) -
Media(message) -
NamedBoundingBox(message) -
RaiInfo(message) -
SemanticFilterResponse(message) -
Video(message)
GenerateVideoResponse
Generate video response.
| Fields | |
|---|---|
generated_samples[]
|
The generates samples. |
rai_media_filtered_count
|
Returns if any videos were filtered due to RAI policies. |
rai_media_filtered_reasons[]
|
Returns rai failure reasons if any. |
Image
Image.
encoding
string
Image encoding, encoded as "image/png" or "image/jpg".
image_rai_scores
RAI scores for generated image.
rai_info
RAI info for image.
semantic_filter_response
Semantic filter info for image.
text
string
Text/Expanded text input for imagen.
image_size
Image size. The size of the image. Can be self reported, or computed from the image bytes.
Union field content
.
content
can be only one of the following:
image
bytes
Raw bytes.
uri
string
Path to another storage (typically Google Cloud Storage).
ImageSize
Image size.
| Fields | |
|---|---|
width
|
|
height
|
|
channels
|
|
ImageRAIScores
RAI scores for generated image returned.
| Fields | |
|---|---|
agile_watermark_detection_score
|
Agile watermark score for image. |
Media
Media.
NamedBoundingBox
| Fields | |
|---|---|
x1
|
|
x2
|
|
y1
|
|
y2
|
|
classes[]
|
|
entities[]
|
|
scores[]
|
|
RaiInfo
Next ID: 6
| Fields | |
|---|---|
rai_categories[]
|
List of rai categories' information to return |
scores[]
|
List of rai scores mapping to the rai categories. Rounded to 1 decimal place. |
blocked_entities[]
|
List of blocked entities from the blocklist if it is detected. |
model_name
|
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. |
SemanticFilterResponse
| Fields | |
|---|---|
passed_semantic_filter
|
This response is added when semantic filter config is turned on in EditConfig. It reports if this image is passed semantic filter response. If passed_semantic_filter is false, the bounding box information will be populated for user to check what caused the semantic filter to fail. |
named_bounding_boxes[]
|
Class labels of the bounding boxes that failed the semantic filtering. Bounding box coordinates. |
Video
Video
encoding
string
Video encoding, for example "video/mp4".
text
string
Text/Expanded text input for Help Me Write.
Union field content
.
content
can be only one of the following:
video
bytes
Raw bytes.
uri
string
Path to another storage (typically Google Cloud Storage).
encoded_video
string
Base 64 encoded video bytes.
