Package google.cloud.aiplatform.v1beta1.schema.predict.params

bool

Whether to use AlternateInitConfig

float

Maximum inpainting area below which to consider using AlternateInitConfig

string

The blending mode for background swap. The values can be one of: * alpha-blending

float

The blending factor for background swap blending. Valid range: [0, 1]. Default value: 0

bool

true if ControlNet is enabled.

ControlNetConditionConfig

Configurations for each condition.

float

The weight for the original image. Valid range: [0, 1]. When set to 1.0, the output basically copies the input image. When set to 0.0, the output not respect the input image at all.

string

Currently supported conditions: * cannyEdges * depth

bytes

When the condition map is provided by the user, we will not compute the condition map on our side.

float

The guidance weight for the condition signal. Valid range: [0, 1]. The higher the weight, the model respects the ControlNet condition more. The default value is 1.0 if unspecified.

float

The strength of the ControlNet's effect on each diffusion step. Valid range: [0, 1].

BufferZone

Buffer zone, if provided, must be length 2.

int32

Guidance scale: this controls strength of text guidance. If provided, must be a list of 4 integers representing values during 4 stages of diffusion [fine-grained,...,...,coarse].

bool

Whether to enable clamping mode, which: * Enables the rest of the configurations in EditConfig. * Better preserves unmasked area * Skips model internal dilation so client can fully control this

int32

Number of sampling steps.

float

Gamma: influences how much noise is added during sampling.

int32

Number of sampling steps for sr1 stage.

int32

Number of sampling steps for sr2 stage.

SemanticFilterConfig

NOTE: for experiment use, not production ready. Semantic Filter Config. This config reduces object hallucination on inpainted images. Users can set filter classes and filter entities to filter out generated images that hallucinate undesired objects in the inpainted area. This config is only enabled in Editing config.

bool

Experiment flag to use servo backend.

string

The editing mode that describes the use case for editing. The values can be one of: * inpainting-remove * inpainting-insert * outpainting

AlternateInitConfig

Parameters for AlternateInitConfig

string

Experimental flag for sr version.

string

Experimental flag for base version.

float

Parameter to control embedding scale, range: [0, 1], default: 0.6.

bool

Parameter to enable recompute with BORDER_REPLICATE mode for outpainting image padding.

bool

Parameter to enable post-processing blending for masked editing.

OutpaintingProcessingConfig

Outpainting processing config.

BackgroundSwapProcessingConfig

Background swap processing config.

int32

The number of pixels for the mask to dilate.

float

When during diffusion this pixel dilation takes effect, 1=start, 0=end.

BufferZone

Buffer zone, if provided, must be length 2.

string

The editing mode that describes the use case for editing. The values can be one of: * inpainting-remove * inpainting-insert * outpainting * product-image

float

Parameter to control mask dilation, range: [0, 1], default: 0.03.

int32

Guidance scale: this controls strength of text guidance.

string

Product position: this controls the product position in the returned product editing image. The values can be one of: * reposition - the default behavior in the GPS pipeline * fixed - keeps the product in the same position as in the position as in the input image. This assume input image is square.

MaskMode

Automatic mask generation configuration.

int32

Number of sampling steps for base model.

string

The backend to use for the model. The values can be one of: * experimental * prod

SemanticFilterConfig

Semantic Filter Config. This config reduces object hallucination on inpainted images. Users can set filter classes and filter entities to filter out generated images that hallucinate undesired objects in the inpainted area. This config is only enabled in Editing config.

AlternateInitConfig

Parameters for AlternateInitConfig

OutpaintingProcessingConfig

Outpainting config.

int32

The number of pixels for the mask to dilate.

float

When during diffusion this pixel dilation takes effect, 1=start, 0=end.

int32

Number of pixels to expand the image and mask from the top Value is an integer that has a minimum of 0 and a maximum of 500.

int32

Number of pixels to expand the image and mask from the bottom Value is an integer that has a minimum of 0 and a maximum of 500.

int32

Number of pixels to expand the image and mask from the left Value is an integer that has a minimum of 0 and a maximum of 500.

int32

Number of pixels to expand the image and mask from the right Value is an integer that has a minimum of 0 and a maximum of 500.

int32

Initialization seed per generation sample. len(seeds) should be equal to sample_count.

float

Parameter for identity control. Valid range: [0, 1.0] Default value: 0.9

float

Parameter for structure control. Valid range: [0, 1.0] Default value: 1.0

string

The version for the base model.

bool

Whether to skip detecting and cropping the face in the input image. Default value: false.

int32

Number of sampling steps.

bool

Whether to enable image sharpening post-processing.

float

The threshold for the face detection model. Images with a face detection score below this threshold will be rejected.

string

The criteria to select the face for Gen Selfie. Accepted values: * LARGEST * MOST_CONFIDENT

string

The style for the generated image. Accepted values: * watercolor * hand-drawing * illustration * 3d-character

string

Currently supported: -- image/jpeg -- image/png. Defaults to image/png.

int32

Optional compression quality if encoding in image/jpeg. Valid range is any integer [0, 100]. Defaults to 75.

string

The type of mask to generate from the provided input image. The values can be one of: * background * foreground * semantic

Value

The class IDs to generate masks of using the Semantic Segmenter model. Only numeric class IDs are supported.

Not used if the mask_type value is not semantic.

string

The blending mode for outpainting. The values can be one of: * alpha-blending * pyramid-blending

float

The blending factor for outpainting blending. Valid range: [0, 1]. Default value: 0

bool

Parameter to enable recompute with BORDER_REPLICATE mode for outpainting image padding.

ExpansionConfig

Fix to one-side expansion issue by adding padding to the image and mask in the backend server and cropped them out in the post-processing.

string

The MIME type of the output image.

The following values are supported:

• image/jpeg
• image/png

If not set, defaults to image/png.

int32

Specifies the compression quality for JPEG images. Accepted values are in the range [0, 100].

If not set, defaults to 75.

string

Specify object class text names to filter. Any detected object in the masked region bearing anyone of the class names will be checked.

string

Specify object entity ids to filter, similar to filter_classes. The Final filter list is an union of filter classes and filter entities.

string

For outpainting case. Specify object class text names to filter. Any detected object in the masked region bearing anyone of the class names will be checked.

string

For outpainting case. Specify object entity ids to filter, similar to filter_classes. The Final filter list is an union of filter classes and filter entities.

string

For special_init case. Specify object class text names to filter. Any detected object in the masked region bearing anyone of the class names will be checked.

string

For special_init case. Specify object entity ids to filter, similar to filter_classes. The Final filter list is an union of filter classes and filter entities.

bool

Whether to enable semantic filtering mode, which enables the following parameters to apply semantic filter on image editing results.

float

A threshold value to decide what detected boxes should be included in semantic filter checking.

int32

Additional count of samples, expect a value between 0 and 4.

string

A string to specify semantic filter experimental mode. This allows semantic filter to change the default behavior to filter generated images.

float

A detection confidence score threshold to decide which detection boxes are considered as the valid detections for semantic filter checking.

float

For outpainting case. A threshold value to decide what detected boxes should be included in semantic filter checking.

float

For outpainting case. A detection confidence score threshold to decide which detection boxes are considered as the valid detections for semantic filter checking.

float

For special_init case. A threshold value to decide what detected boxes should be included in semantic filter checking.

float

For special_init case. A detection confidence score threshold to decide which detection boxes are considered as the valid detections for semantic filter checking.

bool

Whether to silently truncate inputs longer than the max sequence length. This behavior is enabled by default. If this option is set to false, oversized inputs will lead to an INVALID_ARGUMENT error, similar to other text APIs.

int32

An optional argument for the output embedding's dimensionality. This parameter is only supported by some models, and the supported value range is specific to the requested model. If this parameter is specified for a model that does not support it, or if the specified value is not supported by the model, the request will fail with an INVALID_ARGUMENT error.

bool

Whether to add an image enhancing step before upscaling. It is expected to suppress the noise and JPEG compression artifact from the input image. Default value: false.

bool

NOTE: For experimental use, not production-ready. Whether to speed up upscaling. This option can't be used with high QPS since it lowers the availability of the upscaling API.

string

The factor to which the image will be upscaled. If not specified, the upscale factor will be determined from the longer side of the input image and sampleImageSize. enum: - x2 - x4

float

With a higher image preservation factor, the original image pixels are more respected. The output image is more similar to input image. With a lower image preservation factor, the output image will have be more different from the input image, but maybe with finer details and fewer noises. Only works with: * imagegeneration@003 Valid range: [0, 1.0] Default value: 0.5

int32

The number of videos to generate. If not specified, 1 video is generated.

string

The Google Cloud Storage URI for saving the generated videos. The URI must start with gs:// and point to a bucket or folder. If this field is specified, generated videos are uploaded to the specified location.

int32

The frame rate of the generated videos in frames per second (fps). This value can affect the smoothness of motion in the video. If not specified, a default value appropriate for the model is used.

double

The target duration of the generated videos in seconds. The actual duration of the generated videos may vary slightly. If not specified, a default value appropriate for the model is used.

int32

Seed for random number generation. Providing the same seed with the same input parameters will produce consistent video generation results. If not specified, a random seed is used, resulting in different videos each time. If sample_count is greater than 1, a different random seed is used for each generated video, even if a seed is provided.

string

The aspect ratio of the generated videos. Supported values: * 16:9 (landscape) * 9:16 (portrait)

string

The resolution of the generated videos. Supported values: * 720p * 1080p

string

Controls whether videos of people can be generated, based on age appearance. Supported values: * dont_allow: Prevents generation of videos with people. * allow_adult: Allows generation of videos with people who appear to be adults. * allow_all: Allows generation of videos with people of all ages. If not specified, allow_adult is used.

string

The Cloud Pub/Sub topic to publish video generation progress to. If this field is specified, messages are published to the topic detailing the progress of video generation. The topic must be in the format projects/{project}/topics/{topic}.

string

Things that shouldn't appear in the generated videos. For example: "low quality", "ugly", "deformed".

bool

Deprecated: This field is deprecated and has no effect. Use enhance_prompt instead.

bool

Whether to automatically enhance the prompt before generating videos. If true, the prompt is improved to generate higher quality videos. If prompt enhancement is enabled, providing a seed won't guarantee consistent results. Defaults to true.

bool

Whether to generate audio along with the video. If true, an audio track is generated for the videos. Defaults to true.

string

The compression quality of the generated videos. A lower quality might result in a smaller file size, while a higher quality might result in a better-looking video. Supported values: * optimized: (Default) Optimized for quality and file size. * lossless: Highest quality, larger file size.

OutputOptions

Options for configuring the output image format.

int32

The number of images to generate. Accepted values are in the range [1,4].

If not set, defaults to 1.

string

The Google Cloud Storage location where the generated images are stored.

int32

The random seed for image generation. This avoids randomness in generating the output images.

If a seed value is provided, add_watermark must be set to false.

int32

The number of diffusion steps to run. The higher the number of steps, the higher the quality of the generated image, but the greater the latency.

If not set, defaults to 32.

string

Safety filter level for generated images. The filter blocks images that contain objectionable content.

The following values are supported:

• block-low-and-above: Strongest filtering level, most strict blocking.
• block-medium-and-above: Block some problematic content prompts and responses.
• block-only-high: Reduces the number of requests blocked due to safety filters. May increase objectionable content in generated images.
• block-none: Block very few problematic prompts and responses. Access to this feature is restricted.

If not set, defaults to block_medium_and_above.

string

Controls whether or not faces or people are included in generated images.

The following values are supported:

• dont-allow: Disallow the inclusion of faces or people in generated images.
• allow-adult: Allow generation of adults only.
• allow-all: Allow generation of people of all ages.

If not set, defaults to allow-adult.

bool

Whether to add a watermark to the generated images.

If not set, defaults to true.

bool

Whether to enhance the user-provided prompt internally for models that support it.

If not set, defaults to true.

int32

Number of output images.

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.

string

The gcs bucket where to save the generated images.

string

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

int32

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.

string

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

string

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

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)

float

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)

bool

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

bool

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

int32

bool

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

bool

string

Whether allow to generate person images, and restrict to specific ages. Supported values are: dont_allow (Deprecated. Use allow_none instead.) allow_none allow_adult allow_all

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

bool

Whether to include the reason why generated images are filtered

bool

Whether use self background editing for product images.

ControlNetConfig

Configurations for ControlNet conditions.

ImageOutputOptions

Output configuration.

ImageOutputOptions

UpscaleConfig

Configurations for upscaling API.

EditConfig

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

EditConfigV6

Configurations for editing API for imagegeneration@006

EditMode

Configurations for edit mode in imagen 3 capability.

string

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

bool

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

string

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

bool

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

GenSelfieConfig

Configurations for GenSelfie API.

bool

Show rai error codes instead of messgaes

bool

Whether to use the new prompt rewriting logic.

int32

Number of output text responses.

string

The gcs bucket where to save the generated text responses.

int32

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.

string

Specific output text language. Support lanagues are: - en (default) - de - fr - it - es