Class: Google::Apis::AiplatformV1beta1::CloudAiLargeModelsVisionGenerateVideoExperiments

Inherits:
Object
  • Object
show all
Includes:
Core::Hashable, Core::JsonObjectSupport
Defined in:
lib/google/apis/aiplatform_v1beta1/classes.rb,
lib/google/apis/aiplatform_v1beta1/representations.rb,
lib/google/apis/aiplatform_v1beta1/representations.rb

Overview

Experimental parameters for video generation.

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(**args) ⇒ CloudAiLargeModelsVisionGenerateVideoExperiments

Returns a new instance of CloudAiLargeModelsVisionGenerateVideoExperiments.



88
89
90
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 88

def initialize(**args)
   update!(**args)
end

Instance Attribute Details

#codec ⇒ String

Optional. Video codec to use for output. Corresponds to the JSON property codec

Returns:

  • (String) 


32
33
34
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 32

def codec
  @codec
end

#conditioning_frames ⇒ Array<Google::Apis::AiplatformV1beta1::CloudAiLargeModelsVisionGenerateVideoExperimentsConditioningFrame>

Conditioning frames for veo experimental models ONLY, not to be confused with keyframes (ID:31) in GenerateVideoRequest. Corresponds to the JSON property conditioningFrames

Returns:



38
39
40
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 38

def conditioning_frames
  @conditioning_frames
end

#human_pose ⇒ Google::Apis::AiplatformV1beta1::CloudAiLargeModelsVisionHumanPose

Human pose parameters for Pose Control Corresponds to the JSON property humanPose

Returns:



43
44
45
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 43

def human_pose
  @human_pose
end

#model_name ⇒ String

Model names, as defined in: xyz Corresponds to the JSON property modelName

Returns:

  • (String) 


48
49
50
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 48

def model_name
  @model_name
end

#num_diffusion_steps ⇒ Fixnum

Number of diffusion steps Corresponds to the JSON property numDiffusionSteps

Returns:

  • (Fixnum) 


53
54
55
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 53

def num_diffusion_steps
  @num_diffusion_steps
end

#prompt_inputs ⇒ Google::Apis::AiplatformV1beta1::CloudAiLargeModelsVisionPromptInputs

"Direct" prompting for Experimental Video Generation. These will be sent directly to the LDM without being rewritten. Corresponds to the JSON property promptInputs

Returns:



59
60
61
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 59

def prompt_inputs
  @prompt_inputs
end

#request_origin_tag ⇒ String

Optional tag for tracking the source of this request. Allowed values: "colab", "comfyui", "curl", "flowresearch", "vertexstudio". Unrecognized tags are recorded as "unknown" in metrics. Tags do not affect video generation behavior. Up to 16 characters, ASCII alphanumeric, hyphens, and underscores only. Corresponds to the JSON property requestOriginTag

Returns:

  • (String) 


67
68
69
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 67

def request_origin_tag
  @request_origin_tag
end

#truncate_input_video ⇒ Boolean Also known as: truncate_input_video?

If true (default), truncate input videos that exceed the model's maximum frame count by applying a frame_selection_config to video_file inputs. Set to false to preserve the existing fail-fast behavior. Corresponds to the JSON property truncateInputVideo

Returns:

  • (Boolean) 


74
75
76
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 74

def truncate_input_video
  @truncate_input_video
end

#video_transform_mask_gcs_uri ⇒ String

GCS URI of the grayscale video mask for Differential Diffusion. Maps to sdedit_video_tmax_scale_map Corresponds to the JSON property videoTransformMaskGcsUri

Returns:

  • (String) 


81
82
83
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 81

def video_transform_mask_gcs_uri
  @video_transform_mask_gcs_uri
end

#video_transform_strength ⇒ Float

SDEdit: Scalar noise level (0.0 to 1.0) Maps to sdedit_tmax Corresponds to the JSON property videoTransformStrength

Returns:

  • (Float) 


86
87
88
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 86

def video_transform_strength
  @video_transform_strength
end

Instance Method Details

#update!(**args) ⇒ Object

Update properties of this object



93
94
95
96
97
98
99
100
101
102
103
104
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 93

def update!(**args)
  @codec = args[:codec] if args.key?(:codec)
  @conditioning_frames = args[:conditioning_frames] if args.key?(:conditioning_frames)
  @human_pose = args[:human_pose] if args.key?(:human_pose)
  @model_name = args[:model_name] if args.key?(:model_name)
  @num_diffusion_steps = args[:num_diffusion_steps] if args.key?(:num_diffusion_steps)
  @prompt_inputs = args[:prompt_inputs] if args.key?(:prompt_inputs)
  @request_origin_tag = args[:request_origin_tag] if args.key?(:request_origin_tag)
  @truncate_input_video = args[:truncate_input_video] if args.key?(:truncate_input_video)
  @video_transform_mask_gcs_uri = args[:video_transform_mask_gcs_uri] if args.key?(:video_transform_mask_gcs_uri)
  @video_transform_strength = args[:video_transform_strength] if args.key?(:video_transform_strength)
end