Skip to main content
The WanCameraEmbedding node generates camera trajectory embeddings using Plücker embeddings based on camera motion parameters. It creates a sequence of camera poses that simulate different camera movements and converts them into embedding tensors suitable for video generation pipelines.

Inputs

ParameterDescriptionData TypeRequiredRange
camera_poseThe type of camera movement to simulate (default: “Static”)COMBOYes”Static"
"Pan Up"
"Pan Down"
"Pan Left"
"Pan Right"
"Zoom In"
"Zoom Out"
"Anti Clockwise (ACW)"
"ClockWise (CW)“
widthThe width of the output in pixels (default: 832, step: 16)INTYes16 to MAX_RESOLUTION
heightThe height of the output in pixels (default: 480, step: 16)INTYes16 to MAX_RESOLUTION
lengthThe length of the camera trajectory sequence (default: 81, step: 4)INTYes1 to MAX_RESOLUTION
speedThe speed of the camera movement (default: 1.0, step: 0.1)FLOATNo0.0 to 10.0
fxThe focal length x parameter (default: 0.5, step: 0.000000001)FLOATNo0.0 to 1.0
fyThe focal length y parameter (default: 0.5, step: 0.000000001)FLOATNo0.0 to 1.0
cxThe principal point x coordinate (default: 0.5, step: 0.01)FLOATNo0.0 to 1.0
cyThe principal point y coordinate (default: 0.5, step: 0.01)FLOATNo0.0 to 1.0

Outputs

Output NameDescriptionData Type
camera_embeddingThe generated camera embedding tensor containing the trajectory sequenceTENSOR
widthThe width value that was used for processingINT
heightThe height value that was used for processingINT
lengthThe length value that was used for processingINT
This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

Source fingerprint (SHA-256): 9c13c4504ca58b7623f106eaf07ceb2aef7739a9b9ce24e321445078b1f953c9