Skip to main content
The WanMoveTrackToVideo node prepares conditioning and latent space data for video generation, incorporating optional motion tracking information. It encodes a starting image sequence into a latent representation and can blend in positional data from object tracks to guide the motion in the generated video. The node outputs modified positive and negative conditioning along with an empty latent tensor ready for a video model.

Inputs

ParameterDescriptionData TypeRequiredRange
positiveThe positive conditioning input to be modified.CONDITIONINGYes-
negativeThe negative conditioning input to be modified.CONDITIONINGYes-
vaeThe VAE model used to encode the starting image into the latent space.VAEYes-
tracksOptional motion tracking data containing object paths.TRACKSNo-
strengthStrength of the track conditioning. (default: 1.0)FLOATNo0.0 - 100.0
widthThe width of the output video. Must be divisible by 16. (default: 832)INTNo16 - MAX_RESOLUTION
heightThe height of the output video. Must be divisible by 16. (default: 480)INTNo16 - MAX_RESOLUTION
lengthThe number of frames in the video sequence. (default: 81)INTNo1 - MAX_RESOLUTION
batch_sizeThe batch size for the latent output. (default: 1)INTNo1 - 4096
start_imageThe starting image or image sequence to encode.IMAGEYes-
clip_vision_outputOptional CLIP vision model output to add to the conditioning.CLIPVISIONOUTPUTNo-
Note: The strength parameter only has an effect when tracks are provided. If tracks are not provided or strength is 0.0, the track conditioning is not applied. The start_image is used to create a latent image and mask for the conditioning; if it is not provided, the node only passes through the conditioning and outputs an empty latent.

Outputs

Output NameDescriptionData Type
positiveThe modified positive conditioning, potentially containing concat_latent_image, concat_mask, and clip_vision_output.CONDITIONING
negativeThe modified negative conditioning, potentially containing concat_latent_image, concat_mask, and clip_vision_output.CONDITIONING
latentAn empty latent tensor with dimensions shaped by the batch_size, length, height, and width inputs.LATENT
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): 9dc861c3616a3d92c9dc647e1d227bc1f94d5c74c58eed41ffa8d28b445c9160