Skip to main content
This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub
The WanPhantomSubjectToVideo node generates video content by processing conditioning inputs and optional reference images. It creates latent representations for video generation and can incorporate visual guidance from input images when provided. The node prepares conditioning data with time-dimensional concatenation for video models and outputs modified conditioning along with generated latent video data.

Inputs

ParameterData TypeRequiredRangeDescription
positiveCONDITIONINGYes-Positive conditioning input for guiding video generation
negativeCONDITIONINGYes-Negative conditioning input to avoid certain characteristics
vaeVAEYes-VAE model for encoding images when provided
widthINTNo16 to MAX_RESOLUTIONOutput video width in pixels (default: 832, must be divisible by 16)
heightINTNo16 to MAX_RESOLUTIONOutput video height in pixels (default: 480, must be divisible by 16)
lengthINTNo1 to MAX_RESOLUTIONNumber of frames in the generated video (default: 81, must be divisible by 4)
batch_sizeINTNo1 to 4096Number of videos to generate simultaneously (default: 1)
imagesIMAGENo-Optional reference images for time-dimensional conditioning
Note: When images are provided, they are automatically upscaled to match the specified width and height, and only the first length frames are used for processing.

Outputs

Output NameData TypeDescription
positiveCONDITIONINGModified positive conditioning with time-dimensional concatenation when images are provided
negative_textCONDITIONINGModified negative conditioning with time-dimensional concatenation when images are provided
negative_img_textCONDITIONINGNegative conditioning with zeroed time-dimensional concatenation when images are provided
latentLATENTGenerated latent video representation with specified dimensions and length