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 WanVaceToVideo node processes video conditioning data for video generation models. It takes positive and negative conditioning inputs along with video control data and prepares latent representations for video generation. The node handles video upscaling, masking, and VAE encoding to create the appropriate conditioning structure for video models.

Inputs

ParameterData TypeRequiredRangeDescription
positiveCONDITIONINGYes-Positive conditioning input for guiding the generation
negativeCONDITIONINGYes-Negative conditioning input for guiding the generation
vaeVAEYes-VAE model used for encoding images and video frames
widthINTYes16 to MAX_RESOLUTIONOutput video width in pixels (default: 832, step: 16)
heightINTYes16 to MAX_RESOLUTIONOutput video height in pixels (default: 480, step: 16)
lengthINTYes1 to MAX_RESOLUTIONNumber of frames in the video (default: 81, step: 4)
batch_sizeINTYes1 to 4096Number of videos to generate simultaneously (default: 1)
strengthFLOATYes0.0 to 1000.0Control strength for video conditioning (default: 1.0, step: 0.01)
control_videoIMAGENo-Optional input video for control conditioning
control_masksMASKNo-Optional masks for controlling which parts of the video to modify
reference_imageIMAGENo-Optional reference image for additional conditioning
Note: When control_video is provided, it will be upscaled to match the specified width and height. If control_masks are provided, they must match the dimensions of the control video. The reference_image is encoded through the VAE and prepended to the latent sequence when provided.

Outputs

Output NameData TypeDescription
positiveCONDITIONINGPositive conditioning with video control data applied
negativeCONDITIONINGNegative conditioning with video control data applied
latentLATENTEmpty latent tensor ready for video generation
trim_latentINTNumber of latent frames to trim when reference image is used