Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.comfy.org/llms.txt

Use this file to discover all available pages before exploring further.

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub
The VOIDInpaintConditioning node prepares the conditioning data needed for inpainting with CogVideoX models. It takes a source video and a preprocessed quadmask, encodes them through the VAE, and combines them into a 32-channel conditioning signal that the model uses to fill in the masked areas.

Inputs

ParameterData TypeRequiredRangeDescription
positiveCONDITIONINGYes-The positive conditioning to be augmented with the inpainting latent information
negativeCONDITIONINGYes-The negative conditioning to be augmented with the inpainting latent information
vaeVAEYes-The VAE model used to encode the mask and masked video into latent space
videoIMAGEYes-Source video frames [T, H, W, 3]
quadmaskMASKYes-Preprocessed quadmask from VOIDQuadmaskPreprocess [T, H, W]
widthINTYes16 to MAX_RESOLUTION (step: 8)The width to resize the video and mask to (default: 672)
heightINTYes16 to MAX_RESOLUTION (step: 8)The height to resize the video and mask to (default: 384)
lengthINTYes1 to MAX_RESOLUTION (step: 1)Number of pixel frames to process. For CogVideoX-Fun-V1.5 (patch_size_t=2), latent_t must be even — lengths that produce odd latent_t are rounded down (e.g. 49 → 45) (default: 45)
batch_sizeINTYes1 to 64The batch size for the output noise latent (default: 1)

Outputs

Output NameData TypeDescription
positiveCONDITIONINGThe positive conditioning with the inpainting latent information added
negativeCONDITIONINGThe negative conditioning with the inpainting latent information added
latentLATENTA zero-filled noise latent tensor with shape [batch_size, 16, latent_t, latent_h, latent_w]

Source fingerprint (SHA-256): 47c40f8bb7527bc28178f3ad78e7bfb579e07d42efd0398d5760335c6b5b3c44