Inputs
| Parameter | Description | Data Type | Required | Range |
|---|---|---|---|---|
positive | The positive conditioning to be augmented with the inpainting latent information | CONDITIONING | Yes | - |
negative | The negative conditioning to be augmented with the inpainting latent information | CONDITIONING | Yes | - |
vae | The VAE model used to encode the mask and masked video into latent space | VAE | Yes | - |
video | Source video frames [T, H, W, 3] | IMAGE | Yes | - |
quadmask | Preprocessed quadmask from VOIDQuadmaskPreprocess [T, H, W] | MASK | Yes | - |
width | The width to resize the video and mask to (default: 672) | INT | Yes | 16 to MAX_RESOLUTION (step: 8) |
height | The height to resize the video and mask to (default: 384) | INT | Yes | 16 to MAX_RESOLUTION (step: 8) |
length | 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) | INT | Yes | 1 to MAX_RESOLUTION (step: 1) |
batch_size | The batch size for the output noise latent (default: 1) | INT | Yes | 1 to 64 |
Outputs
| Output Name | Description | Data Type |
|---|---|---|
positive | The positive conditioning with the inpainting latent information added | CONDITIONING |
negative | The negative conditioning with the inpainting latent information added | CONDITIONING |
latent | A zero-filled noise latent tensor with shape [batch_size, 16, latent_t, latent_h, latent_w] | 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):
47c40f8bb7527bc28178f3ad78e7bfb579e07d42efd0398d5760335c6b5b3c44