> ## 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.

# VOIDInpaintConditioning - ComfyUI Built-in Node Documentation

> The VOIDInpaintConditioning node prepares the conditioning data needed for inpainting with CogVideoX models.

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 (16 channels from the mask + 16 channels from the masked video) that the model uses to fill in the masked areas.

## 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 |

**Note:** Because CogVideoX-Fun-V1.5 uses `patch_size_t=2`, the encoded latent must have an even temporal dimension. If `length` would produce an odd `latent_t`, the node automatically rounds it down to the nearest valid value and logs a warning. Using an odd `latent_t` corrupts the last frame through circular padding, which can cause visible jitter or disappearing subjects near the end of the decoded video.

## 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](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/VOIDInpaintConditioning/en.md)

***

**Source fingerprint (SHA-256):** `885e462c0f17a3e9610146a05ba3b9c879db0112d3961c95a83f63ba2cd511f1`