Void Video Inpainting Mask

What you can set

• PromptRequired

  Text

  Text description of the desired background after object removal.

• Mask video

  Upload a video

  URL of a mask video for the removal target. For best results this should be a VOID-style quadmask video with 4 grayscale values: 0=object to remove, 63=overlap,

• VideoRequired

  Upload a video

  URL of the input video containing the object to remove.

• Mask prompt

  Text

  Text description of what should be masked in the input video, such as the object or person to remove. Used to generate a temporary mask video with SAM-3 when `q

• Negative prompt

  Text

  Negative prompt to guide generation away from undesired outputs.

• Enable pass2 refinement

  On or off

  Run VOID Pass 2 warped-noise refinement after Pass 1. This is slower but can improve temporal consistency on longer clips.

• Guidance scale

  Number from 0 to 20

  Classifier-free guidance scale.

• Num frames

  Number from 1 to 197

  Temporal window size for inference. The backend snaps this to the nearest CogVideoX-safe value that works with temporal compression and patching. Valid outputs

• Steps

  Number from 1 to 50

  Number of denoising steps. Higher values improve quality but increase latency.

• Seed

  Number, repeats a result

  Random seed for reproducibility.

• Strength

  Number from 0 to 1

  Denoising strength. 1.0 means full denoising.