Quad Mask Video Urlisteğe bağlı
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, 127=affected region, 255=background to keep. A simple binary mask (0=remove, 255=keep) also works. If omitted, the app will generate a temporary mask video from `mask_prompt` using the SAM-3 video endpoint and convert it to a quadmask automatically.
Mask Promptisteğe bağlı
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 `quad_mask_video_url` is not provided.
Enable Pass2 Refinementisteğe bağlı
Run VOID Pass 2 warped-noise refinement after Pass 1. This is slower but can improve temporal consistency on longer clips.
Negative Promptisteğe bağlı
Negative prompt to guide generation away from undesired outputs.
Num Inference Stepsisteğe bağlı
Number of denoising steps. Higher values improve quality but increase latency.
Guidance Scaleisteğe bağlı
Classifier-free guidance scale.
Strengthisteğe bağlı
Denoising strength. 1.0 means full denoising.
Seedisteğe bağlı
Random seed for reproducibility.
Num Framesisteğe bağlı
Temporal window size for inference. The backend snaps this to the nearest CogVideoX-safe value that works with temporal compression and patching. Valid outputs are 69, 77, 85, ..., 197.
Enable Safety Checkeristeğe bağlı
Enable content safety checking on the output.
