Video to Video — SAM 3.1 builds comes with Object Multiplex, a shared-memory approach for joint multi-object tracking that delivers faster speeds with larger number of objects tracked.

≈ 8.962 kredi/üretim

Ayarlar

Video Urlzorunlu

The URL of the video to be segmented.

Mask Urlisteğe bağlı

The URL of the mask to be applied initially.

Point Promptsisteğe bağlı

List of point prompts with frame indices.

Box Promptsisteğe bağlı

List of box prompts with optional frame_index.

Apply Maskisteğe bağlı

Apply the mask on the video.

Boundingbox Zipisteğe bağlı

Return per-frame bounding box overlays as a zip archive.

Detection Thresholdisteğe bağlı

Detection confidence threshold (0.0-1.0). Lower = more detections but less precise. Defaults: 0.5 for existing, 0.7 for new objects. Try 0.2-0.3 if text prompts fail.

Frame Indexisteğe bağlı

Frame index used for initial interaction when mask_url is provided.

Max Num Objectsisteğe bağlı

Maximum number of objects to track in the video.

Return Object Rlesisteğe bağlı

Also return every tracked object's own mask in each frame, with an id the object keeps for the whole video. The merged rle is returned as before.

Üretmek için giriş yap

Modeli inceleyebilirsin; üretim için hesabınla giriş yapman gerekiyor.

Giriş yap