Image to Image — SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks.

≈ 4.481 kredi/üretim~2 sn

Ayarlar

Image Urlzorunlu

URL of the image to be segmented

Text Promptisteğe bağlı

[DEPRECATED] Use 'prompt' instead. Kept for backward compatibility.

Point Promptsisteğe bağlı

List of point prompts

Box Promptsisteğe bağlı

Box prompt coordinates (x_min, y_min, x_max, y_max). Multiple boxes supported - use object_id to group boxes for the same object or leave empty for separate objects.

Apply Maskisteğe bağlı

Apply the mask on the image.

Output Formatisteğe bağlı

The format of the generated image.

Return Multiple Masksisteğe bağlı

If True, upload and return multiple generated masks as defined by `max_masks`.

Max Masksisteğe bağlı

Maximum number of masks to return when `return_multiple_masks` is enabled.

Include Scoresisteğe bağlı

Whether to include mask confidence scores.

Include Boxesisteğe bağlı

Whether to include bounding boxes for each mask (when available).

Üretmek için giriş yap

Modeli inceleyebilirsin; üretim için hesabınla giriş yapman gerekiyor.

Giriş yap