You're looking at a specific version of this model. Jump to the model overview.

meta /sam-2-video:33432afd

Input

*file

Input video file path

*string
Shift + Return to add a new line

Click coordinates as '[x,y],[x,y],...'. Determines number of clicks.

string
Shift + Return to add a new line

Click types (1=foreground, 0=background) as '1,1,0,1'. Auto-extends if shorter than coordinates.

Default: "1"

string
Shift + Return to add a new line

Frame indices for clicks as '0,0,150,0'. Auto-extends if shorter than coordinates.

Default: "0"

string
Shift + Return to add a new line

Object labels for clicks as 'person,dog,cat'. Auto-generates if missing or incomplete.

Default: ""

string

Mask type: binary (B&W), highlighted (colored overlay), or greenscreen

Default: "binary"

string

Annotation type: mask only, bounding box only, or both (ignored for binary and greenscreen)

Default: "mask"

Including output_video and 4 more...
boolean

True for video output, False for image sequence

Default: false

integer
(minimum: 1, maximum: 60)

Video output frame rate (ignored for image sequence)

Default: 30

string

Image format for sequence (ignored for video)

Default: "webp"

integer
(minimum: 0, maximum: 100)

JPG/WebP compression quality (0-100, ignored for PNG and video)

Default: 80

integer

Output every Nth frame. 1=all frames, 2=every other, etc.

Default: 1

Output

Generated in