Meta

Segment Image (Mask2Former)

Universal image segmentation on an Image with a Mask2Former checkpoint. The task setting selects the panoptic, instance or semantic head; the sink resolves one of nine projections of the per-segment result, from [(Segmentation, BoundingBox)] to a count.

Segment Image Everything (SAM 3)

Prompt-free "segment everything" on an Image: a point grid segments every object with no prompt. The sink resolves the projection: mask+box pairs, masks, mask-derived boxes, parallel arrays, a merged Mask, a count, or a colourised Image. Class-agnostic.

Track Objects (SAM 3)

SAM 3 seed-and-propagate video tracker. A detector seeds objects (boxes or masks); SAM 3 memory propagates each object's mask across frames with a stable id. Mask-native resolved oneof: [TrackedSegmentation] (default), tracks, objects, boxes, or ids.

Segment Image (SAM 3)

Concept-prompted open-vocabulary segmentation on an Image. Each noun phrase is segmented and the sink resolves the projection: mask-plus-box pairs, masks, boxes, parallel arrays, a merged Mask, a UInt64 count, or a colourised label Image.

Translate Audio (SeamlessM4T v2)

Downmixes one AudioFrame to mono, resamples to 16 kHz, and runs SeamlessM4T v2 speech-to-text translation into a configured target language, returning a single String; silent or failing audio yields the empty string.

Translate Text (NLLB)

Runs Meta NLLB-200 sequence-to-sequence translation over a String or [String] between two explicit FLORES-200 codes, forcing the target token at decode, and returns a string, string list, or language-tagged record chosen from the resolved downstream port.

Detect Objects (SAM 3)

Exhaustively detects every instance matching a SAM 3 concept phrase in each Image, running comma-separated phrases in order, and projects detections onto the connected output: boxes, geometry, classes, a count, or an overlay. Offline from the bound model.