Seedance 2.0 SCONTO 15% | Crea nel Video Generator →
Object Detection and Segmentation

Object Detection and Segmentation

Detect, identify, and segment objects in images and videos with AI models on WaveSpeed

La nostra selezione

wavespeed-ai/moondream3-preview/point
image-to-text

wavespeed-ai/moondream3-preview/point

Moondream3 Point finds objects in images and returns precise coordinate points for computer vision tasks, enabling accurate point localization. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Tutti i modelli

10 modelli
wavespeed-ai/moondream3-preview/point
image-to-text

wavespeed-ai/moondream3-preview/point

Moondream3 Point finds objects in images and returns precise coordinate points for computer vision tasks, enabling accurate point localization. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

wavespeed-ai/moondream3-preview/detect
image-to-text

wavespeed-ai/moondream3-preview/detect

Moondream3 Detect: Precise object bounding boxes in images for accurate computer vision localization. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

wavespeed-ai/sam-3d-body
image-to-3d

wavespeed-ai/sam-3d-body

Advanced SAM 3D body generation model for creating detailed 3D human body models from images with optional mask-based segmentation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

wavespeed-ai/sam-3d-objects
image-to-3d

wavespeed-ai/sam-3d-objects

Advanced SAM 3D objects generation model for creating detailed 3D object models from images with text prompts and optional mask-based segmentation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

wavespeed-ai/sam3-video
video-to-video

wavespeed-ai/sam3-video

SAM3 Video is a unified foundation model for prompt-based video segmentation. Provide text, point, box, or mask prompts and the model segments and tracks targets across frames with strong temporal consistency. Supports concept-level (“segment anything with concepts”) and multi-object masks for editing, analytics, and VFX. Ready-to-use REST inference API with fast response, no cold starts, and affordable pricing.

wavespeed-ai/sam3-image
image-to-image

wavespeed-ai/sam3-image

SAM 3 is a unified foundation model for promptable image segmentation using text, points, or boxes to detect and segment objects. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

wavespeed-ai/sam3-video-rle
video-to-text

wavespeed-ai/sam3-video-rle

SAM 3 Video RLE is a unified foundation model for prompt-based segmentation in video. Track and segment objects across frames using text, points, or boxes, returning RLE encoded masks for efficient processing. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

wavespeed-ai/sam3-image-rle
image-to-text

wavespeed-ai/sam3-image-rle

SAM 3 RLE is a unified foundation model for promptable image segmentation using text, points, or boxes to detect and segment objects. Returns RLE (Run-Length Encoding) encoded masks for efficient storage and processing. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

bria/embed-product
image-to-image

bria/embed-product

Bria Embed Product seamlessly integrates product images into scene backgrounds with natural lighting and perspective matching. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

wavespeed-ai/void-video-inpainting/mask
video-to-video

wavespeed-ai/void-video-inpainting/mask

VOID Video Inpainting removes objects from videos using mask-guided inpainting. Supports quad-mask or auto-generated SAM-3 masks, optional Pass 2 refinement for temporal consistency, adjustable denoising steps, guidance scale, and temporal window size. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

API Object Detection and Segmentation — prezzi e prestazioni

Esegui qualsiasi modello della collezione Object Detection and Segmentation tramite una singola API REST. Paga a generazione — senza abbonamenti né minimi — con latenza ai vertici del settore su un'infrastruttura con uptime del 99,9%.

Perché eseguire Object Detection and Segmentation su WaveSpeedAI

Prezzi trasparenti

Prezzo per chiamata per ogni modello Object Detection and Segmentation. Il prezzo è indicato nella pagina di ogni modello — senza costi di piattaforma aggiuntivi.

Ottimizzato per bassa latenza

La maggior parte dei modelli immagine Object Detection and Segmentation si completa in meno di 2 secondi. I modelli video e 3D sono diverse volte più veloci delle alternative self-hosted.

Uptime 99,9%

Failover multi-regione e tentativi automatici tengono online il tuo traffico di produzione — anche durante interruzioni del provider.

Domande frequenti

Quanto costa l'API di Object Detection and Segmentation?+

Ogni modello ha il proprio prezzo per chiamata indicato nella pagina del modello. Fatturiamo per generazione riuscita, senza abbonamenti né minimi.

Quanto sono veloci i modelli Object Detection and Segmentation su WaveSpeedAI?+

I modelli immagine di questa collezione tipicamente si completano in meno di 2 secondi. I modelli video e 3D dipendono da durata e risoluzione, ma sono di solito diverse volte più veloci delle esecuzioni self-hosted.

Posso provare l'API senza carta di credito?+

Sì — ogni account riceve $1 di crediti gratuiti alla registrazione, sufficienti per provare la maggior parte dei modelli Object Detection and Segmentation senza carta di credito.

Ci sono limiti di velocità?+

Gli account standard hanno limiti generosi di job concorrenti. I piani Enterprise offrono RPM personalizzato, concurrency più alta e capacità dedicata — contatta il commerciale per i dettagli.