Run time and cost

This model runs on CPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

🎯 JigsawStack Object Detection – Replicate Wrapper

This model wraps the JigsawStack Object Detection API

This model wraps the JigsawStack Speech-to-Text API and leverages the powerful Whisper V3 model to transcribe and optionally translate audio/video files.

Detect and highlight objects in images with high accuracy using JigsawStack’s Object Detection API. This model on Replicate supports generic detection, prompt-based targeting, and optional annotated image output — all powered by a fast and scalable vision backend.

🧠 What It Does

You provide an image (via URL or file storage key), and the model returns: - Detected objects with labels and coordinates - Optionally, an annotated image - Support for prompt-guided detection (e.g., only detect “cat” or “helmet”)

🔑 Inputs

Name	Type	Required	Description
`url`	string	❌ No	Public URL to an image file
`file_store_key`	string	❌ No	Key of an image stored on JigsawStack File Storage
`prompts`	list of strings	❌ No	Optional array of prompts (e.g. `["dog", "car"]`) for targeted detection
`features`	list of enums	❌ No	Features to enable. Options: `object_detection`, `gui`. At least one required
`annotated_image`	boolean	❌ No	If `true`, returns image with bounding boxes drawn
`return_type`	string	❌ No	`url` or `base64` image format (default: `url`)
`api_key`	string	✅ Yes	Your JigsawStack API key

📌 You must provide either url or file_store_key, not both.