Sam 3d Objects

Playground

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.

Features

SAM 3D Objects (Image-to-3D with Optional Mask)

wavespeed-ai/sam-3d-objects is an advanced SAM-powered 3D object generation model that converts images into detailed 3D assets, with optional mask-based segmentation to isolate the target object for cleaner geometry and more stable reconstruction. Built for production with a ready-to-use REST inference API, best performance, no cold starts, and simple pay-per-run pricing.

🌟 Why it stands out

Mask-guided control (optional): isolate the object from cluttered backgrounds for cleaner 3D results.
Strong reconstruction stability: designed for consistent outputs in real production workflows.
Fast iteration loop: generate, tweak mask, re-run—ideal for asset refinement.
API-first: easy to integrate into 3D pipelines for ecommerce, games, and content tools.

⚙️ Capabilities

Image-to-3D object reconstruction
Optional mask-based segmentation for precise foreground extraction
Produces 3D assets suitable for downstream editing and refinement (format depends on endpoint configuration)
Works best for single-object images with clear outlines and minimal occlusion

💰 Pricing

$0.02 per run

✅ Best use cases

Rapid 3D asset creation for ecommerce visualization
Fast prototyping for games / XR / virtual worlds
Converting product photos into 3D models for catalogs and configurators
Segmentation-guided reconstruction when backgrounds are complex

🧠 Tips for best results

Use single, centered object images with good lighting and sharp edges.
If you provide a mask, ensure it matches the input image size and framing exactly.
Avoid heavy occlusions (hands covering objects, overlapping items) for best geometry.

More 3D Model Recommendations

hyper3d/rodin-v2 — Image to 3D — Generate high-quality 3D models from a single image with production-ready performance for fast 3D asset creation.
hyper3d/rodin-v2 — Text to 3D — Turn text prompts into detailed 3D objects for rapid prototyping and scalable concept-to-asset workflows.
tripo3d/v2.5 — Image to 3D — Convert images into clean, edit-friendly 3D models with strong shape fidelity for ecommerce, games, and 3D pipelines.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result


# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/sam-3d-objects" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"

Parameters

Task Submission Parameters

Request Parameters

Parameter	Type	Required	Default	Range	Description
image	string	Yes		-	Input image URL for 3D object generation.
prompt	string	No		-	Text prompt to guide 3D object generation.
mask_images	array	No	-	-	Optional array of mask image URLs for specific region processing.

Response Parameters

Parameter	Type	Description
code	integer	HTTP status code (e.g., 200 for success)
message	string	Status message (e.g., “success”)
data.id	string	Unique identifier for the prediction, Task Id
data.model	string	Model ID used for the prediction
data.outputs	array	Array of URLs to the generated content (empty when status is not `completed`)
data.urls	object	Object containing related API endpoints
data.urls.get	string	URL to retrieve the prediction result
data.has_nsfw_contents	array	Array of boolean values indicating NSFW detection for each output
data.status	string	Status of the task: `created`, `processing`, `completed`, or `failed`
data.created_at	string	ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.error	string	Error message (empty if no error occurred)
data.timings	object	Object containing timing details
data.timings.inference	integer	Inference time in milliseconds

Result Request Parameters

Parameter	Type	Required	Default	Description
id	string	Yes	-	Task ID

Result Response Parameters

Parameter	Type	Description
code	integer	HTTP status code (e.g., 200 for success)
message	string	Status message (e.g., “success”)
data	object	The prediction data object containing all details
data.id	string	Unique identifier for the prediction, the ID of the prediction to get
data.model	string	Model ID used for the prediction
data.outputs	string	Array of URLs to the generated content (empty when status is not completed).
data.urls	object	Object containing related API endpoints
data.urls.get	string	URL to retrieve the prediction result
data.status	string	Status of the task: `created`, `processing`, `completed`, or `failed`
data.created_at	string	ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.error	string	Error message (empty if no error occurred)
data.timings	object	Object containing timing details
data.timings.inference	integer	Inference time in milliseconds

Sam 3d Body Scail