Sam 3d Body
Playground
Try it on WavespeedAI!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.
Features
SAM3 Video (Mask-Guided Video Editing)
wavespeed-ai/sam3-video is an advanced SAM-powered video editing model that applies prompt-based edits with optional mask guidance for cleaner, more controllable results. It’s built for production usage with a ready-to-use REST inference API, strong stability, no cold starts, and duration-based pricing.
🌟 Why it stands out
- SAM-guided masking helps target edits more precisely (especially in cluttered scenes).
- Prompt-driven editing for fast iteration (remove / clean / modify with natural language).
- Optional apply_mask: you can enable mask application for tighter control, or disable it for general edits.
- Production-ready inference: consistent performance and smoother frame-to-frame stability.
⚙️ Capabilities
- Prompt-based video editing
- Optional mask application via apply_mask (mask-guided control over where edits happen)
- Designed to keep edits more consistent across frames (reduced flicker / drifting artifacts)
- Works best for short-to-medium clips with clear subjects and stable motion
💰 Pricing
wavespeed-ai/sam3-video {“total_price”: $max([5, $min([$number(get_duration_v2(video)), 600])]) / 5 * base_price} base price = 0.05
- Duration is clamped to 5–600 seconds
- Billed in 5-second units
- Effective rate: $0.05 per 5s (≈ $0.01 per second)
Reference prices:
- 5s → $0.05
- 10s → $0.10
- 30s → $0.30
- 60s → $0.60
- 120s → $1.20
- 300s → $3.00
- 600s → $6.00
How to use
- Upload the video (or provide a public URL).
- Write a prompt describing the edit (e.g., “remove the person in the background, keep lighting unchanged”).
- Toggle apply_mask if you want mask-guided editing.
- Run the model and download the edited result.
💡 Best Use Cases
- Video object removal and background cleanup
- Short-form content polishing (social clips, ads, product demos)
- Mask-guided edits for busy scenes where precision matters
- Fast creative iteration for editing concepts before heavy post-production
📝 Notes
- Best results: stable footage, clear subject separation, minimal heavy motion blur.
- apply_mask is recommended when you need tighter control over edited regions.
- Very long videos are clamped at 600s for pricing and processing consistency.
More Video Models For you
- wavespeed-ai/video-face-swap — Swap faces in video with natural blending for content creation and creative editing workflows.
- wavespeed-ai/video-head-swap — Replace a subject’s head in video while keeping motion continuity and scene consistency.
- wavespeed-ai/video-eraser — Remove unwanted objects from video with clean inpainting for background cleanup and decluttering.
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-body" \
--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 body generation or segmentation. | |
| mask_image | string | No | - | Optional mask image URL 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 |