Sam 3 | Image to 3D

fal-ai/sam-3/3d-body

SAM 3D allows for accurate 3D reconstruction of human body shape and position from a single image.

Inference

Commercial use

Schema

LLMs

Playground API

About

Reconstruct 3D human meshes from an image.

1. Calling the API#

Install the client#

The client provides a convenient way to interact with the model API.

npm install --save @fal-ai/client

Migrate to @fal-ai/client

The @fal-ai/serverless-client package has been deprecated in favor of @fal-ai/client. Please check the migration guide for more information.

Setup your API Key#

Set FAL_KEY as an environment variable in your runtime.

export FAL_KEY="YOUR_API_KEY"

Submit a request#

The client API handles the API submit protocol. It will handle the request status updates and return the result when the request is completed.

import { fal } from "@fal-ai/client";

const result = await fal.subscribe("fal-ai/sam-3/3d-body", {
  input: {
    image_url: "https://v3b.fal.media/files/b/0a8439f8/E8gEXWsl2C-Euo4dGayzi_An_zyCCnSaytVklh_99sSYt4Z4Hh5e3s7VnNlx5JfN5KuC0j_bnq1AP9JfRoAmOQz5TP0DdCYMk4796Gloe5no1vvpoqhD-p3kE.jpeg"
  },
  logs: true,
  onQueueUpdate: (update) => {
    if (update.status === "IN_PROGRESS") {
      update.logs.map((log) => log.message).forEach(console.log);
    }
  },
});
console.log(result.data);
console.log(result.requestId);

2. Authentication#

The API uses an API Key for authentication. It is recommended you set the FAL_KEY environment variable in your runtime when possible.

API Key#

In case your app is running in an environment where you cannot set environment variables, you can set the API Key manually as a client configuration.

import { fal } from "@fal-ai/client";

fal.config({
  credentials: "YOUR_FAL_KEY"
});

Protect your API Key

When running code on the client-side (e.g. in a browser, mobile app or GUI applications), make sure to not expose your FAL_KEY. Instead, use a server-side proxy to make requests to the API. For more information, check out our server-side integration guide.

3. Queue#

Long-running requests

For long-running requests, such as training jobs or models with slower inference times, it is recommended to check the Queue status and rely on Webhooks instead of blocking while waiting for the result.

Submit a request#

The client API provides a convenient way to submit requests to the model.

import { fal } from "@fal-ai/client";

const { request_id } = await fal.queue.submit("fal-ai/sam-3/3d-body", {
  input: {
    image_url: "https://v3b.fal.media/files/b/0a8439f8/E8gEXWsl2C-Euo4dGayzi_An_zyCCnSaytVklh_99sSYt4Z4Hh5e3s7VnNlx5JfN5KuC0j_bnq1AP9JfRoAmOQz5TP0DdCYMk4796Gloe5no1vvpoqhD-p3kE.jpeg"
  },
  webhookUrl: "https://optional.webhook.url/for/results",
});

Fetch request status#

You can fetch the status of a request to check if it is completed or still in progress.

import { fal } from "@fal-ai/client";

const status = await fal.queue.status("fal-ai/sam-3/3d-body", {
  requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b",
  logs: true,
});

Get the result#

Once the request is completed, you can fetch the result. See the Output Schema for the expected result format.

import { fal } from "@fal-ai/client";

const result = await fal.queue.result("fal-ai/sam-3/3d-body", {
  requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b"
});
console.log(result.data);
console.log(result.requestId);

4. Files#

Some attributes in the API accept file URLs as input. Whenever that's the case you can pass your own URL or a Base64 data URI.

Data URI (base64)#

You can pass a Base64 data URI as a file input. The API will handle the file decoding for you. Keep in mind that for large files, this alternative although convenient can impact the request performance.

Hosted files (URL)#

You can also pass your own URLs as long as they are publicly accessible. Be aware that some hosts might block cross-site requests, rate-limit, or consider the request as a bot.

Uploading files#

We provide a convenient file storage that allows you to upload files and use them in your requests. You can upload files using the client API and use the returned URL in your requests.

import { fal } from "@fal-ai/client";

const file = new File(["Hello, World!"], "hello.txt", { type: "text/plain" });
const url = await fal.storage.upload(file);

Auto uploads

The client will auto-upload the file for you if you pass a binary object (e.g. File, Data).

Read more about file handling in our file upload guide.

5. Schema#

Input#

image_url string* required

URL of the image containing humans

mask_url string

Optional URL of a binary mask image (white=person, black=background). When provided, skips auto human detection and uses this mask instead. Bbox is auto-computed from the mask.

export_meshes boolean

Export individual mesh files (.ply) per person Default value: true

include_3d_keypoints boolean

Include 3D keypoint markers (spheres) in the GLB mesh for visualization Default value: true

{
  "image_url": "https://v3b.fal.media/files/b/0a8439f8/E8gEXWsl2C-Euo4dGayzi_An_zyCCnSaytVklh_99sSYt4Z4Hh5e3s7VnNlx5JfN5KuC0j_bnq1AP9JfRoAmOQz5TP0DdCYMk4796Gloe5no1vvpoqhD-p3kE.jpeg",
  "export_meshes": true,
  "include_3d_keypoints": true
}

Output#

model_glb File* required

3D body mesh in GLB format with optional 3D keypoint markers

visualization File* required

Combined visualization image (original + keypoints + mesh + side view)

meshes list<File>

Individual mesh files (.ply), one per detected person (when export_meshes=True)

metadata SAM3DBodyMetadata* required

Structured metadata including keypoints and camera parameters

{
  "model_glb": "https://v3b.fal.media/files/b/0a8439f9/5LVt3C2YesqnQzg-CxPpu_combined_bodies.glb",
  "visualization": {
    "url": "",
    "content_type": "image/png",
    "file_name": "z9RV14K95DvU.png",
    "file_size": 4404019
  },
  "meshes": [
    {
      "url": "",
      "content_type": "image/png",
      "file_name": "z9RV14K95DvU.png",
      "file_size": 4404019
    }
  ],
  "metadata": {
    "people": [
      {}
    ]
  }
}

Other types#

SAM3DObjectMetadata#

object_index integer* required

Index of the object in the scene

scale list<list<float>>

Scale factors [sx, sy, sz]

rotation list<list<float>>

Rotation quaternion [x, y, z, w]

translation list<list<float>>

Translation [tx, ty, tz]

camera_pose list<list<float>>

Camera pose matrix

BoxPrompt#

x_min integer

X Min Coordinate of the box

y_min integer

Y Min Coordinate of the box

x_max integer

X Max Coordinate of the box

y_max integer

Y Max Coordinate of the box

object_id integer

Optional object identifier. Boxes sharing an object id refine the same object.

frame_index integer

The frame index to interact with.

PointPromptBase#

x integer

X Coordinate of the prompt

y integer

Y Coordinate of the prompt

label Enum

1 for foreground, 0 for background

Possible enum values: 0, 1

object_id integer

Optional object identifier. Prompts sharing an object id refine the same object.

File#

url string* required

The URL where the file can be downloaded from.

content_type string

The mime type of the file.

file_name string

The name of the file. It will be auto-generated if not provided.

file_size integer

The size of the file in bytes.

Image#

url string* required

The URL where the file can be downloaded from.

content_type string

The mime type of the file.

file_name string

The name of the file. It will be auto-generated if not provided.

file_size integer

The size of the file in bytes.

width integer

The width of the image in pixels.

height integer

The height of the image in pixels.

BoxPromptBase#

x_min integer

X Min Coordinate of the box

y_min integer

Y Min Coordinate of the box

x_max integer

X Max Coordinate of the box

y_max integer

Y Max Coordinate of the box

object_id integer

Optional object identifier. Boxes sharing an object id refine the same object.

SAM3DBodyMetadata#

num_people integer* required

Number of people detected

people list<SAM3DBodyPersonMetadata>* required

Per-person metadata

MaskMetadata#

index integer* required

Index of the mask inside the model output.

score float

Score for this mask.

box list<float>

Bounding box for the mask in normalized cxcywh coordinates.

PointPrompt#

x integer

X Coordinate of the prompt

y integer

Y Coordinate of the prompt

label Enum

1 for foreground, 0 for background

Possible enum values: 0, 1

object_id integer

Optional object identifier. Prompts sharing an object id refine the same object.

frame_index integer

The frame index to interact with.

SAM3DBodyPersonMetadata#

person_id integer* required

Index of the person in the scene

bbox list<float>* required

Bounding box [x_min, y_min, x_max, y_max]

focal_length float* required

Estimated focal length

pred_cam_t list<float>* required

Predicted camera translation [tx, ty, tz]

keypoints_2d list<list<float>>* required

2D keypoints [[x, y], ...] - 70 body keypoints

keypoints_3d list<list<float>>

3D keypoints [[x, y, z], ...] - 70 body keypoints in camera space

SAM3DBodyAlignmentInfo#

person_id integer* required

Index of the person

scale_factor float* required

Scale factor applied for alignment

translation list<float>* required

Translation [tx, ty, tz]

focal_length float* required

Focal length used

target_points_count integer* required

Number of target points for alignment

cropped_vertices_count integer* required

Number of cropped vertices

Sam 3 Image to 3D

Table of contents

1. Calling the API

2. Authentication

3. Queue

4. Files

5. Schema

About

1. Calling the API#

Install the client#

Migrate to @fal-ai/client

Setup your API Key#

Submit a request#

2. Authentication#

API Key#

Protect your API Key

3. Queue#

Long-running requests

Submit a request#

Fetch request status#

Get the result#

4. Files#

Data URI (base64)#

Hosted files (URL)#

Uploading files#

Auto uploads

5. Schema#

Input#

Output#

Other types#

SAM3DObjectMetadata#

BoxPrompt#

PointPromptBase#

File#

Image#

BoxPromptBase#

SAM3DBodyMetadata#

MaskMetadata#

PointPrompt#

SAM3DBodyPersonMetadata#

SAM3DBodyAlignmentInfo#

Related Models