Imageutils API

API reference for Imageutils. Remove the background from an image.

Rembg

Endpoint: POST https://fal.run/fal-ai/imageutils/rembg Endpoint ID: fal-ai/imageutils/rembg

Try it in the Playground

Run this model interactively with your own prompts.

Quick Start

Python

import fal_client

def on_queue_update(update):
    if isinstance(update, fal_client.InProgress):
        for log in update.logs:
           print(log["message"])

result = fal_client.subscribe(
    "fal-ai/imageutils/rembg",
    arguments={
        "image_url": "https://storage.googleapis.com/falserverless/model_tests/remove_background/elephant.jpg"
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)

Input Schema

image_url · string · required

Input image url.

sync_mode · boolean · default: "false"

If True, the media will be returned as a data URI and the output data won’t be available in the request history.

crop_to_bbox · boolean · default: "false"

If set to true, the resulting image be cropped to a bounding box around the subject

Output Schema

image · Image · required

Background removed image.

Input Example

{
  "image_url": "https://storage.googleapis.com/falserverless/model_tests/remove_background/elephant.jpg",
  "sync_mode": false,
  "crop_to_bbox": false
}

Output Example

{
  "image": {
    "url": "",
    "content_type": "image/png",
    "file_name": "z9RV14K95DvU.png",
    "file_size": 4404019,
    "width": 1024,
    "height": 1024
  }
}

Depth

Endpoint: POST https://fal.run/fal-ai/imageutils/depth Endpoint ID: fal-ai/imageutils/depth

Try it in the Playground

Run this model interactively with your own prompts.

Quick Start

Python

import fal_client

def on_queue_update(update):
    if isinstance(update, fal_client.InProgress):
        for log in update.logs:
           print(log["message"])

result = fal_client.subscribe(
    "fal-ai/imageutils/depth",
    arguments={
        "image_url": "https://storage.googleapis.com/falserverless/model_tests/remove_background/elephant.jpg"
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)

Input Schema

image_url · string · required

Input image url.

a · float · default: "6.283185307179586"

a Default value: 6.283185307179586

bg_th · float · default: "0.1"

bg_th Default value: 0.1

depth_and_normal · boolean · default: "false"

depth_and_normal

Output Schema

image · Image · required

The depth map.

Input Example

{
  "image_url": "https://storage.googleapis.com/falserverless/model_tests/remove_background/elephant.jpg",
  "a": 6.283185307179586,
  "bg_th": 0.1,
  "depth_and_normal": false
}

Output Example

{
  "image": {
    "url": "",
    "content_type": "image/png",
    "file_name": "z9RV14K95DvU.png",
    "file_size": 4404019,
    "width": 1024,
    "height": 1024
  }
}

Marigold Depth

Endpoint: POST https://fal.run/fal-ai/imageutils/marigold-depth Endpoint ID: fal-ai/imageutils/marigold-depth

Try it in the Playground

Run this model interactively with your own prompts.

Quick Start

Python

import fal_client

def on_queue_update(update):
    if isinstance(update, fal_client.InProgress):
        for log in update.logs:
           print(log["message"])

result = fal_client.subscribe(
    "fal-ai/imageutils/marigold-depth",
    arguments={
        "image_url": "https://storage.googleapis.com/falserverless/model_tests/remove_background/elephant.jpg"
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)

Examples

Input Schema

image_url · string · required

Input image url.

num_inference_steps · integer · default: "10"

Number of denoising steps. Defaults to 10. The higher the number, the more accurate the result, but the slower the inference. Default value: 10

Range: 2 to 50

ensemble_size · integer · default: "10"

Number of predictions to average over. Defaults to 10. The higher the number, the more accurate the result, but the slower the inference. Default value: 10

Range: 2 to 50

processing_res · integer · default: "0"

Maximum processing resolution. Defaults 0 which means it uses the size of the input image.

Range: 0 to 2048

Output Schema

image · Image · required

The depth map.

Input Example

{
  "image_url": "https://storage.googleapis.com/falserverless/model_tests/remove_background/elephant.jpg",
  "num_inference_steps": 10,
  "ensemble_size": 10,
  "processing_res": 0
}

Output Example

{
  "image": {
    "url": "",
    "content_type": "image/png",
    "file_name": "z9RV14K95DvU.png",
    "file_size": 4404019,
    "width": 1024,
    "height": 1024
  }
}

Limitations

• num_inference_steps range: 2 to 50
• ensemble_size range: 2 to 50
• processing_res range: 0 to 2048