Florence 2 Large API

Endpoint: POST https://fal.run/fal-ai/florence-2-large/object-detection Endpoint ID: fal-ai/florence-2-large/object-detection

Try it in the Playground

Run this model interactively with your own prompts.

Quick Start

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/florence-2-large/object-detection",
    arguments={
        "image_url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg"
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)

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

const result = await fal.subscribe("fal-ai/florence-2-large/object-detection", {
  input: {
      image_url: "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg"
    },
  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);

curl --request POST \
  --url https://fal.run/fal-ai/florence-2-large/object-detection \
  --header "Authorization: Key $FAL_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "image_url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg"
}'

Input Schema

string

required

The URL of the image to be processed.

Output Schema

BoundingBoxes

required

Results from the model

Image

Processed image

Input Example

{
  "image_url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg"
}

Output Example

{
  "results": {
    "bboxes": [
      {
        "label": ""
      }
    ]
  }
}

Endpoint: POST https://fal.run/fal-ai/florence-2-large/open-vocabulary-detection Endpoint ID: fal-ai/florence-2-large/open-vocabulary-detection

Try it in the Playground

Run this model interactively with your own prompts.

Quick Start

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/florence-2-large/open-vocabulary-detection",
    arguments={
        "image_url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg",
        "text_input": ""
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)

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

const result = await fal.subscribe("fal-ai/florence-2-large/open-vocabulary-detection", {
  input: {
      image_url: "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg",
      text_input: ""
    },
  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);

curl --request POST \
  --url https://fal.run/fal-ai/florence-2-large/open-vocabulary-detection \
  --header "Authorization: Key $FAL_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "image_url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg",
  "text_input": ""
}'

Input Schema

string

required

The URL of the image to be processed.

string

required

Text input for the task

Output Schema

BoundingBoxes

required

Results from the model

Image

Processed image

Input Example

{
  "image_url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg",
  "text_input": ""
}

Output Example

{
  "results": {
    "bboxes": [
      {
        "label": ""
      }
    ]
  }
}

Endpoint: POST https://fal.run/fal-ai/florence-2-large/ocr-with-region Endpoint ID: fal-ai/florence-2-large/ocr-with-region

Try it in the Playground

Run this model interactively with your own prompts.

Quick Start

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/florence-2-large/ocr-with-region",
    arguments={
        "image_url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg"
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)

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

const result = await fal.subscribe("fal-ai/florence-2-large/ocr-with-region", {
  input: {
      image_url: "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg"
    },
  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);

curl --request POST \
  --url https://fal.run/fal-ai/florence-2-large/ocr-with-region \
  --header "Authorization: Key $FAL_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "image_url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg"
}'

Input Schema

string

required

The URL of the image to be processed.

Output Schema

OCRBoundingBox

required

Results from the model

Image

Processed image

Input Example

{
  "image_url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg"
}

Output Example

{
  "results": {
    "quad_boxes": [
      {
        "label": ""
      }
    ]
  }
}

Endpoint: POST https://fal.run/fal-ai/florence-2-large/caption-to-phrase-grounding Endpoint ID: fal-ai/florence-2-large/caption-to-phrase-grounding

Try it in the Playground

Run this model interactively with your own prompts.

Quick Start

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/florence-2-large/caption-to-phrase-grounding",
    arguments={
        "image_url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg",
        "text_input": ""
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)

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

const result = await fal.subscribe("fal-ai/florence-2-large/caption-to-phrase-grounding", {
  input: {
      image_url: "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg",
      text_input: ""
    },
  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);

curl --request POST \
  --url https://fal.run/fal-ai/florence-2-large/caption-to-phrase-grounding \
  --header "Authorization: Key $FAL_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "image_url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg",
  "text_input": ""
}'

Input Schema

string

required

The URL of the image to be processed.

string

required

Text input for the task

Output Schema

BoundingBoxes

required

Results from the model

Image

Processed image

Input Example

{
  "image_url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg",
  "text_input": ""
}

Output Example

{
  "results": {
    "bboxes": [
      {
        "label": ""
      }
    ]
  }
}

Endpoint: POST https://fal.run/fal-ai/florence-2-large/referring-expression-segmentation Endpoint ID: fal-ai/florence-2-large/referring-expression-segmentation

Try it in the Playground

Run this model interactively with your own prompts.

Quick Start

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/florence-2-large/referring-expression-segmentation",
    arguments={
        "image_url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg",
        "text_input": ""
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)

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

const result = await fal.subscribe("fal-ai/florence-2-large/referring-expression-segmentation", {
  input: {
      image_url: "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg",
      text_input: ""
    },
  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);

curl --request POST \
  --url https://fal.run/fal-ai/florence-2-large/referring-expression-segmentation \
  --header "Authorization: Key $FAL_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "image_url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg",
  "text_input": ""
}'

Input Schema

string

required

The URL of the image to be processed.

string

required

Text input for the task

Output Schema

PolygonOutput

required

Results from the model

Image

Processed image

Input Example

{
  "image_url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg",
  "text_input": ""
}

Output Example

{
  "results": {
    "polygons": [
      {
        "label": ""
      }
    ]
  }
}

Endpoint: POST https://fal.run/fal-ai/florence-2-large/dense-region-caption Endpoint ID: fal-ai/florence-2-large/dense-region-caption

Try it in the Playground

Run this model interactively with your own prompts.

Quick Start

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/florence-2-large/dense-region-caption",
    arguments={
        "image_url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg"
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)

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

const result = await fal.subscribe("fal-ai/florence-2-large/dense-region-caption", {
  input: {
      image_url: "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg"
    },
  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);

curl --request POST \
  --url https://fal.run/fal-ai/florence-2-large/dense-region-caption \
  --header "Authorization: Key $FAL_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "image_url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg"
}'

Input Schema

string

required

The URL of the image to be processed.

Output Schema

BoundingBoxes

required

Results from the model

Image

Processed image

Input Example

{
  "image_url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg"
}

Output Example

{
  "results": {
    "bboxes": [
      {
        "label": ""
      }
    ]
  }
}

Endpoint: POST https://fal.run/fal-ai/florence-2-large/region-to-segmentation Endpoint ID: fal-ai/florence-2-large/region-to-segmentation

Try it in the Playground

Run this model interactively with your own prompts.

Quick Start

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/florence-2-large/region-to-segmentation",
    arguments={
        "image_url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg",
        "region": {
            "x1": 100,
            "x2": 200,
            "y1": 100,
            "y2": 200
        }
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)

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

const result = await fal.subscribe("fal-ai/florence-2-large/region-to-segmentation", {
  input: {
      image_url: "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg",
      region: {
        x1: 100,
        x2: 200,
        y1: 100,
        y2: 200
      }
    },
  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);

curl --request POST \
  --url https://fal.run/fal-ai/florence-2-large/region-to-segmentation \
  --header "Authorization: Key $FAL_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "image_url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg",
  "region": {
    "x1": 100,
    "x2": 200,
    "y1": 100,
    "y2": 200
  }
}'

Input Schema

string

required

The URL of the image to be processed.

Region

required

The user input coordinates

Output Schema

PolygonOutput

required

Results from the model

Image

Processed image

Input Example

{
  "image_url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg",
  "region": {
    "x1": 100,
    "x2": 200,
    "y1": 100,
    "y2": 200
  }
}

Output Example

{
  "results": {
    "polygons": [
      {
        "label": ""
      }
    ]
  }
}

Endpoint: POST https://fal.run/fal-ai/florence-2-large/region-proposal Endpoint ID: fal-ai/florence-2-large/region-proposal

Try it in the Playground

Run this model interactively with your own prompts.

Quick Start

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/florence-2-large/region-proposal",
    arguments={
        "image_url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg"
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)

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

const result = await fal.subscribe("fal-ai/florence-2-large/region-proposal", {
  input: {
      image_url: "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg"
    },
  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);

curl --request POST \
  --url https://fal.run/fal-ai/florence-2-large/region-proposal \
  --header "Authorization: Key $FAL_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "image_url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg"
}'

Input Schema

string

required

The URL of the image to be processed.

Output Schema

BoundingBoxes

required

Results from the model

Image

Processed image

Input Example

{
  "image_url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg"
}

Output Example

{
  "results": {
    "bboxes": [
      {
        "label": ""
      }
    ]
  }
}

Florence-2 Large — Vision
Florence-2 Large — Image Generation

Try it in the Playground

​Quick Start

​Input Schema

​Output Schema

​Input Example

​Output Example

Try it in the Playground

​Quick Start

​Input Schema

​Output Schema

​Input Example

​Output Example

Try it in the Playground

​Quick Start

​Input Schema

​Output Schema

​Input Example

​Output Example

Try it in the Playground

​Quick Start

​Input Schema

​Output Schema

​Input Example

​Output Example

Try it in the Playground

​Quick Start

​Input Schema

​Output Schema

​Input Example

​Output Example

Try it in the Playground

​Quick Start

​Input Schema

​Output Schema

​Input Example

​Output Example

Try it in the Playground

​Quick Start

​Input Schema

​Output Schema

​Input Example

​Output Example

Try it in the Playground

​Quick Start

​Input Schema

​Output Schema

​Input Example

​Output Example

​Related

Quick Start

Input Schema

Output Schema

Input Example

Output Example

Quick Start

Input Schema

Output Schema

Input Example

Output Example

Quick Start

Input Schema

Output Schema

Input Example

Output Example

Quick Start

Input Schema

Output Schema

Input Example

Output Example

Quick Start

Input Schema

Output Schema

Input Example

Output Example

Quick Start

Input Schema

Output Schema

Input Example

Output Example

Quick Start

Input Schema

Output Schema

Input Example

Output Example

Quick Start

Input Schema

Output Schema

Input Example

Output Example

Related