Florence-2 Model

v2

Class: Florence2BlockV2 (there are multiple versions of this block)

Source: inference.core.workflows.core_steps.models.foundation.florence2.v2.Florence2BlockV2

Warning: This block has multiple versions. Please refer to the specific version for details. You can learn more about how versions work here: Versioning

Dedicated inference server required (GPU recommended) - you may want to use dedicated deployment

This Workflow block introduces Florence 2, a Visual Language Model (VLM) capable of performing a wide range of tasks, including:

• Object Detection

• Instance Segmentation

• Image Captioning

• Optical Character Recognition (OCR)

• and more...

Below is a comprehensive list of tasks supported by the model, along with descriptions on how to utilize their outputs within the Workflows ecosystem:

Task Descriptions:

• Custom Prompt (custom) - Use free-form prompt to generate a response. Useful with finetuned models.

• Text Recognition (OCR) (ocr) - Model recognizes text in the image

• Text Detection & Recognition (OCR) (ocr-with-text-detection) - Model detects text regions in the image, and then performs OCR on each detected region

• Captioning (short) (caption) - Model provides a short description of the image

• Captioning (detailed-caption) - Model provides a long description of the image

• Captioning (long) (more-detailed-caption) - Model provides a very long description of the image

• Unprompted Object Detection (object-detection) - Model detects and returns the bounding boxes for prominent objects in the image

• Object Detection (open-vocabulary-object-detection) - Model detects and returns the bounding boxes for the provided classes

• Detection & Captioning (object-detection-and-caption) - Model detects prominent objects and captions them

• Prompted Object Detection (phrase-grounded-object-detection) - Based on the textual prompt, model detects objects matching the descriptions

• Prompted Instance Segmentation (phrase-grounded-instance-segmentation) - Based on the textual prompt, model segments objects matching the descriptions

• Segment Bounding Box (detection-grounded-instance-segmentation) - Model segments the object in the provided bounding box into a polygon

• Classification of Bounding Box (detection-grounded-classification) - Model classifies the object inside the provided bounding box

• Captioning of Bounding Box (detection-grounded-caption) - Model captions the object in the provided bounding box

• Text Recognition (OCR) for Bounding Box (detection-grounded-ocr) - Model performs OCR on the text inside the provided bounding box

• Regions of Interest proposal (region-proposal) - Model proposes Regions of Interest (Bounding Boxes) in the image

Type identifier

Use the following identifier in step "type" field: roboflow_core/florence_2@v2to add the block as as step in your workflow.

Properties

Name	Type	Description	Refs
name	str	Enter a unique identifier for this step..	❌
task_type	str	Task type to be performed by model. Value determines required parameters and output response..	❌
prompt	str	Text prompt to the Florence-2 model.	✅
classes	List[str]	List of classes to be used.	✅
grounding_detection	Optional[List[float], List[int]]	Detection to ground Florence-2 model. May be statically provided bounding box [left_top_x, left_top_y, right_bottom_x, right_bottom_y] or result of object-detection model. If the latter is true, one box will be selected based on grounding_selection_mode..	✅
grounding_selection_mode	str	.	❌
model_id	str	Model to be used.	✅

The Refs column marks possibility to parametrise the property with dynamic values available in workflow runtime. See Bindings for more info.

Available Connections

Compatible Blocks

Check what blocks you can connect to Florence-2 Model in version v2.

• inputs: Icon Visualization, Image Preprocessing, LMM, Blur Visualization, Detections Classes Replacement, Color Visualization, Contrast Equalization, Detections Merge, Llama 3.2 Vision, Velocity, Reference Path Visualization, SIFT, OpenAI, Buffer, SAM 3, Halo Visualization, Trace Visualization, Roboflow Dataset Upload, Dimension Collapse, Twilio SMS/MMS Notification, Detections Transformation, Single-Label Classification Model, VLM as Detector, Image Convert Grayscale, Path Deviation, Background Color Visualization, Multi-Label Classification Model, Camera Calibration, VLM as Detector, Triangle Visualization, Dynamic Zone, Ellipse Visualization, Seg Preview, Slack Notification, Absolute Static Crop, Google Gemini, Time in Zone, Webhook Sink, Line Counter Visualization, Florence-2 Model, Detections Consensus, QR Code Generator, Anthropic Claude, Object Detection Model, Keypoint Detection Model, Image Slicer, Byte Tracker, Image Contours, Stability AI Inpainting, Line Counter, Google Gemini, Motion Detection, SIFT Comparison, Keypoint Detection Model, Dot Visualization, Camera Focus, Byte Tracker, YOLO-World Model, Bounding Box Visualization, OCR Model, Background Subtraction, OpenAI, SAM 3, Dynamic Crop, Keypoint Visualization, Email Notification, Image Threshold, Anthropic Claude, Corner Visualization, Pixelate Visualization, Twilio SMS Notification, Moondream2, Morphological Transformation, Roboflow Custom Metadata, Stitch Images, Detections Filter, Circle Visualization, Stability AI Image Generation, Image Blur, Template Matching, Detections List Roll-Up, Bounding Rectangle, Email Notification, Detection Event Log, EasyOCR, Google Gemini, Instance Segmentation Model, Classification Label Visualization, Clip Comparison, Detection Offset, CogVLM, Google Vision OCR, Stitch OCR Detections, Segment Anything 2 Model, LMM For Classification, Text Display, SAM 3, Mask Visualization, OpenAI, Local File Sink, Anthropic Claude, Polygon Zone Visualization, Polygon Visualization, Model Comparison Visualization, Label Visualization, Perspective Correction, Overlap Filter, Image Slicer, Instance Segmentation Model, Stability AI Outpainting, VLM as Classifier, Grid Visualization, Relative Static Crop, CSV Formatter, Size Measurement, Path Deviation, Camera Focus, Time in Zone, Florence-2 Model, Object Detection Model, Detections Stitch, Crop Visualization, Clip Comparison, Byte Tracker, Detections Stabilizer, Roboflow Dataset Upload, PTZ Tracking (ONVIF).md), Model Monitoring Inference Aggregator, Time in Zone, Detections Combine, Depth Estimation, OpenAI, Gaze Detection
• outputs: Icon Visualization, LMM, Image Preprocessing, Detections Classes Replacement, Color Visualization, Contrast Equalization, Cache Set, Llama 3.2 Vision, Reference Path Visualization, OpenAI, Buffer, SAM 3, Halo Visualization, Roboflow Dataset Upload, Trace Visualization, Twilio SMS/MMS Notification, VLM as Detector, Path Deviation, Background Color Visualization, VLM as Detector, Triangle Visualization, Ellipse Visualization, Seg Preview, Slack Notification, Time in Zone, Google Gemini, Webhook Sink, Line Counter Visualization, Florence-2 Model, Detections Consensus, QR Code Generator, Anthropic Claude, Object Detection Model, Keypoint Detection Model, Pixel Color Count, Stability AI Inpainting, VLM as Classifier, Line Counter, Google Gemini, Motion Detection, SIFT Comparison, Line Counter, Keypoint Detection Model, Dot Visualization, YOLO-World Model, Bounding Box Visualization, OpenAI, SAM 3, Dynamic Crop, Distance Measurement, Keypoint Visualization, Email Notification, Image Threshold, Anthropic Claude, Corner Visualization, Twilio SMS Notification, Moondream2, Morphological Transformation, Roboflow Custom Metadata, Stability AI Image Generation, Circle Visualization, Image Blur, Detections List Roll-Up, Email Notification, Perception Encoder Embedding Model, Google Gemini, Instance Segmentation Model, Classification Label Visualization, Clip Comparison, Google Vision OCR, CogVLM, Stitch OCR Detections, Segment Anything 2 Model, LMM For Classification, Text Display, CLIP Embedding Model, SAM 3, Local File Sink, OpenAI, Mask Visualization, Anthropic Claude, Polygon Zone Visualization, Polygon Visualization, Model Comparison Visualization, Label Visualization, JSON Parser, Perspective Correction, Instance Segmentation Model, Stability AI Outpainting, VLM as Classifier, Grid Visualization, Size Measurement, Path Deviation, Time in Zone, Florence-2 Model, Object Detection Model, Detections Stitch, Cache Get, Crop Visualization, Clip Comparison, Roboflow Dataset Upload, PTZ Tracking (ONVIF).md), Model Monitoring Inference Aggregator, Time in Zone, Depth Estimation, OpenAI

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds Florence-2 Model in version v2 has.

Bindings

• input

  • images (image): The image to infer on..
  • prompt (string): Text prompt to the Florence-2 model.
  • classes (list_of_values): List of classes to be used.
  • grounding_detection (Union[object_detection_prediction, list_of_values, keypoint_detection_prediction, instance_segmentation_prediction]): Detection to ground Florence-2 model. May be statically provided bounding box [left_top_x, left_top_y, right_bottom_x, right_bottom_y] or result of object-detection model. If the latter is true, one box will be selected based on grounding_selection_mode..
  • model_id (roboflow_model_id): Model to be used.

• output

  • raw_output (Union[string, language_model_output]): String value if string or LLM / VLM output if language_model_output.
  • parsed_output (dictionary): Dictionary.
  • classes (list_of_values): List of values of any type.

Example JSON definition of step Florence-2 Model in version v2

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/florence_2@v2",
    "images": "$inputs.image",
    "task_type": "<block_does_not_provide_example>",
    "prompt": "my prompt",
    "classes": [
        "class-a",
        "class-b"
    ],
    "grounding_detection": "$steps.detection.predictions",
    "grounding_selection_mode": "first",
    "model_id": "florence-2-base"
}

v1

Class: Florence2BlockV1 (there are multiple versions of this block)

Source: inference.core.workflows.core_steps.models.foundation.florence2.v1.Florence2BlockV1

Warning: This block has multiple versions. Please refer to the specific version for details. You can learn more about how versions work here: Versioning

Dedicated inference server required (GPU recommended) - you may want to use dedicated deployment

This Workflow block introduces Florence 2, a Visual Language Model (VLM) capable of performing a wide range of tasks, including:

• Object Detection

• Instance Segmentation

• Image Captioning

• Optical Character Recognition (OCR)

• and more...

Below is a comprehensive list of tasks supported by the model, along with descriptions on how to utilize their outputs within the Workflows ecosystem:

Task Descriptions:

• Custom Prompt (custom) - Use free-form prompt to generate a response. Useful with finetuned models.

• Text Recognition (OCR) (ocr) - Model recognizes text in the image

• Text Detection & Recognition (OCR) (ocr-with-text-detection) - Model detects text regions in the image, and then performs OCR on each detected region

• Captioning (short) (caption) - Model provides a short description of the image

• Captioning (detailed-caption) - Model provides a long description of the image

• Captioning (long) (more-detailed-caption) - Model provides a very long description of the image

• Unprompted Object Detection (object-detection) - Model detects and returns the bounding boxes for prominent objects in the image

• Object Detection (open-vocabulary-object-detection) - Model detects and returns the bounding boxes for the provided classes

• Detection & Captioning (object-detection-and-caption) - Model detects prominent objects and captions them

• Prompted Object Detection (phrase-grounded-object-detection) - Based on the textual prompt, model detects objects matching the descriptions

• Prompted Instance Segmentation (phrase-grounded-instance-segmentation) - Based on the textual prompt, model segments objects matching the descriptions

• Segment Bounding Box (detection-grounded-instance-segmentation) - Model segments the object in the provided bounding box into a polygon

• Classification of Bounding Box (detection-grounded-classification) - Model classifies the object inside the provided bounding box

• Captioning of Bounding Box (detection-grounded-caption) - Model captions the object in the provided bounding box

• Text Recognition (OCR) for Bounding Box (detection-grounded-ocr) - Model performs OCR on the text inside the provided bounding box

• Regions of Interest proposal (region-proposal) - Model proposes Regions of Interest (Bounding Boxes) in the image

Type identifier

Use the following identifier in step "type" field: roboflow_core/florence_2@v1to add the block as as step in your workflow.

Properties

Name	Type	Description	Refs
name	str	Enter a unique identifier for this step..	❌
task_type	str	Task type to be performed by model. Value determines required parameters and output response..	❌
prompt	str	Text prompt to the Florence-2 model.	✅
classes	List[str]	List of classes to be used.	✅
grounding_detection	Optional[List[float], List[int]]	Detection to ground Florence-2 model. May be statically provided bounding box [left_top_x, left_top_y, right_bottom_x, right_bottom_y] or result of object-detection model. If the latter is true, one box will be selected based on grounding_selection_mode..	✅
grounding_selection_mode	str	.	❌
model_version	str	Model to be used.	✅

The Refs column marks possibility to parametrise the property with dynamic values available in workflow runtime. See Bindings for more info.

Available Connections

Compatible Blocks

Check what blocks you can connect to Florence-2 Model in version v1.

• inputs: Icon Visualization, Image Preprocessing, LMM, Blur Visualization, Detections Classes Replacement, Color Visualization, Contrast Equalization, Detections Merge, Llama 3.2 Vision, Velocity, Reference Path Visualization, SIFT, OpenAI, Buffer, SAM 3, Halo Visualization, Trace Visualization, Roboflow Dataset Upload, Dimension Collapse, Twilio SMS/MMS Notification, Detections Transformation, Single-Label Classification Model, VLM as Detector, Image Convert Grayscale, Path Deviation, Background Color Visualization, Multi-Label Classification Model, Camera Calibration, VLM as Detector, Triangle Visualization, Dynamic Zone, Ellipse Visualization, Seg Preview, Slack Notification, Absolute Static Crop, Google Gemini, Time in Zone, Webhook Sink, Line Counter Visualization, Florence-2 Model, Detections Consensus, QR Code Generator, Anthropic Claude, Object Detection Model, Keypoint Detection Model, Image Slicer, Byte Tracker, Image Contours, Stability AI Inpainting, Line Counter, Google Gemini, Motion Detection, SIFT Comparison, Keypoint Detection Model, Dot Visualization, Camera Focus, Byte Tracker, YOLO-World Model, Bounding Box Visualization, OCR Model, Background Subtraction, OpenAI, SAM 3, Dynamic Crop, Keypoint Visualization, Email Notification, Image Threshold, Anthropic Claude, Corner Visualization, Pixelate Visualization, Twilio SMS Notification, Moondream2, Morphological Transformation, Roboflow Custom Metadata, Stitch Images, Detections Filter, Circle Visualization, Stability AI Image Generation, Image Blur, Template Matching, Detections List Roll-Up, Bounding Rectangle, Email Notification, Detection Event Log, EasyOCR, Google Gemini, Instance Segmentation Model, Classification Label Visualization, Clip Comparison, Detection Offset, CogVLM, Google Vision OCR, Stitch OCR Detections, Segment Anything 2 Model, LMM For Classification, Text Display, SAM 3, Mask Visualization, OpenAI, Local File Sink, Anthropic Claude, Polygon Zone Visualization, Polygon Visualization, Model Comparison Visualization, Label Visualization, Perspective Correction, Overlap Filter, Image Slicer, Instance Segmentation Model, Stability AI Outpainting, VLM as Classifier, Grid Visualization, Relative Static Crop, CSV Formatter, Size Measurement, Path Deviation, Camera Focus, Time in Zone, Florence-2 Model, Object Detection Model, Detections Stitch, Crop Visualization, Clip Comparison, Byte Tracker, Detections Stabilizer, Roboflow Dataset Upload, PTZ Tracking (ONVIF).md), Model Monitoring Inference Aggregator, Time in Zone, Detections Combine, Depth Estimation, OpenAI, Gaze Detection
• outputs: Icon Visualization, LMM, Image Preprocessing, Detections Classes Replacement, Color Visualization, Contrast Equalization, Cache Set, Llama 3.2 Vision, Reference Path Visualization, OpenAI, Buffer, SAM 3, Halo Visualization, Roboflow Dataset Upload, Trace Visualization, Twilio SMS/MMS Notification, VLM as Detector, Path Deviation, Background Color Visualization, VLM as Detector, Triangle Visualization, Ellipse Visualization, Seg Preview, Slack Notification, Time in Zone, Google Gemini, Webhook Sink, Line Counter Visualization, Florence-2 Model, Detections Consensus, QR Code Generator, Anthropic Claude, Object Detection Model, Keypoint Detection Model, Pixel Color Count, Stability AI Inpainting, VLM as Classifier, Line Counter, Google Gemini, Motion Detection, SIFT Comparison, Line Counter, Keypoint Detection Model, Dot Visualization, YOLO-World Model, Bounding Box Visualization, OpenAI, SAM 3, Dynamic Crop, Distance Measurement, Keypoint Visualization, Email Notification, Image Threshold, Anthropic Claude, Corner Visualization, Twilio SMS Notification, Moondream2, Morphological Transformation, Roboflow Custom Metadata, Stability AI Image Generation, Circle Visualization, Image Blur, Detections List Roll-Up, Email Notification, Perception Encoder Embedding Model, Google Gemini, Instance Segmentation Model, Classification Label Visualization, Clip Comparison, Google Vision OCR, CogVLM, Stitch OCR Detections, Segment Anything 2 Model, LMM For Classification, Text Display, CLIP Embedding Model, SAM 3, Local File Sink, OpenAI, Mask Visualization, Anthropic Claude, Polygon Zone Visualization, Polygon Visualization, Model Comparison Visualization, Label Visualization, JSON Parser, Perspective Correction, Instance Segmentation Model, Stability AI Outpainting, VLM as Classifier, Grid Visualization, Size Measurement, Path Deviation, Time in Zone, Florence-2 Model, Object Detection Model, Detections Stitch, Cache Get, Crop Visualization, Clip Comparison, Roboflow Dataset Upload, PTZ Tracking (ONVIF).md), Model Monitoring Inference Aggregator, Time in Zone, Depth Estimation, OpenAI

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds Florence-2 Model in version v1 has.

Bindings

• input

  • images (image): The image to infer on..
  • prompt (string): Text prompt to the Florence-2 model.
  • classes (list_of_values): List of classes to be used.
  • grounding_detection (Union[object_detection_prediction, list_of_values, keypoint_detection_prediction, instance_segmentation_prediction]): Detection to ground Florence-2 model. May be statically provided bounding box [left_top_x, left_top_y, right_bottom_x, right_bottom_y] or result of object-detection model. If the latter is true, one box will be selected based on grounding_selection_mode..
  • model_version (string): Model to be used.

• output

  • raw_output (Union[string, language_model_output]): String value if string or LLM / VLM output if language_model_output.
  • parsed_output (dictionary): Dictionary.
  • classes (list_of_values): List of values of any type.

Example JSON definition of step Florence-2 Model in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/florence_2@v1",
    "images": "$inputs.image",
    "task_type": "<block_does_not_provide_example>",
    "prompt": "my prompt",
    "classes": [
        "class-a",
        "class-b"
    ],
    "grounding_detection": "$steps.detection.predictions",
    "grounding_selection_mode": "first",
    "model_version": "florence-2-base"
}