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

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

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, instance_segmentation_prediction, keypoint_detection_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"
}