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

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

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[instance_segmentation_prediction, keypoint_detection_prediction, object_detection_prediction, list_of_values]): 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"
}