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

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

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"
}