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