Clip Comparison

v2

Class: ClipComparisonBlockV2 (there are multiple versions of this block)

Source: inference.core.workflows.core_steps.models.foundation.clip_comparison.v2.ClipComparisonBlockV2

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

Use the OpenAI CLIP zero-shot classification model to classify images.

This block accepts an image and a list of text prompts. The block then returns the similarity of each text label to the provided image.

This block is useful for classifying images without having to train a fine-tuned classification model. For example, you could use CLIP to classify the type of vehicle in an image, or if an image contains NSFW material.

Type identifier

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

Properties

Name	Type	Description	Refs
name	str	Unique name of step in workflows.	❌
classes	List[str]	List of classes to calculate similarity against each input image.	✅
version	str	Variant of CLIP model.	✅

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 Clip Comparison in version v2.

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

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds Clip Comparison in version v2 has.

Bindings

• input

  • images (image): The image to infer on..
  • classes (list_of_values): List of classes to calculate similarity against each input image.
  • version (string): Variant of CLIP model.

• output

  • similarities (list_of_values): List of values of any type.
  • max_similarity (float_zero_to_one): float value in range [0.0, 1.0].
  • most_similar_class (string): String value.
  • min_similarity (float_zero_to_one): float value in range [0.0, 1.0].
  • least_similar_class (string): String value.
  • classification_predictions (classification_prediction): Predictions from classifier.
  • parent_id (parent_id): Identifier of parent for step output.
  • root_parent_id (parent_id): Identifier of parent for step output.

Example JSON definition of step Clip Comparison in version v2

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/clip_comparison@v2",
    "images": "$inputs.image",
    "classes": [
        "a",
        "b",
        "c"
    ],
    "version": "ViT-B-16"
}

v1

Class: ClipComparisonBlockV1 (there are multiple versions of this block)

Source: inference.core.workflows.core_steps.models.foundation.clip_comparison.v1.ClipComparisonBlockV1

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

Use the OpenAI CLIP zero-shot classification model to classify images.

This block accepts an image and a list of text prompts. The block then returns the similarity of each text label to the provided image.

This block is useful for classifying images without having to train a fine-tuned classification model. For example, you could use CLIP to classify the type of vehicle in an image, or if an image contains NSFW material.

Type identifier

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

Properties

Name	Type	Description	Refs
name	str	Unique name of step in workflows.	❌
texts	List[str]	List of texts to calculate similarity against each input image.	✅

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 Clip Comparison in version v1.

• inputs: QR Code Generator, Clip Comparison, Pixelate Visualization, Florence-2 Model, Morphological Transformation, Google Gemini, Camera Calibration, Buffer, Polygon Zone Visualization, Motion Detection, Keypoint Visualization, Camera Focus, Background Subtraction, Text Display, Anthropic Claude, Bounding Box Visualization, Image Threshold, Contrast Equalization, Halo Visualization, Model Comparison Visualization, Anthropic Claude, Label Visualization, Dynamic Zone, OpenAI, Circle Visualization, Reference Path Visualization, Camera Focus, Image Contours, Background Color Visualization, Image Blur, Mask Visualization, Size Measurement, Image Slicer, Stability AI Image Generation, Stability AI Outpainting, Stitch Images, Color Visualization, Corner Visualization, Classification Label Visualization, Llama 3.2 Vision, OpenAI, Depth Estimation, Google Gemini, OpenAI, Image Preprocessing, Clip Comparison, Florence-2 Model, Image Convert Grayscale, Line Counter Visualization, Ellipse Visualization, Icon Visualization, Dynamic Crop, Image Slicer, Dot Visualization, Absolute Static Crop, Triangle Visualization, Polygon Visualization, SIFT Comparison, Stability AI Inpainting, Crop Visualization, Perspective Correction, Relative Static Crop, SIFT, Detections List Roll-Up, Dimension Collapse, Grid Visualization, Google Gemini, Blur Visualization, Trace Visualization
• outputs: Instance Segmentation Model, Clip Comparison, Florence-2 Model, Google Gemini, Instance Segmentation Model, Polygon Zone Visualization, Email Notification, Motion Detection, Keypoint Visualization, Anthropic Claude, LMM For Classification, Keypoint Detection Model, Anthropic Claude, Email Notification, Reference Path Visualization, OpenAI, Time in Zone, Roboflow Dataset Upload, YOLO-World Model, Google Gemini, Florence-2 Model, VLM as Detector, SAM 3, Time in Zone, Time in Zone, Triangle Visualization, Dot Visualization, Seg Preview, Crop Visualization, Path Deviation, Twilio SMS/MMS Notification, Perspective Correction, SAM 3, Detections List Roll-Up, Grid Visualization, Google Gemini, Line Counter, Object Detection Model, Trace Visualization, Detections Consensus, Webhook Sink, Buffer, Roboflow Dataset Upload, Object Detection Model, VLM as Detector, Bounding Box Visualization, Cache Set, Halo Visualization, Label Visualization, OpenAI, Circle Visualization, VLM as Classifier, Size Measurement, Mask Visualization, Llama 3.2 Vision, Path Deviation, Corner Visualization, Classification Label Visualization, Color Visualization, OpenAI, Clip Comparison, Line Counter Visualization, Ellipse Visualization, Line Counter, VLM as Classifier, Polygon Visualization, Keypoint Detection Model, SAM 3

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds Clip Comparison in version v1 has.

Bindings

• input

  • images (image): The image to infer on..
  • texts (list_of_values): List of texts to calculate similarity against each input image.

• output

  • similarity (list_of_values): List of values of any type.
  • parent_id (parent_id): Identifier of parent for step output.
  • root_parent_id (parent_id): Identifier of parent for step output.
  • prediction_type (prediction_type): String value with type of prediction.

Example JSON definition of step Clip Comparison in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/clip_comparison@v1",
    "images": "$inputs.image",
    "texts": [
        "a",
        "b",
        "c"
    ]
}