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

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

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"
    ]
}