CLIP Embedding Model

Class: ClipModelBlockV1

Source: inference.core.workflows.core_steps.models.foundation.clip.v1.ClipModelBlockV1

Use a CLIP model to create semantic embeddings of text and images.

This block accepts an image or string and returns an embedding. The embedding can be used to compare the similarity between different images or between images and text.

Type identifier

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

Properties

Name	Type	Description	Refs
name	str	Unique name of step in workflows.	❌
data	str	The string or image to generate an embedding for..	✅
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 Embedding Model in version v1.

• inputs: LMM, Roboflow Custom Metadata, Image Convert Grayscale, Absolute Static Crop, Multi-Label Classification Model, Relative Static Crop, Line Counter Visualization, Background Color Visualization, OCR Model, Camera Focus, Image Contours, Image Slicer, Keypoint Detection Model, Instance Segmentation Model, Reference Path Visualization, SIFT Comparison, Object Detection Model, Triangle Visualization, Depth Estimation, Google Vision OCR, Roboflow Dataset Upload, Llama 3.2 Vision, Clip Comparison, Perspective Correction, Crop Visualization, Webhook Sink, Dot Visualization, Email Notification, Model Comparison Visualization, Classification Label Visualization, Camera Calibration, Slack Notification, Stability AI Image Generation, Trace Visualization, Corner Visualization, Image Threshold, Local File Sink, Blur Visualization, CogVLM, Stability AI Inpainting, SIFT, Circle Visualization, OpenAI, Florence-2 Model, Twilio SMS Notification, Label Visualization, Stitch Images, Image Preprocessing, Grid Visualization, Polygon Zone Visualization, Keypoint Visualization, LMM For Classification, Stitch OCR Detections, Bounding Box Visualization, Image Blur, OpenAI, Halo Visualization, Google Gemini, Ellipse Visualization, Color Visualization, Pixelate Visualization, VLM as Detector, Roboflow Dataset Upload, Polygon Visualization, Single-Label Classification Model, VLM as Classifier, CSV Formatter, Model Monitoring Inference Aggregator, Image Slicer, Mask Visualization, Anthropic Claude, Florence-2 Model, Dynamic Crop
• outputs: Identify Changes, Cosine Similarity, Identify Outliers

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds CLIP Embedding Model in version v1 has.

Bindings

• input

  • data (Union[image, string]): The string or image to generate an embedding for..
  • version (string): Variant of CLIP model.

• output

  • embedding (embedding): A list of floating point numbers representing a vector embedding..

Example JSON definition of step CLIP Embedding Model in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/clip@v1",
    "data": "$inputs.image",
    "version": "ViT-B-16"
}