krthr / clip-embeddings

Generate CLIP (clip-vit-large-patch14) text & image embeddings

  • Public
  • 131.8K runs
  • GitHub
  • Paper
Run with an API
Playground API Examples README Versions

Input

Output

Run time and cost

This model runs on Nvidia A40 GPU hardware. Predictions typically complete within 1 seconds. The predict time for this model varies significantly based on the inputs.

Readme

Get text & image embeddings using CLIP.

Details

  • Model used: clip-vit-large-patch14
  • Length of the embeddings: 768

Response

{
  "embedding": [0.1, 0.2, ..., 0.5]
}