cjwbw/clip-vit-large-patch14 📝🖼️ → 🔢

▶️ 12.5M runs 📅 Sep 2022 ⚙️ Cog 0.4.3 🔗 GitHub
image-classification image-text-matching text-image-similarity zero-shot-classification zero-shot-image-classification

About

openai/clip-vit-large-patch14 with Transformers

Example Output

Output

3.860912656250548e-80.00000252170798376027960.9999974966049194

Performance Metrics

0.27s Prediction Time
95.87s Total Time
All Input Parameters 
{
  "text": "a photo of a dog | a cat | two cats with remote controls",
  "image": "https://replicate.delivery/mgxm/36b04aec-efe2-4dea-9c9d-a5faca68b2b2/000000039769.jpg"
}
Input Parameters
text (required) Type: string
Description of the image, separate different descriptions with "|"
image (required) Type: string
Input Image.
Output Schema

Output

Type: array • Items Type: number

Version Details
Version ID
566ab1f111e526640c5154e712d4d54961414278f89d36590f1425badc763ecb
Version Created
September 22, 2022
Run on Replicate →