rmokady/clip_prefix_caption 🖼️❓✓ → 📝

▶️ 1.7M runs 📅 Oct 2021 ⚙️ Cog 0.4.1 🔗 GitHub ⚖️ License
image-captioning image-to-text

About

Simple image captioning model using CLIP and GPT-2

Example Output

Output

[object Object]

Performance Metrics

1.63s Total Time
All Input Parameters 
{
  "image": "https://replicate.delivery/mgxm/4dc7763a-f234-4a7c-a85f-cb9e05e37cf8/COCO_val2014_000000579664.jpg",
  "model": "coco",
  "use_beam_search": false
}
Input Parameters
image (required) Type: string
Input image
model Default: coco
Choose a model
use_beam_search Type: booleanDefault: false
Whether to apply beam search to generate the output text
Output Schema

Output

Type: string

Version Details
Version ID
9a34a6339872a03f45236f114321fb51fc7aa8269d38ae0ce5334969981e4cd8
Version Created
September 29, 2022
Run on Replicate →