salesforce/blip ❓🖼️📝 → 📝

▶️ 168.4M runs 📅 Feb 2022 ⚙️ Cog 0.4.1 🔗 GitHub 📄 Paper ⚖️ License
image-captioning image-text-matching image-to-text visual-question-answering

About

Generate image captions

Example Output

Output

[object Object]

Performance Metrics

6.64s Prediction Time
100.91s Total Time
All Input Parameters 
{
  "task": "image_captioning",
  "image": "https://replicate.delivery/mgxm/f4e50a7b-e8ca-432f-8e68-082034ebcc70/demo.jpg"
}
Input Parameters
task Default: image_captioning
Choose a task.
image (required) Type: string
Input image
caption Type: string
Type caption for the input image for image text matching task.
question Type: string
Type question for the input image for visual question answering task.
Output Schema

Output

Type: string

Version Details
Version ID
2e1dddc8621f72155f24cf2e0adbde548458d3cab9f00c0139eea840d0ac4746
Version Created
September 29, 2022
Run on Replicate →