https://github.com/fofr/cog-batch-image-captioning

Caption images for lora training
https://github.com/fofr/cog-batch-image-captioning

ai anthropic captioning claude cog gemini openai replicate

Last synced: 3 months ago
JSON representation

Caption images for lora training

• Host: GitHub
• URL: https://github.com/fofr/cog-batch-image-captioning
• Owner: fofr
• License: mit
• Created: 2024-08-13T09:33:08.000Z (5 months ago)
• Default Branch: main
• Last Pushed: 2024-08-13T12:52:23.000Z (5 months ago)
• Last Synced: 2024-08-14T13:41:53.964Z (5 months ago)
• Topics: ai, anthropic, captioning, claude, cog, gemini, openai, replicate
• Language: Python
• Homepage: https://replicate.com/fofr/batch-image-captioning
• Size: 17.6 KB
• Stars: 3
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# cog-batch-image-captioning

A cog model for batch image captioning using various AI from OpenAI, Anthropic, and Google's Generative AI:

https://replicate.com/fofr/batch-image-captioning

## Features

- Process multiple images from a ZIP archive

- supports png, jpg, jpeg, webp

- Optional image resizing for more cost-effective captioning

- Customizable caption prefixes and suffixes

- Support for multiple AI models:

  - OpenAI: GPT-4 and variants

  - Anthropic: Claude-3.5, Claude-3 variants

  - Google: Gemini-1.5 variants

- Flexible system and message prompts

- Error handling and retry mechanism

- Output as a ZIP file containing captions that match image filenames as well as a CSV summary