Picture Analyzer (GPT Vision)
Describes images, pulls out text, and answers questions about photos using GPT-4 Vision.
by openakita · ★ 2,005 on GitHub
What it does
Give Claude an image or screenshot, and it sends it to OpenAI's vision model to describe the scene, read text, identify objects, or answer your question about it. You get a clear written answer back.
Who it’s for
A good fit for people who research markets, competitors or topics and anyone working with Word, PDF, Excel or PowerPoint files.
Do you need to code?
Some. To get the most from this one you may need to be comfortable with code, the command line or technical setup.
How to install
Add it to Claude as a skill. Download the skill folder from its source page, zip it, and upload it in Claude’s settings under Skills. See the step-by-step guide.
Safety note
Includes 2 script files that can run on your computer; Needs your own paid OpenAI API key; sends your images to OpenAI's servers.
Script files included: 2
As with any add-on, only install skills from sources you trust, and read what it does first.
License
MIT