# Building an open source, accessibility-focused image describer

**URL:** <https://community.fly.io/t/building-an-open-source-accessibility-focused-image-describer/19085>\
**Category:** Show & Tell\
**Created:** [April 2, 2024, 10:15pm UTC](https://community.fly.io/t/building-an-open-source-accessibility-focused-image-describer/19085 "2024-04-02T22:15:02Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![nolan-fly](https://avatars.discourse-cdn.com/v4/letter/n/a183cd/32.png) [@nolan-fly](https://community.fly.io/u/nolan-fly)\
**Post date:** [April 2, 2024, 10:15pm UTC](https://community.fly.io/t/building-an-open-source-accessibility-focused-image-describer/19085/1 "2024-04-02T22:15:02Z")

</div>

We’re all about experimentation at [Fly.io](http://Fly.io), and we want to be the easiest place for you to run GPU-powered experiments without breaking the bank or needing a PhD in your cloud provider of choice to figure things out.

As a blind screen reader user, I’ve been interested in automated image descriptions and how they can form a foundation for entirely new types of accessibility tools, but I didn’t have a good GPU or the time to figure out where to rent one. Now that [Fly.io](http://Fly.io) has GPUs, I made my own describer and hosted it on [Fly.io](http://Fly.io). I would love to know your thoughts on it, particularly if there are ways it might be improved.

[LLM-Describer](https://github.com/superfly/llm-describer) is a [PocketBase](https://pocketbase.io) project which, when pointed at an [Ollama](https://ollama.com) instance, provides a simple authenticated API for users to submit images, get descriptions, and ask followup questions about the image. It also includes a simple Python program to put it through its paces.

I have an upcoming blog post describing this project in greater detail, but I’m not kidding when I call this an experiment. I’m new to both AI development and working with Go, so there are probably things I could do differently or ways I can improve. This is meant as a sample project, so I’m trying not to go too far into the weeds, but I’m open to any thoughts or suggestions that don’t introduce a lot of scope creep or change the project substantially.

Looking forward to reading your feedback! This has been a blast to make, and I’m glad to finally share it with folks.
