Crumb
c/webdev · by Tablaste@linux.community · 1y

Comparing local large language models for alt-text generation

https://dri.es/comparing-local-llms-for-alt-text-generation

I tested 12 LLMs — 10 running locally and 2 cloud-based — to assess their accuracy in generating alt-text for images.

I have 10,000 photos on my website. About 9,000 have no alt-text. I'm not proud of that, and it has bothered me for a long time.

8 points · 1 comments · view on lemmy.world

1 Comments

Kissaki@programming.dev · 0 pts · 1y

Their follow-ups:

  1. I want to run AI locally. Here is why I'm not (yet).
  2. Automating alt-text generation with AI
  3. Trusting AI with my images wasn't easy.

They went through with it.

AI isn't perfect, but it can be very useful. People worry about hallucinations and inaccuracy, and I did too. But after generating alt-text for 9,000 images, I saw something different: real, practical value.

/edit: Added the other follow-up posts too.