this post was submitted on 20 Apr 2024
410 points (96.6% liked)

Memes

45661 readers
1093 users here now

Rules:

  1. Be civil and nice.
  2. Try not to excessively repost, as a rule of thumb, wait at least 2 months to do it if you have to.

founded 5 years ago
MODERATORS
 

image descriptionAn infographic titled “How To Write Alt Text” featuring a photo of a capybara. Parts of alt text are divided by color, including "identify who", "expression", "description", "colour", and "interesting features". The finished description reads “A capybara looking relaxed in a hot spa. Yellow yuzu fruits are floating in the water, and one is balanced on the top of the capybara’s head.”

via https://www.perkins.org/resource/how-write-alt-text-and-image-descriptions-visually-impaired/

top 28 comments
sorted by: hot top controversial new old
[–] [email protected] 1 points 6 months ago (2 children)

Ignorant question: isn't alt text primarily for visually impaired people? If so, what is the point of including info about color?

[–] [email protected] 1 points 6 months ago (1 children)

You can also become visually impaired at points other than birth in life, and know colours and stuff

[–] [email protected] 1 points 6 months ago

That's a very good point!

[–] [email protected] 2 points 6 months ago

Color can provide useful context. For example, in the case of this image, imagine if in a thread about it there was some discussion of the ripeness of the yuzu fruit.

[–] [email protected] 1 points 6 months ago

Is this not the kind of thing machine vision/language models would be really good at?

[–] [email protected] 6 points 6 months ago

Just as important is “decorative images” where you explicitly leave the alt empty https://www.w3.org/WAI/tutorials/images/decorative/

[–] [email protected] 5 points 6 months ago

You know those little [] that appear when you upload an image? You can put alt-text in there.

[–] [email protected] 12 points 6 months ago (1 children)

Me writing alt text: Time is a flat circle. God is a sock.

[–] [email protected] 3 points 6 months ago (1 children)

Reminds me of my git commit messages!

[–] [email protected] 2 points 6 months ago

Nothing but crucial intel

[–] [email protected] 23 points 6 months ago (1 children)

I like how “description” is one of the components of the… description.

[–] [email protected] 4 points 6 months ago

See also: self referential

goes to dictionary entry for "recursion"

[–] [email protected] 27 points 6 months ago (1 children)

Bro I fucking love capybaras so much

10/10 animal, fucking brilliant.

[–] [email protected] 11 points 6 months ago

my favourite animal

the carbonara

[–] [email protected] 14 points 6 months ago

This is excellent, very useful for continuing to make images accessible on the fediverse

[–] [email protected] 49 points 6 months ago (2 children)

A capybara in the library with a candlestick.

[–] [email protected] 13 points 6 months ago

He was definitely the murderer

[–] [email protected] 5 points 6 months ago (1 children)
[–] [email protected] 6 points 6 months ago* (last edited 6 months ago) (1 children)
[–] [email protected] 2 points 6 months ago

A true classic

[–] [email protected] 15 points 6 months ago (5 children)

Potentially also useful for creating good prompts for AI image generators?

[–] [email protected] 1 points 6 months ago

We don't do that here.

[–] [email protected] 5 points 6 months ago* (last edited 6 months ago)

Prompts are just the reverse of image recognition AI tagging stuff.

Alt text is exactly the kind of tedious work that AI would be good at doing, but everyone in the fediverse seems to have a huge hate boner for ANYTHING AI...

Fediverse: write a fucking essay every time you post an image.... But make sure you waste time doing it manually, instead of using AI tools!!!

[–] [email protected] 2 points 6 months ago

If you have really detailed image tags, a model trained on them can make great outputs.

[–] [email protected] 8 points 6 months ago (1 children)

It's essentially by-hand CLIP, that's how the training data for CLIP came into being, it was descriptive text for images.

[–] [email protected] 1 points 6 months ago (1 children)

Explains why it sucks so much shit.

[–] [email protected] 1 points 6 months ago

CLIP is pretty decent for what it does though

[–] [email protected] 6 points 6 months ago

It’s only useful if the AI was trained on similar prompts. A lot of the anime style ones work best with lists of tags, while the realistic ones work best with descriptions like above.