Jump to content

My photo has a 97.7% chance of being awesome.

You are about to reply to a thread that has been inactive for 1027 days.

Please take a moment to consider if this thread is worth bumping.

Recommended Posts

  • Replies 81
  • Created
  • Last Reply

Top Posters In This Topic

Top Posters In This Topic

Popular Posts


I'm filing a JIRA, like right now!

I found a website that uses a neural network (artificial intelligence) to evaluate how good is your photo is. I tried a photo of my mesh SL avatar and got 97.7%! It even suggests tags for your photo.

Posted Images

12 hours ago, Dementia Obviate said:

I'm with you... apparently 99% of my pics suck.  I tried numerous pics. Most got single digits or below even though they generated tags like beautiful, sensual, fashion model, and sex symbol. Only one I tried that got in the 90s was the free Altamura avatar in her underwear and tank top. ?

I put in some of the textures for some of my most popular paintings, and the results were horrible. I only hope that this is because the program looks for contrast and a variety of colors, and my tendency to create somewhat monochromatic images to evoke a specific mood does not work with the algorithm,

Link to post
Share on other sites

And a slightly serious one too.

There's a special reason why I post this one. It's from a Photohunt so it's been judged by humans before. It didn't win of course, it's not a very good picture. I'm not even sure if it reached top ten - among about a dozen contestants. But Everypixel gives it a very high score. Food for thought.

Then again, did anybody actually click on the "Awesome" word to see what they really mean by it?


This service doesn't measure the coolness or beauty of a person or any object in a photo. It cares only about technical parts like brightness, contrast, noise and so on. Service doesn't dedicate for historical photos, illustrations or 3D visualizations.


I have to say I'm seriously impressed by the tags generated though. It's very human-centric and failed to identify less common species like driders, centaurs, nagas and mermaids but apart from that (and its failure to make sense of modern art) they were usually spot on. I'm tempted to run my Alamy portfolio through it but I suppose that would be rude.



Oh as a special bonus, out beloved jellybean. A fake one that is. For some weird reason LL forgot to include the pink one in their collection.


Edited by ChinRey
  • Like 2
Link to post
Share on other sites

From what I recall (from the discussion of AI on the radio) was that most neural networks are narrowly focused on one subject and the humanity destroying version (that we welcome) would have to be widely focused on all subjects.

Link to post
Share on other sites
You are about to reply to a thread that has been inactive for 1027 days.

Please take a moment to consider if this thread is worth bumping.

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now

  • Create New...