this post was submitted on 14 Apr 2024

59 points (91.5% liked)

The Lyrics Game

418 readers

2 users here now

Anybody can post a challenge.

The rules of the game are simple, take any song you like from any genre you want, put the lyrics through any AI [you may weight lyrics as the AI allows] that you want and post the resulting image here under the post title Name That Song [GENRE]. After 48-72 Hours or if the answer is guessed sooner, edit the post's title to [Solved][Genre] and put the song title and artist (and optionally any highlighted lyrics) in a spoiler tag in the body of the post.

Other than that, enjoy.

Here is a list to a few AI image generators you can use.

founded 6 months ago

MODERATORS

[email protected]

[Solved] 1985 - Bowling for Soup (lemmy.world)

submitted 5 months ago* (last edited 5 months ago) by [email protected] to c/[email protected]

36 comments fedilink hide all child comments

First Post (but have loved playing along)

top 36 comments

sorted by: hot top controversial new old

[–] [email protected] 15 points 5 months ago (2 children)

That's AI? Dear me, it's really really sexy.

[–] [email protected] 7 points 5 months ago (2 children)

Now that you mention it, the car front does look weird.

Jup, AI image generation has gotten really good. And this song guessing game based on custom pictures is the perfect use case for it.

[–] [email protected] 4 points 5 months ago* (last edited 5 months ago) (1 children)

Yep its gotten stunning at first glance, but has little mistakes, like the double indicator on the side of the car 🤣

[–] [email protected] 3 points 5 months ago

And the way her top fabric doesn't line up under her arm. If you did cut a top like that, the extra hanging bit in front would fall forward under the bust, without tension to pull it back.

[–] [email protected] 2 points 5 months ago

Yes it's very fun.

[–] [email protected] 2 points 5 months ago

Worryingly so

[–] [email protected] 9 points 5 months ago (1 children)

1985 by bowling for soup

[–] [email protected] 2 points 5 months ago (1 children)

Exactly..! I was worried for a bit there no one would get it 🥳

[–] [email protected] 5 points 5 months ago (1 children)

Soon as I saw it, the aesthetic reminded me of the song. Then I remembered the line, "her yellow SUV, is now the enemy" and was sure of it!

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

Yeah the AI grabbed that yellow reference and went wild with it.

The prompt was that entire verse,

She was gonna be an actress, she was gonna be a star, She was gonna shake her ass on the hood of Whitesnake's car, Her yellow SUV is now the enemy, Looks at her average life and nothin' has been alright,

[–] [email protected] 4 points 5 months ago

What's also funny about that, is I always took it as the modern (2000s) yellow suv is now the enemy cause shes driving her kids all around, but the AI definitely heard 1985 and "yellow suv" and tried to smash them together.

[–] [email protected] 7 points 5 months ago (2 children)

Baby Got Back - Sir Mix-a-Lot

[–] [email protected] 4 points 5 months ago (1 children)

Baby Got Back Problems, namely spinal lordosis.

[–] [email protected] 1 points 5 months ago

Oh boy do I know the pain of that. Men say it looks sexy. But it hurts like hell.

[–] [email protected] 1 points 5 months ago

Nopes, awesome song though

[–] [email protected] 5 points 5 months ago (2 children)

She wears short shorts

[–] [email protected] 3 points 5 months ago

Nopes

[–] [email protected] 2 points 5 months ago (1 children)

Is that an actual song, and not just a ad jingle?

[–] [email protected] 3 points 5 months ago

Yeah

[–] [email protected] 4 points 5 months ago (1 children)

Coldplay - Yellow

[–] [email protected] 3 points 5 months ago

Good guess, but no

[–] [email protected] 3 points 5 months ago (1 children)

Legs - ZZ Top

[–] [email protected] 1 points 5 months ago

Another great song, but no

[–] [email protected] 3 points 5 months ago (1 children)

Mellow Yellow by Donovan

[–] [email protected] 2 points 5 months ago

Nopes, clue for everyone yellow is a lyric, not a title

[–] [email protected] 2 points 5 months ago (1 children)

Dan Seals - My Old Yellow Car

[–] [email protected] 1 points 5 months ago

Nopes

[–] [email protected] 1 points 5 months ago

I'm amazed how LLMs still mess up hands.

[+] [email protected] -6 points 5 months ago (1 children)

Killing the environment one stupid AI image at a time. Great job

[–] [email protected] 4 points 5 months ago (1 children)

Oh no! 5 seconds of GPU time on consumer grade hardware!

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

It’s not nearly as small as you think it is.

Generating 1,000 images with a powerful AI model, such as Stable Diffusion XL, is responsible for roughly as much carbon dioxide as driving the equivalent of 4.1 miles in an average gasoline-powered car.

https://www.technologyreview.com/2023/12/01/1084189/making-an-image-with-generative-ai-uses-as-much-energy-as-charging-your-phone/

Even better when you take into account the scale at that these run at:

https://www.washingtonpost.com/business/2024/03/07/ai-data-centers-power/

[–] [email protected] 4 points 5 months ago* (last edited 5 months ago)

Consider the average toaster, roughly 1100W (on average) and toast takes 1-4 min to cook, (for the purposes of this we'll split the difference and say 2 minutes).
With math, toasting 1 slice of bread equates to roughly 0.037kWh of electricity. (kWh = (watts × hours) ÷ 1000)

Now I'm running a 7900XTX (OC) who's peak power draw is 800W (300W less than a toaster), and it legit takes 5-10secs to generate an image. Realistically I might do a couple of runs (some small then one big one) and use 30 secs of peak compute time. This would equate to 0.0067kWh of electricity usage.

Toasting bread quite literally draws way more electricity than it takes for me to generate one AI image.

1000025193

So are you out there hassling people cooking their morning toast for thier criminally high power usage?

Also some further context for you, I don't use Stable Diffusion XL (listed in your article) as the old school 512x512 is more than enough for my needs (as demonstrated in this post^^). Your second article is paywalled, (not great to share if ppl can't access it), but appears to be data center use which as described above is not what I'm doing here.

edit, spelling

[–] [email protected] 3 points 5 months ago* (last edited 5 months ago) (1 children)

I know exactly how much goes into it, 5 seconds of GPU time, on my own computer. That's why I said it. How many phone charges do you think it would take to fully create a digital drawing on a laptop? It's not going to be much different IME.

[–] [email protected] -4 points 5 months ago (2 children)

You aren’t taking into account the resources required to train the model. You clearly have very little idea how much goes into it other than running software someone else wrote.

[–] [email protected] 2 points 5 months ago

We aren't training models here, this isn't the training-ai-with-massive-datacentres@lemmy

[–] [email protected] 2 points 5 months ago

Of course I've taken into account model training costs, was that supposed to be your gotcha? You don't actually think the energy cost amortization from training still accounts for the bulk of energy expended per image generated do you?