Plus side is generating them is increasing global warming
Yes and no.
Generating images instead of not generating images? Increases global warming
Generating vacation images instead of flying to vacation? Net benefit
Create 1,000 images with a model like Stable Diffusion XL, and you’ve produced as much carbon dioxide as driving just over four miles in a gas-powered car, according to the researchers Melissa spoke to.
I would say that compares maybe be wrong.
How, that’s scary, thanks!
How will artists ever compete with this?
Too perfect but wrong hands
The fire also looks a bit too intents to me 😉
It’s funny how similar AI generated images are to accompanying drawings for “what are ten things that are wrong with this picture?” style questions in an IQ test.
Ah, good idea putting the fire in the tent, that way the fire will stay warm
No, that’s fine. It’s the 👍 thumb! Look at it! It’s freakishly small but not ridiculously small.
Or the single Wolverine stick claw.
that’s just a sardine, I think
The hot air is also guaranteed to keep the tent up.
It also stores a lot of heat in the walls of the tent, which will keep the air inside from cooling down too much over the course of the night.
If you put the whole ass campfire in the tent, it might fly away. Put the fire in the freezer overnight, then thaw it out in chunks when needed.
Alternatively, scrape some glue off your pizza and use it to stick the tent’s bottom to the ground.
Great advice. I’ve sometimes woken up several fields over after the fire has been a bit ferocious. The screams of my family as we’ve flown over people’s houses has also caused some complaints.
I always pack several tablets of dehydrated water with me so if I’m running out, I can just dissolve a couple to have something to drink or cook with
I did not notice that, all I did was look at the image on autopilot
Fuck I was totally convinced until I saw her shoe laces
And that could be one if the “totally lifehack” ways of tieing your shoes that never make any sense.
what about the metal rod extending from her right hand?
Nah that’s normal, obviously
That’s a genetic condition, racist
Just a shitty version of Wolverine
Nice asbestos tent, but she still got Gollum fingers doe.
She has the same skeletal structure as Wolverine it seems.
Achtually Wolverine can’t bend his wrists
I’ve seen live people actually starting a bonfire in their living room something like 20 years ago, so to me this is perfectly possible :D
The magical half hair, half rock.
Even with foreshortening, those are some freakishly short legs.
This reminds me of camping in my youth with my alcoholic uncle.
Your uncle is hot
I think more that the fire is hot cuz he made it in a tent
You better not be gearing up to go all Deliverance on us with that story
Deliverance didn’t have drunk uncles.
I mean, that’s just a minor detail. And Deliverance taught me how to prepare for south of Market clubs in my 20s. IYKYK.
The eyes look demonic
The tells
Hands issues, thumb and metal claw
Face issue, studio lighting on face, right eye is not eyeing.
Body issues, left leg is a weird tiny leg
Boot laces lack credibility
Fire in a tent
AI is bad at the details.
Prespective is not done properly. Trying to spoof 3D with a 2D model.
I’ve gotten so used to looking at the details that I didn’t even notice the blatant fire-in-the-tent.
I was staring at the hands and thinking it wasn’t too bad.
They’re terrible!
I actually kind of love that AI art can’t even pretend to do hands right. But also I had an instructor who’s catch phrase was ‘‘if you let the computer do it, it’s gonna suck’’ so. Not really a surprise AI can only defeat art that’s placid and uninspired shit. and can’t even do anything on model or sequential… it’s just… it can be a placeholder and that’s about it.
It’s funny how the generators arent getting better. They’ve plateaued pretty hard in terms of believability. Glance value? Convincing.
Under any level of scrutiny though this falls apart in at least a dozen ways.
“AI” image generation actually takes a lot of human knowledge and understanding of the models to manipulate outcomes. It is a different kind of effort, but the issues with it are based in human use of the tool.
Prompt engineering isn’t a real field bro
I think the scale of image believability is logarithmic. Going from “believable at a glance” to “believable under scrutiny” requires an exponential increase in performance compared with going from “not believable at a glance” to “believable at a glance”. The same principle applies to text generation, facial recognition, sound generation, image enhancement, etc. One of the many reasons AI should not be being integrated in many of the ways world governments and corporations are trying to integrate it.
It’s unclear if the current models can reach that level though. They seem more like they’re asymtotically approaching their limit.
Maybe I’m wrong and GPT 5 will be the end all and be all - but I don’t think generalist models will ever be consistent enough. Specialist generators focused on specifics, trained to output very defined data seem more likely to be useful than this attempt to make a single catch all LLM.
It’s more the free and public versions have plateaued
Gpt 4 premium pictures still have these major issues.
