Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Spent $15 in DALL·E 2 credits creating this AI image

pub.towardsai.net

Post reply on HN
Print view View original

51–60 of 153 posts

Re: Spent $15 in DALL·E 2 credits creating this AI image

#51

Post by Comevius »

dougmwne wrote: post #25
keepquestioning wrote: post #15

DALL-E is truly magic. It got me believing we are close to AGI. I wonder what Gary Marcus or Filip Pieknewski think about it. Surely they must be eating crow.

Yesterday I saw one of Gandalf eating samples at Costco. I was laughing hysterically for a minute. AI is not supposed to have a sense of humor. That was supposed to be the last province of the human, but it is quite awhile since a human made me laugh like that.

If I write a Python script that cuts together a bunch of pictures and the output makes you laught the script hardly deserves all the credit. It's us humans that create meaning.

Re: Spent $15 in DALL·E 2 credits creating this AI image

#52

Post by thfuran »

jmfldn wrote: post #37
keepquestioning wrote: post #15

DALL-E is truly magic. It got me believing we are close to AGI. I wonder what Gary Marcus or Filip Pieknewski think about it. Surely they must be eating crow.

This tells us little about AGI. It might seem like it does but this is an incredibly narrow specific set of technologies. They work together to produce some startling results (with many limitations) but this is just another narrow application. I suspect AGI, depending on how its defined, will be with us in some form in the next few decades at most. Just a hunch. This is nothing to do with that mission though imho. Ma…

We're pretty much just a big bag of stuff glued together.

Re: Spent $15 in DALL·E 2 credits creating this AI image

#53

Post by MonkeyMalarky »

pamelafox wrote: post #24
MonkeyMalarky wrote: post #8

Earlier quoted context omitted.

I want to see a few iterations of describing an image with AI, generating it, describing it again, generating it... Like when passing a piece of text through Google translate back and forth.

I tried that! Results were mixed: https://twitter.com/pamelafox/status/1542593090472386561 It needs a better text to image model, I think. Maybe you can fork it and improve?

Interesting! I really like the flute > cup > bathtub sequence. It has a real dreamlike disjointedness to it.

Re: Spent $15 in DALL·E 2 credits creating this AI image

#54

Post by pigtailgirl »

planetsprite wrote: post #48
pigtailgirl wrote: post #13

-- spent a day with DALL-E - here are some of my favorites: https://imgur.com/a/uD5yjV3 --

Were a lot of your prompts just "attractive girl hat and sunglasses high quality photography"

-- hat pic are playing with "variations" mode - the prompt was: “portrait photo, california beach with female model wearing hat and sunglasses, studio, lens flare, colourful, 4k, high definition, 35mm, HD” --

Re: Spent $15 in DALL·E 2 credits creating this AI image

#55

Post by jcims »

Vox_Leone wrote: post #5

Can I use NLP to generate input for DALL-E 2? That would be cool.

I used GPT-3 to 'write' a children's book and asked it to include descriptions of the illustrations.

https://docs.google.com/presentation/d/1y8EE_p8bw9dIEDguT1bT...

The fact that it's a derivative of an existing work is noteworthy, but I gave it absolutely no guidance on the topic. If i suggest something it will give it a go with similar fervor. eg https://imgur.com/a/N1qWaSV

Re: Spent $15 in DALL·E 2 credits creating this AI image

#57

Post by TheOtherHobbes »

falcor84 wrote: post #50

>the ball is positioned in such a way that the llama has no real hope of making the shot I love that we're at the level where the physical "realism" of correctly representing quadrupedals playing basketball is a thing now. I suppose the next level AI will be expected to model a full 3d environment with physical assumptions based on the prompt and then run the simulation

That's the only way to get reliably usable output.

There's a lot of "80% there but not quite" in the current version, which makes it more of a novelty than a useful content generator.

The problem with moving to 3D is there are no almost no 3D data sources that combine textures, poses (where relevant), lighting, 3D geometry and (ideally) physics.

They can be inferred to some extent from 2D sources. But not reliably.

Humans operate effortlessly in 3D and creative humans have no issues with using 3D perceptions creatively.

But as for as most content is concerned it's a 2D world. Which is why AI art bots know the texture of everything and the geometry of nothing.

AI generation is going to be stuck at nearly-but-not-quite until that changes.

Re: Spent $15 in DALL·E 2 credits creating this AI image

#58

Post by jfk13 »

karaterobot wrote: post #20

I ran into this too. When I got my invite, I told a friend I would learn how to talk to DALL-E by having it make some concept art for the game he was designing. I ran through all of my free credits, and most of the first $15 bucket and never really got anything usable. Even when I re-used the exact prompts from the DALL-E Prompt Book, I didn't get anything near the level of quality and fidelity to the prompt that the…

I suspect that many of the "impressive" examples that we see from tools like this have been carefully selected by human curators. I'm sure it's not at the level of "monkeys + typewriters = Shakespeare [if you're sufficiently selective]", but the general idea is still applicable.

Re: Spent $15 in DALL·E 2 credits creating this AI image

#59

Post by kube-system »

ticviking wrote: post #47
obloid wrote: post #31

"Image intentionally modified to blur and hide faces" I thought this was strange. Why hide an AI generated face?

They’re being used to create fake profile pictures.

I'm not sure why anyone bothers. StyleGAN2 profile photos are literally all over social media and they're good enough to fool the human reviewers every time I report them.

Re: Spent $15 in DALL·E 2 credits creating this AI image

#60

Post by jfk13 »

jcims wrote: post #55
Vox_Leone wrote: post #5

Can I use NLP to generate input for DALL-E 2? That would be cool.

I used GPT-3 to 'write' a children's book and asked it to include descriptions of the illustrations. https://docs.google.com/presentation/d/1y8EE_p8bw9dIEDguT1bT... The fact that it's a derivative of an existing work is noteworthy, but I gave it absolutely no guidance on the topic. If i suggest something it will give it a go with similar fervor. eg https://imgur.com/a/N1qWaSV

Your link doesn't seem to be publicly accessible.
Post reply on HN