Live data from Hacker News

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

pub.towardsai.net

31–40 of 153 posts

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

#32
> It’s important to tell DALL·E 2 exactly what you want

That’s not as easy as it sounds. Specially in the surreal cases that DALL-E is usually requested.

Sometimes you don’t know what you want until you see it. Other times you do, but are not able to express in ways that the computer can understand.

I see being able to communicate efficiently with the machine as a future in demand skill

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

#33
post #14

> it was difficult to find images where the entire llama fit within the frame I had the same trouble. In my experiment I wanted to generate a Porco Rosso style seaplane. illustration. Sadly none of the generated pictured had the whole of the airplane in them. The wingtips or the tail always got left off. I found this method to be a reliable workaround: I have downloaded the image I liked the most. Used an image editi…

What prompts did you use for the infill and detail generation?

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

#34
post #21
post #14

> it was difficult to find images where the entire llama fit within the frame I had the same trouble. In my experiment I wanted to generate a Porco Rosso style seaplane. illustration. Sadly none of the generated pictured had the whole of the airplane in them. The wingtips or the tail always got left off. I found this method to be a reliable workaround: I have downloaded the image I liked the most. Used an image editi…

Wow, I've had the same trouble and these are some great tips! Thanks for sharing

Anytime! I have uploaded the image in question: the initial prompt with first generated images, the extended raw image, and then the one with the added details on the city.

https://imgur.com/a/QEU7EJ2

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

#35

> It’s important to tell DALL·E 2 exactly what you want That’s not as easy as it sounds. Specially in the surreal cases that DALL-E is usually requested. Sometimes you don’t know what you want until you see it. Other times you do, but are not able to express in ways that the computer can understand. I see being able to communicate efficiently with the machine as a future in demand skill

No post body was provided.

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

#37

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. Maybe you can read into it something like, "we are solving lots of discrete problems like this, maybe we can somehow glue them together into a higher level program"? That might give you something AI-esque? My guess is that 'true' AGI will have an elegant solution rather than a big bag of stuff glued together.

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

#39
Wow the blogs posted here are awesome, the octopus and this lama are awesome.

Myself cant seem to get it to work. I think it's not very good at real things. Tried fitness related images, all is weird. Probably with fantasy kinda stuff its better since it has to be less accurate.

Post reply on HN