Live data from Hacker News

AI generated artwork inspired by current events

prompt.press

1–9 of 9 posts

Re: AI generated artwork inspired by current events

#2
I did something along these lines, but a realtime ghetto version. I had a computer that sat there with windows speech to text API constantly running. Once it reached some word count or time span, it would do a google meme gif image search, and show the top four hits. It was pretty amusing when it would get things completely wrong.

Something similar would make an interesting art installation.

Re: AI generated artwork inspired by current events

#4

I actually found most of the illustrations compelling for the story.

thanks! I wrote a bit about the challenges of prompt engineering here: https://twitter.com/d_jones/status/1541873676173189120

The difficulty of prompt engineering cannot be underestimated. You have to try lots of variations and iterate heaps on the prompt. I usually generate several hundred images to pick from and evaluate based on connection to the topic, coherence + esthetic.

For many generated images, people don't have a specific target in mind and let themselves be surprised (which is fun!), but it's quite difficult to take a given topic, write a prompt and get back a coherent image that is on topic.

Re: AI generated artwork inspired by current events

#6
post #2

I did something along these lines, but a realtime ghetto version. I had a computer that sat there with windows speech to text API constantly running. Once it reached some word count or time span, it would do a google meme gif image search, and show the top four hits. It was pretty amusing when it would get things completely wrong. Something similar would make an interesting art installation.

Another fun art installation would be a camera system attempting to recognize people and logos and items in real time and send those string of converted text items to Dalle.

Re: AI generated artwork inspired by current events

#9
post #4

I actually found most of the illustrations compelling for the story.

thanks! I wrote a bit about the challenges of prompt engineering here: https://twitter.com/d_jones/status/1541873676173189120 The difficulty of prompt engineering cannot be underestimated. You have to try lots of variations and iterate heaps on the prompt. I usually generate several hundred images to pick from and evaluate based on connection to the topic, coherence + esthetic. For many generated images, people don't…

Is there anything out there on “what works” and doesn’t, what those challenges look like in iteration etc? It sounds like an interesting skill frankly.