Hacker News new | ask | show | jobs
by feynmanalgo 1471 days ago
If this is legit it would be one of the most impressive things I've seen in many years.
2 comments
oldstrangers 1471 days ago
It's legit, just variations / iterations.

Here's what I got for "A still of Kermit The Frog in Blade Runner 2049 (2017)":

https://imgur.com/a/y7t3RKx

link
feynmanalgo 1471 days ago
None of them scream Blade Runner 2049 to me.
link
oldstrangers 1471 days ago
In this case its the overall "tone" and color palette. Very uniform diffuse lighting, muted color, etc.
link
lfkdev 1471 days ago
? Dale is a legit project from openAI
link
jffry 1471 days ago
I think "legit" in this context might mean more of the Twitter post author's representation of their use of DALL-E 2:

- Were the prompts shown the ones fed to DALL-E 2 or were there more complex details described in the prompt?

- Were these the first images generated for the prompt, or did the author generate many images and cherry-pick the best example, and if so from how many?

link
sillysaurusx 1471 days ago
The second one is how everyone does it, by the way. AI may as well be a cherry orchard. There’s nothing wrong with it.

The first one, I’d have a huge problem with. Lying about prompts is a no no. Thankfully there’s not much incentive to lie.

link
tommoor 1471 days ago
That doesn't mean the images in this tweet thread are output from Dalle though…

Although if an individual created all of these then that's about the same amount of impressive

link
gk1 1471 days ago
It's funny that 10 years ago "a human did it" would be, by far, the most plausible explanation. Today, it's "AI did it." Put another way, if a human made these then it'd be as shocking as seeing DALL-E 2 in 2012.
link