OpenAI opens doors to DALL-E after the horse has bolted to Midjourney and others

OpenAI on Wednesday made DALL-E, its cloud service for generating images from text prompts, available to the public without any waitlist. But the crowd that had gathered outside its gate may have moved on. The original DALL-E debuted in January 2021 and was superseded by DALL-E 2 this April. The latest release, which offers …

[Anonymous Coward]

mmm

been playing with stable diffusion.

the output varies between WTF, nightmare fuel, and nice waterfall

[heyrick]

Re: mmm

Been playing with Dall-E (my waitlist was four days, about a month and a bit ago).

It can create some interesting images depending upon how it understood the text given, but they really need to fix the faces. It clearly understands how a human body is constructed, and generally does quite good work except for the eyes which are a complete horror show. It's as if the AI has a routine to pick an eye to go with the face, but runs it twice completely independently for each eye. The results are generally rather awful. Sometimes for the character it works, but oftentimes a person with two notably different eyes just looks bizarre.

[Death Boffin]

Art history class

So none of the artists complaining about their images being used for training ever looked at another artist's work to learn techniques and styles?

Paris icon because I'm sure she is one of the training images.

[The Indomitable Gall]

Re: Art history class

This is fundamentally different.

A human looking at a coffee-table book of a particular artist's pieces doesn't automagically gain the ability to produce works that are nearly indistinguishable from the artist's own work

[Yet Another Anonymous coward]

Re: Art history class

That is the big advantage of famous art as an investment - there is no way for a human artist to produce works indistinguishable from other famous works

[low_resolution_foxxes]

Re: Art history class

I have no training in art. After 1 hour I was producing quite nice stuff here.

Easily stuff that was better than 50% of the Tate Modern.

I find this tool wonderful for band album covers initially. The actual stuff that won the award is beautiful

There's a weird argument that humans can take existing art as a reference but apparently AI cannot? I find that argument silly. There will always be a market for old school art. But now my 13yr old cousin can create this stuff with 2hours training.

[GraXXoR]

Open source leading the revolution, as it should be.

And as a certain Light Transport YouTuber would say:

What a time to be alive!