First look – AI faces by DALL-E 2 – (in the style of portrait photographers like Annie Leibovitz)

Yes today readers of my paid mailing list the memo got a bit of a surprise. Besides getting an invitation to mid-journey where they can go play around with text to image generation similar to Dolly, maybe better than Dolly according to some but a bit dark for me. They also got 100 page PDF that I put together based on some work from a user of Dolly too that is generating new faces in the style of different portrait photographers. This is Annie Levy, it’s behind me. This person never existed. This photo never existed until OpenAI is Dolly too created it. We’ve only been able to create images with faces via Dolly too in the last few days. I think they enabled that the 25th of June 2022 after they put a lot of safety in place to make sure that they weren’t generating figures of real people, celebrities, that kind of thing that’s all been blocked. I’m not actually that interested in text to image generation that’s kind of just outside of my focus area which is large language models based on text being able to generate text but they do say a picture paints a thousand words. One of the memo subscribers Shuddy wrote this comment, thank you for the memo. Can we expect a video about Dolly too faces anytime soon and he’s referring there to the PDF? Alright let’s do it. I’ve put together these images with some Ken Burns zoom effect so you can see what’s actually happening. They’re all 1024 by 1024 squares but we’ll zoom them in so they get into your 1920 screen. Let’s do it. All these images were generated by Dolly too by a guy called Michael Green. He cut in the prompt. I don’t think anyone owns the copyright and I’m just doing this for fun. Let’s start with a famous portrait photographer Dorothea Lange. Every photo is using the phrase photo of a young Mexican woman in the style of X. Next one is Helmut Newton. Let’s have a look at Diane Arbus. Michael Green chose the search phrase because he’s currently living in Mexico City so he’s really grabbed one particular topic and played around with it. Eric LaForg. Michael noted that Dolly has an incredibly refined understanding of lighting and composition. This one’s probably my favourite. Any LeBovets. And Michael chose the best four of six images and probably rented a couple of times to see which was the best. Lee Jeffries. This one is Steve McCurry. Next we have Nancy Golden. Michael comments while this is most definitely art, it is not yet known what impact this will have on the future of photography. Number 9 Robert Mapplethorp. This is David Bailey. Terry Richardson, very famous for his use of clothing accessories, expressions and obviously very close up work in his portrait photography. Yusuf Kash. Michael admits here that the status of copyright is too complicated. Simply put, he reckons he does not own the copyright to the digital file. Martin Scholar. Julia Margaret Cameron. George Hurrell. Michael made the comment here. I don’t understand how any of this works. Referring of course to the fact that none of these people exist yet. The AI is conceptualising these people out of its imagination. Peter Lindberg. Brian Ingram. Kenneth Willott. Richard Avedon. The Metri Agive. With Michael’s note here that the Metri is an active NFT artist but these rendered images cannot be sold as NFTs. Michael says Dolly appears to be effortlessly creative. Herb Ritz. This is Arnold Newman. This is Arnold Newman. And Michael’s noting here the difficulty with eyes. I notice of course that even Google Imagine has trouble with eyes and sometimes fingers. But this will be fixed very soon. Robert Frank. And number 25 Bruce Gilden. That was a lot of fun. Note one more time. None of this is photoshopped or copy pasted or emulated even. Every single face you just saw is conceptualised. It is created brand new from scratch out of its imagination. The AI is essentially using connections between what it knows. Maybe that’s a lot like a human, including a human artist or a human portrait photographer like Annie. Did you see the memo about this? Yeah. Yeah, yeah I have the memo right here. Love artificial intelligence? Excited by the explosive progress of integrated AI? I am. Join my private mailing list. The memo. Did you get that memo? Yeah I got the memo. Get priority access to my articles, videos and behind the scenes tips as soon as they’re released with a monthly or annual subscription. Yeah. Didn’t you get that memo? Lifearchitect.ai slash memo. I have the memo.

AI video(s) you might be interested in …