Twitter seems to have an endless stream of examples with the aiart and generativeart hashtags. Also I really like Katherine Crowson's twitter because she builds Colab notebooks that n00bs like me can use to tinker:

https://twitter.com/RiversHaveWings

https://github.com/crowsonkb

Some examples I shared a while back using Katherine's VQGAN+CLIP notebook: https://imgur.com/a/1R5UZQb Promp was 'mad max dieselpunk alien spaceship landed in a desert' and then I upscaled the images. These are cherry picked from a set of about 3x this size.

One thing I find pretty remarkable is how good it handles shadows and depth of field. These are all kind of mud tones but if you let it run away with color you'll get some really brilliant results.

Scroll down to prompts and put in your prompt. I just did:

    prompts = ['fire ants attacking a school bus cinematic 35mm']

Click on 'Runtime->Run all' and let the notebook execute it's initialization steps and then start to generate the image. By default it goes 1000 iterations, and spits out what it's working with every 100 iterations. Once you get one you like you can update the prompt, re-run that cell and the one below it to generate something new.

I pay $9/mo to get access to better GPUs (usually P100 sometimes get better), the free accounts tend to get slower ones so it might take 30-60 minutes to complete per image.

"CUDA out of memory."

Check out my other post for those that use a very customized version of ruDALL-e

Rather than calling these the final products, these are more like something I would take to an artist to produce some commissioned work in finer detail with their personal touch.

https://imgur.com/a/zeCPnyA https://imgur.com/a/w2ifLVm https://imgur.com/a/gVlzlUG https://imgur.com/a/LOLq2ad https://imgur.com/a/QHyyrtY https://imgur.com/a/HFozuFe https://imgur.com/a/eR6PTBR https://imgur.com/a/L7uKC8d https://imgur.com/a/kmOIQiW https://imgur.com/a/GWGt56i

I have tons of these each day...though several of these examples use the same sources with different settings if you notice any monotony.

This actually highlights how this kind of AI simply smushes sources up randomly without any sense of content or meaning.

It has a look - more horror than SF - but that's because distorted smushing with vague hints of distorted body parts is a look in itself. (See also artists like Francis Bacon.)

Neither AI nor developers aimed for this look deliberately. It just happens to be what falls out of the process. (See also Wombo, which has a similar aesthetic.)

What it doesn't do is evoke the imaginative narratives of the originals, which were consciously crafted to suggest a mood, setting, or context. Compare with (say) Bruce Pennington or Chris Foss and it's easy to see what's missing.

Very low value in my opinion, pretty much garbage in fact.

Many artists went nowhere back then, others used their experiments to create masterpieces. It is always relative and it baffles me how some people only think about the masterpieces and big names, without looking the whole timeline.

Besides, generative and AI art are so damn cool :) It is something closer to us developers, but still far (not everyone knows how to implement it).

I'm really confused why would someone call this "perfectly fake". Have those people seen the real covers? The covers were meant to catch your eye, to evoke some kind of emotion. Compared to them, most of the examples evokes only repulsion in me.

The main issue is that it's hard to generate good looking faces without a specialized model (because we're so picky about humans), and the companies generating models like DALL-E don't want to teach them how to generate faces in case of bias.

I loved it at first and got quite into it but I have seen enough of these images now that the novelty has worn off and they are just kind of shit.

Physical painting inspired by GAN art might be cool but I don't have the talent for that. There is also something lost for sure when I know I could make a 100 of these album covers in maybe 20 minutes of tinkering around?

https://hypertele.fi/0416e43936606257

https://hypertele.fi/a78fd2489d1b8df8

Here's a presentation for Papers We Love San Diego on a paper describing such a technique:

https://www.youtube.com/watch?v=KFORVMT8AWs

I would argue that the proper way to do this while respecting other creators is to create your own original source images and then train the model based on those, before then applying the style to some other original image of your own.

Which makes me wonder if this is a problem with many/most of the AI images one sees. I think so?

It's been a long time but I found something about the critical methodology used just extremely insulting to any piece of literature it was applied to, reductive and harmful to actually appreciating anything, so despite reading a minimum of 4 books a week I decided to write fake book reports. Generally crappy science fiction and fantasy was the genre.

I only remember one fake book I wrote a review of - The Hinterlands of Horlon - a crappy Tolkien rip off with a quest and everything, written by James R. Canton which was also a role playing character name I had for some occult spy game I was in at the time. Fake cover art would have been a nice topper to the fraud.

I'm the exact same way and I think this says something about how the methods used to generate these images relates in some way to how our mind processes them.

The same can be said for painting (we are already seeing it now) and with writing.

https://www.theguardian.com/education/2020/feb/29/children-r...

I'm guessing the faces because she did so much portraiture.

AI generated covers and titles used as writing prompts would be very fun. They would have to be far better than these, though.

There's this? https://tvtropes.org/pmwiki/storygen.php

And that is a wonderful way to get ideas. :D

"Wondrous...thought-provoking...panda." - The NY Times

The singularity might come sooner than I thought.

Welp, i just tried and: https://imgur.com/x9bwRq2

---Prompt----

I am a children's book author and I will write an illustrated short story for you. I will start with the title, then the first page, then a description of an illustration in square brackets like so: [describe illustration here]. Then I will provide two more pages and illustrations. The subject of the book is a puppy that gets lost and then finds its way home.

Q: How does the book start?

---Answer---- (I just keep clicking Generate after it inserts the next 'Q:')

A: The book starts with the puppy waking up from a nap and noticing that its mom and dad are gone. It starts to get scared and starts to cry.

Q: A: The puppy keeps crying until it falls asleep. [The puppy is shown sleeping in a bed with a teddy bear next to it. There is a window in the background with light shining in, and a door is visible at the side of the bed.]

Q: A: The next time the puppy wakes up, it's dark outside and it's scared again. [The puppy is shown in a different room this time, with a nightlight on and a few toys scattered around. It's looking out a window at the stars.]

Q: A: The puppy spends the whole day looking for its mom and dad, but it can't find them. [The puppy is shown walking through a park, then a city street, then a forest. It's looking tired and sad.]

Q: A: The puppy finds a home in the forest and falls asleep. [The puppy is shown curled up in a bed of leaves. It's raining outside and the window is foggy.]

Q: A: The next day, the puppy wakes up and realizes that it's not in its own home. It starts to cry again. [The puppy is shown looking out the window of the home it found. It's raining and the window is foggy.]

Q: A: The puppy sees a light in the distance and starts to run towards it. [The puppy is shown running towards a house. It's still raining and the ground is wet.]

Q: A: The puppy reaches the house and starts to cry. A woman comes outside and picks it up. [The woman is shown picking up the puppy and hugging it. The puppy is crying and the woman has a sad expression.]

Q: A: The woman takes the puppy inside and starts to cry. [The woman is shown crying on the couch. The puppy is sitting on the floor next to her, looking sad.]

Q: A: The woman calls the police and they come to take the puppy back to its home. [The woman is shown talking on the phone. The puppy is sitting on the floor next to her, looking sad.]

Q: A: The police take the puppy back to its home and it's happy to be back. [The puppy is shown being reunited with its mom and dad. They're all happy and the puppy is wagging its tail.]

Q: A: The end.

EDIT: wrong decade there

There is also the choices made by the art directors at the publishers to consider; they were aware of current trends in SF/F book covers, as well as other genres, and would select artists based on how well they worked with those trends. Or against them. Consider for instance Richard Powers (http://www.richardmpowers.com/1970s) who did a ton of psychedelic SF cover work in the 60s, and less work in the 70s as things swung to a more realistic look.

The history of printing and art materials also plays into this. Full color printing was cheap enough for full color covers to be normal; compare 1970s SF covers to SF covers from the 1920s or 1930s, when color separations had to be done by hand, and when acrylic paints were not yet available!

Powers' work definitely evokes that particular era, but (to me at least) it seems a bit... dour, I suppose, and a poor fit for lighter hearted works from then (Laumer's Retief, Harrison's Stainless Steel Rat novels). Definitely a case where ADs were conforming to a trend, although the later examples in those series aren't as jarring.

https://wearethemutants.com/2017/09/20/atari-400800-box-and-...

http://sorayama.jp/works/

https://overspraybook.blogspot.com/

Ten thousand what?

Man, I hate it when that happens...

Looking at these images I am all but certain that there are going to be identifiable portions of the originals in the AI-generated images. They are derivative works. Erasing the original artist's role in creating these images is immoral.

But technologists insist that since one step in the chain of creation was algorithmic, the technologist gets all the credit and the original artist gets none.

That's what Depp is doing right? Captain Jack Sparrow? It's a Keith Richards impersonation, but although Richards gets a part in one of the later sequels partly off the back of that, I don't see a credit for it in the first movie.

This is just how culture works. The pollination shades over from straight plagiarism, through homage and satire, until it's just unconscious assumptions and then it slips out of view entirely and even the creator has no idea it was there. Long before you disappear into the unconscious you're into a space where what you thought you were saying isn't what your audience understood at all. There are Warhammer 40K fans who don't realise that the Ultramarines are a joke. Yes they're blue, why is everybody laughing?

It’s interesting to think about how we tend to grade the “smarts” of machine intelligence by comparing them to what us humans believe to be the truth. Even if they were trying to teach us something how would we ever know?