It’s actually kinda cool how it tells a story already, isn’t it? I’m tempted to present my story in pictures.
2 Likes
Yeah it is! And it also makes for good cover inspiration 
2 Likes
Just because I’ve got a bit of an obsession about location…uh …
Bern Switzerland is what I’m looking up next:
Screenshot:
Anything on Wiki is free to use, generally speaking, that’s why I pulled it up this way, right now.
Some programs, I consider that too much instruction for them to reproduce. Lol
3 Likes
One day I want to visit the Alps
2 Likes
I suppose those were the first and the last images that I could upload to stock.
This update came from Shutterstock today:
In this spirit, we will not accept content generated by AI to be directly uploaded and sold by contributors in our marketplace because its authorship cannot be attributed to an individual person consistent with the original copyright ownership required to license rights. Please see our latest guidelines here . When the work of many contributed to the creation of a single piece of AI-generated content, we want to ensure that the many are protected and compensated, not just the individual that generated the content.
So it’s questionable if my images will remain where they are or if they’ll be taken down. They didn’t address in the updated terms if it’s just new images going forward or if all existing stock is included.
Well, at least I didn’t spend any money on this or wasted too much time yet. There are AI junkies out there that have submitted thousands of images hoping to make some income from them. And they have started making some money but yeah, easy come, easy go.
Back to creating for my personal use which was always my primary goal anyway.
But, the full message of Shutterstock’s update is very curious. So here it is:
Summary
We’re excited to announce that we are partnering with OpenAI to bring the tools and experiences to the Shutterstock marketplace that will enable our customers to instantly generate and download images based on the keywords they enter.
As we step into this emerging space, we are going to do it in the best way we know how—with an approach that both compensates our contributor community and protects our customers.
In this spirit, we will not accept content generated by AI to be directly uploaded and sold by contributors in our marketplace because its authorship cannot be attributed to an individual person consistent with the original copyright ownership required to license rights. Please see our latest guidelines here . When the work of many contributed to the creation of a single piece of AI-generated content, we want to ensure that the many are protected and compensated, not just the individual that generated the content.
In the spirit of compensating our contributor community, we are excited to announce an additional form of earnings for our contributors. Given the collective nature of generative content, we developed a revenue share compensation model where contributors whose content was involved in training the model will receive a share of the earnings from datasets and downloads of ALL AI-generated content produced on our platform.
We see generative as an exciting new opportunity—an opportunity that we’re committed to sharing with our contributor community. For more information, please see our FAQ on the subject, which will be updated regularly.
My translation: we’re cutting the middle men that have been using AI generators to contribute AI images to stock, and instead, we’re letting OpenAI to use our entire database of images to train our own version of an AI generator so that our customers can pay US to generate the images they want and we won’t have to pay AI artists to do the work for us.
While I’m happy for the thought that contributors of the existing stock will get paid for their contribution to training the AI, I really doubt it will amount to much because each image samples from thousands of images so each generation that results in a sale would result in a fraction of cent payout. And I bet that a huge inventory of what Shutterstock owns is entirely theirs and they don’t have to pay anyone for it (psst, they take images that are in public domain and make money off them because they can).
So in short, the future of AI art is to bring more money for the image stock sites.
I guess I shouldn’t be surprised that a fun open source tool is doomed to fall in the hands of the commercial greed. I just hope that there will still be free (or at least cheap) generators available for me to use on my own without having to go through a corprorate giant (who might introduce further bias to the results).
What’s nice and cool never stays free forever…
3 Likes
Oooh, that’s cool 
I’m just too lazy to go and look for pictures for it to use.
1 Like
That’s wallpaper quality dude
Those are awesome
1 Like
I really like the first one. Does it do only one character at a time?
1 Like
You can try to get more people but it gets harder to generate something well refined or even anatomically correct the more you ask of it.
I was able to get a few nice couples but never the couples I want. It becomes a game of chance whereas when you ask for one specific portrait, you’re more likely going to get what you want.
For example, took me a while to land on a good prompt but finally got one,
Portrait of elderly Indian man in purple hat autumn
Let’s experiment. I know you didn’t ask for this experiment but now I’m on a mission.
It took a few tries but I was able to double him up.
Portrait of two elderly Indian men in purple hat autumn
But when you try to make them into two different people, it gets tricky.
Portrait of elderly Indian man in purple hat and elderly white man autumn
It kept giving me one indian man.
The closest I got is this.
Two Indian elders with white hair.
Lol
I guess it’s easier if you’re trying to generate something more common.
Another experiment. Oh, this was harder than I thought. Took a lot of tries to get to a working prompt.
Portrait of elderly Indian couple autumn
Portrait of elderly Indian gay couple autumn
So the verdict is in. You can create a couple as long as you’re asking for the same type of a person and you’re not picky about what type of a couple you get.
1 Like
If you can see this, someone make a literal Elvish Presley.
1 Like
Dall-e 2 has made it into NightCafe. I can’t wait to try out how those two work together.
@J.L.O a pun art! 
2 Likes
Yeah, I think the poster missed the pun.
2 Likes
I tried Dall-e on NightCafe a couple of times and I think I finally see how to use it.
I like creative AI generations which is why I add a bunch of details to my prompts and let AI pick and choose from them until it lands on something interesting. That doesn’t work well with Dall-e. Simple is better with that tool.
For example, AI really struggles with snails. I tried creating my snail with Dream in the past too and I was getting similar “creative” results as this (stable on NightCafe).
or
Really cool results but it does not resemble a snail.
I tried the last prompt with Dall-e. Results were blurry, unclear. So I simplified the prompt, and at last, Dall-e gave me a snail.
So the verdict is in. If Stable struggles creating something, Dall-e might do it.
Stable is still my go-to though because I like the creative results. And sometimes, the results are totally not what I was looking for but they’re so awesome, I’m happy anyway.
For example, these two happy accidents:
I realized that she would work well as Bryde in my other story so there’s great use for her.
or this one.
I was trying to create a cool clock but it took the term “clock face” literally. lol. Results are so cool though, I love these creative clocks.
1 Like
I spent way too many credits on trying to create myself. I tried to feed it my picture and also just create myself from prompt. No success yet though a few nice portraits came out of it.
Here are just a few.
None of these really look like me though a couple came close. And of course, all of them look about 20 years younger, lol.
2 Likes
You know, this one has probably the closest to my face shape, even the glasses look similar to my current glasses, and even eyebrows are similar. Probably the nose is the biggest difference, and of course, my hair never looks this fancy. It was from a prompt, no picture given, so it’s pretty impressive.
And though I can’t rewind time to look like I’m 20, It definitely makes me wonder what I’d look like as a blonde.
2 Likes
Tonight on AI news, Nightcafe has been doing these challenges where they give you a prompt, you submit a creation and then the community votes. The winners score credits.
I got top 20% several times already, once I got 10%, and once I even had 5% - on the Ancient Ruins prompt.
Today’s prompt is Castles.
Hmmm. I might give this one a try.
In other news, I managed to log myself out of Dream and I can’t seem to get back into my profile. I think I saved all the images I wanted to save but this kind of sucks.
So let this be a cautionary tale for you all. Save whatever images you like because you never know if you’ll have access to it tomorrow.
But where will I put them all??? I have sooo many by now and I love them all. They’re all my babies.
2 Likes