[a / b / c / d / e / f / g / gif / h / hr / k / m / o / p / r / s / t / u / v / vg / vm / vmg / vr / vrpg / vst / w / wg] [i / ic] [r9k / s4s / vip / qa] [cm / hm / lgbt / y] [3 / aco / adv / an / bant / biz / cgl / ck / co / diy / fa / fit / gd / hc / his / int / jp / lit / mlp / mu / n / news / out / po / pol / pw / qst / sci / soc / sp / tg / toy / trv / tv / vp / vt / wsg / wsr / x / xs] [Settings] [Search] [Mobile] [Home]
Board
Settings Mobile Home
/r/ - Adult Requests


Thread archived.
You cannot reply anymore.


[Advertise on 4chan]


File: 455208519.jpg (252 KB, 1080x1079)
252 KB
252 KB JPG
Who makes these A.I pictures? They are waaay higher quality than anything else on the internet. Everything else looks fake but these are next level. Requesting knowledge
>>
File: 1596845119.jpg (168 KB, 1024x1024)
168 KB
168 KB JPG
>>
File: 179816301.jpg (196 KB, 1024x1024)
196 KB
196 KB JPG
>>
They're made in Stable Diffusion (given the resolution of 1024 x 1024 I assume using an SDXL based model).

The reason they look good compared to lots of AI gens is that someone has clearly taken time to iterate and refine them. It might help to explain a little about how AI image gen works. With a service like MidJourney etc you are not able to directly provide prompts. Your input is first passed by their API and changed. Sometimes in quite a radical way (see the actual prompt output in the meta data for Dall-E compared to what you write). This gives a reliable and consistent way of creating images easily but also tends to result in reduced flexibility.

Stable Diffusion you prompt directly, and you have a wide range of tools that can change the image gen, refine it after the fact, and add post-processing onto it. Getting really good results with SD is an iterative process. They didn't just type something random into a text prompt and get these. They probably went through many stages in their workflow, and likely created hundreds if not thousands of images before they arrived here. I would imagine they also custom trained the model they are using, or at the very least had custom trained embeddings/LoRAs to improve the results. They likely also used image-2-image or control net to further balance how the image appears and have greater control. And then they may well have done some final edits outside of AI in a traditional app like Photoshop.
>>
>>19347123
thank you anon, appreciate the knowledge.
>>
>>19347123
but is there any popular creators of these? I only ever find them reposted on other sites
>>
>>19347185

I'd guess that someone is just doing that. Popping them up on Twitter, or wherever, as and when they make them. Might be worth having a look at Civitai to see what kind of stuff you can see on there. You'll find a load of profiles of people that make all kinds of wild AI stuff.
>>
Maybe this account? Not sure.

https://beta.imagefap.com/pictures/12140412/The-Best-of-Taylor-Swift-AI
>>
>>19347268
Some good stuff in there. Too much BBC though. I hate how obsessed the internet is with interracial sex.
>>
There's Bing threads on /trash/ where these guys post and make those pics
>>
>>19347107

It just a bunch of incel basement dwellers who make this stuff. Same guys who used to make fakes with Photoshop. They just got better tools now to make pics of all their sick fantasies.



[Advertise on 4chan]

Delete Post: [File Only] Style:
[Disable Mobile View / Use Desktop Site]

[Enable Mobile View / Use Mobile Site]

All trademarks and copyrights on this page are owned by their respective parties. Images uploaded are the responsibility of the Poster. Comments are owned by the Poster.