Foreverlurk's AI works

Post a reply

Confirmation code
Enter the code exactly as it appears. All letters are case insensitive.
Smilies
:D :) ;) :( :o :shock: :? 8-) :lol: :x :P :oops: :cry: :evil: :twisted: :roll: :!: :?: :idea: :arrow: :| :mrgreen: :geek: :ugeek: :ray_gun
View more smilies

BBCode is ON
[img] is ON
[flash] is OFF
[url] is ON
Smilies are ON

Topic review
   

Expand view Topic review: Foreverlurk's AI works

Re: Foreverlurk's AI works

by foreverlurk » Fri May 03, 2024 9:25 pm

djbtyt wrote:
Tue Apr 09, 2024 7:56 pm
Would you mind sharing the prompt or words to miniaturize? I'm beating my head on the wall and can't seem to make tiny humans unless I start with a 1child and try to age it.
Sorry I missed your post somehow? Can you show me what you are trying, and on which AI? It's all very contextual, but I can help if you show me examples.
dubiouskey wrote:
Thu May 02, 2024 10:09 pm
Mine has a NSFW filter I usually have to get creative to get around.
Oh, what are you using? Is it a local setup or online? I guess it's online since you're talking about filters?

Re: Foreverlurk's AI works

by dubiouskey » Thu May 02, 2024 10:09 pm

Been messing around with AI myself, testing my program of choice's limitations to see what it can do. Mine has a NSFW filter I usually have to get creative to get around.

Re: Foreverlurk's AI works

by djbtyt » Tue Apr 09, 2024 7:56 pm

Hi Foreverlurk,

Would you mind sharing the prompt or words to miniaturize? I'm beating my head on the wall and can't seem to make tiny humans unless I start with a 1child and try to age it.

Re: Foreverlurk's AI works

by foreverlurk » Thu Mar 21, 2024 5:12 pm

Zeshrinkar wrote:
Thu Mar 21, 2024 2:19 am
What program are you using now?? Chat gpt and bing image creator has been nerfed:(
Yeah, "nerfed" is an understatement. I still use ChatGPT to get the base prompt. I need to be way more creative with the prompting nowadays, and I still haven't found workarounds that are 100% foolproof (like those that worked before TaylorSwiftGate).

What changed is my second step in Stable Diffusion. DALL-E is purposely making images less photorealistic (since November), so I used to do img2img through SD version 1.5 and with RealisticVision to get some photo realism back. Now I do the same but with SDXL and JuggernautXL which is what you're seeing in those latest images. All of this is done locally, for user interface I either use ComfyUI with a custom workflow, or Fooocus when I just need a quick touchup (they have a really good custom inpainting/outpainging model).

BTW the next version of Stable Diffusion is looking very promising, maybe it'll finally have good enough prompt understanding for sizey content.

Re: Foreverlurk's AI works

by Zeshrinkar » Thu Mar 21, 2024 2:19 am

What program are you using now?? Chat gpt and bing image creator has been nerfed:(

Re: Foreverlurk's AI works

by foreverlurk » Wed Mar 20, 2024 11:50 pm

DocRick wrote:
Wed Mar 20, 2024 10:13 pm
Gonna have to agree with you. Very nice. Really like the last one for some reason.
Yeah I was sleeping on some of the newer tech for way too long. The next version of generative AIs will be scary good I think.

Re: Foreverlurk's AI works

by DocRick » Wed Mar 20, 2024 10:13 pm

foreverlurk wrote:
Wed Mar 20, 2024 7:06 pm
Another sample from my latest update, playing around with a new model and getting good results I think. More on DA.

Gonna have to agree with you. Very nice. Really like the last one for some reason.

Re: Foreverlurk's AI works

by foreverlurk » Wed Mar 20, 2024 7:06 pm

Another sample from my latest update, playing around with a new model and getting good results I think. More on DA.

Image

Image

Image

Image

Re: Foreverlurk's AI works

by foreverlurk » Sun Mar 03, 2024 8:03 pm

Some more AI content, those were all generated before the Taylor Swift deepfakes drama. I don't know if that will ever die down, but DALL-E has not been the same ever since.

Perks of the Job
Image

Bad Idea
Image

Not Another Word
Image

Size Remote
Image

Re: Foreverlurk's AI works

by DocRick » Fri Feb 09, 2024 11:19 pm

Pacific1982 wrote:
Fri Jan 19, 2024 11:25 pm
Should also mention I really love the image of the girl sitting on the piano keyboard. That is one of my preferred subject matters. Although I’d also prefer her to be nude.
How about this little lady? Wearing a cowboy hat and a guitar. :D

Image

Re: Foreverlurk's AI works

by foreverlurk » Fri Feb 09, 2024 6:26 pm

Tried the new Google AI called Gemini yesterday - wasn't impressed, even more censored than DALL-E, and it did lecture me on the ethics of shrinking, lulz.

Image

Image

Image

Image

Re: Foreverlurk's AI works

by Hand-Holder » Wed Jan 31, 2024 3:29 pm

Amazing job, a whole new World awaits SW arts

Re: Foreverlurk's AI works

by foreverlurk » Sun Jan 28, 2024 11:31 pm

A few more I recenty managed to create, in spite of the recent nerfs and stricter filtering in DALL-E.

Image

Image

Image

Image

Re: Foreverlurk's AI works

by who renders 3d » Mon Jan 22, 2024 4:29 pm

Beautiful!

Re: Foreverlurk's AI works

by foreverlurk » Mon Jan 22, 2024 4:00 pm

blueman wrote:
Mon Jan 22, 2024 11:19 am
Beautiful work in all the images, I really like the settings and the interaction!
Thanks! I love interaction between tiny hands and normal sized fingers...

Image

Re: Foreverlurk's AI works

by blueman » Mon Jan 22, 2024 11:19 am

Beautiful work in all the images, I really like the settings and the interaction!

Re: Foreverlurk's AI works

by foreverlurk » Sun Jan 21, 2024 6:38 pm

Little Sally wrote:
Sat Jan 20, 2024 9:43 am
I think my prompt was "a smiling octopus dancing with a woman in a dress in a realistic setting" :lol:
These are so funny an creative, Sally. More I say, haha!
Pacific1982 wrote:
Fri Jan 19, 2024 11:25 pm
Should also mention I really love the image of the girl sitting on the piano keyboard. That is one of my preferred subject matters. Although I’d also prefer her to be nude.
Here's one I liked (I have a few more I'm still tweaking) :

Image

Re: Foreverlurk's AI works

by Little Sally » Sat Jan 20, 2024 9:43 am

foreverlurk wrote:
Sat Jan 20, 2024 5:08 am
Oh so you could upload a picture, and prompt something based on the that picture? That's usually done through img2img w/ a "Denoise level" - AIs don't draw the same as humans do, they learn to remove chaos (ie. Gaussian Noise) rather than by adding, so the Denoiser's job in this case is to adhere to the original pic up to a certain threshold (0 == "don't touch anything", 1 == "free for all").
No, it had the usual text prompt option as the main thing, then in addition the option to upload an image for reimagination (or re-interpreting) as a separate thing. So two ways of obtaining an image, but neither complimenting the other If that makes sense. I don't think there was a way of influencing what AI did with an uploaded image (at least I didn't notice that), it was just a case letting it do its thing and seeing the result.

foreverlurk wrote:
Sat Jan 20, 2024 5:08 am
Is it possible you were editing the generated pics in Microsoft Designer? It's yet another way to access DALL-E:
https://designer.microsoft.com/image-creator
Thanks for linking to that one which is great. It isn't the one with the pic upload option but still good fun!
I amused myself getting some more octopus related stuff from it (no it isn't a new fetish for me, just a passing whim lol!)

I think my prompt was "a smiling octopus dancing with a woman in a dress in a realistic setting" :lol:

Image

Re: Foreverlurk's AI works

by foreverlurk » Sat Jan 20, 2024 5:08 am

Little Sally wrote:
Fri Jan 19, 2024 10:18 pm
The one I mentioned that I first tried and liked, had the option where you could upload a pic (including work of your own) and AI would do interpretations of it. Or reimagining it as they like to term it.
Oh so you could upload a picture, and prompt something based on the that picture? That's usually done through img2img w/ a "Denoise level" - AIs don't draw the same as humans do, they learn to remove chaos (ie. Gaussian Noise) rather than by adding, so the Denoiser's job in this case is to adhere to the original pic up to a certain threshold (0 == "don't touch anything", 1 == "free for all").

Maybe those details are hidden in the online version but I'm pretty sure they're Stable Diffusion models. Doesn't narrow it down because there are dozens online who offer that service.
Pacific1982 wrote:
Fri Jan 19, 2024 11:25 pm
Should also mention I really love the image of the girl sitting on the piano keyboard. That is one of my preferred subject matters. Although I’d also prefer her to be nude.
It's a favourite of mine, too. Goes way back. I guess I could generate some nudes, I'll see what I can do.

Re: Foreverlurk's AI works

by Pacific1982 » Fri Jan 19, 2024 11:25 pm

Should also mention I really love the image of the girl sitting on the piano keyboard. That is one of my preferred subject matters. Although I’d also prefer her to be nude.

Re: Foreverlurk's AI works

by Little Sally » Fri Jan 19, 2024 10:18 pm

foreverlurk wrote:
Fri Jan 19, 2024 8:06 pm
Little Sally wrote:
Fri Jan 19, 2024 6:08 pm
Anyway I moved on from it thinking I'd find some more that had this reimagine option, and now I've forgotten which one it was! Duh!
Is it possible you were editing the generated pics in Microsoft Designer? It's yet another way to access DALL-E:
https://designer.microsoft.com/image-creator

It allows to erase objects, remove or blur backgrounds, etc. I don't use it since I'm lucky enough to have a powerful graphics card to do all of this locally.
Little Sally wrote:
Fri Jan 19, 2024 6:08 pm
Do you have any recommendations you might think worth trying?
Like I said I use a local Stable Diffusion setup (https://github.com/lllyasviel/Fooocus) for "reimagining" pictures by inpainting the details in the existing pic. Online models aren't very good compared to fully tweaked ones with LORAs (and no censorship).

Otherwise, I also tried MidJourney and it's simply not as good for sizey content (but for landscapes and portraits it's better than DALL-E)
Thank you, I'll look at these.

The one I mentioned that I first tried and liked, had the option where you could upload a pic (including work of your own) and AI would do interpretations of it. Or reimagining it as they like to term it.

Re: Foreverlurk's AI works

by foreverlurk » Fri Jan 19, 2024 8:06 pm

Little Sally wrote:
Fri Jan 19, 2024 6:08 pm
Anyway I moved on from it thinking I'd find some more that had this reimagine option, and now I've forgotten which one it was! Duh!
Is it possible you were editing the generated pics in Microsoft Designer? It's yet another way to access DALL-E:
https://designer.microsoft.com/image-creator

It allows to erase objects, remove or blur backgrounds, etc. I don't use it since I'm lucky enough to have a powerful graphics card to do all of this locally.
Little Sally wrote:
Fri Jan 19, 2024 6:08 pm
Do you have any recommendations you might think worth trying?
Like I said I use a local Stable Diffusion setup (https://github.com/lllyasviel/Fooocus) for "reimagining" pictures by inpainting the details in the existing pic. Online models aren't very good compared to fully tweaked ones with LORAs (and no censorship).

Otherwise, I also tried MidJourney and it's simply not as good for sizey content (but for landscapes and portraits it's better than DALL-E)

Re: Foreverlurk's AI works

by Little Sally » Fri Jan 19, 2024 6:08 pm

I was having a play with that free image creator from Microsoft Bing (doing the tentacle search I mentioned on another thread), and I came across another site which had an option for 'reimagining' pics you've already got, and I was quite impressed with the results. Trouble was I didn't notice it only gave you 5 free tries before asking for a monthly payment (or yearly). But it did give quality results. Anyway I moved on from it thinking I'd find some more that had this reimagine option, and now I've forgotten which one it was! Duh!

I did come across another free one called Stable Diffusion (I think), but the results on that were horrible with a lot of deformity of hands and other stuff.

Do you have any recommendations you might think worth trying?

Re: Foreverlurk's AI works

by foreverlurk » Sun Jan 14, 2024 6:45 pm

who renders 3d wrote:
Sun Jan 14, 2024 6:39 pm
Fantastic! I love the two goth girls. But i guess some with a foot fetish combined with a mathematics fetish will get nightmares from the girl on the desk
What, you don't have three "minus" operator on your calculator? :lol:

Re: Foreverlurk's AI works

by who renders 3d » Sun Jan 14, 2024 6:39 pm

Fantastic! I love the two goth girls. But i guess some with a foot fetish combined with a mathematics fetish will get nightmares from the girl on the desk

Top