AI images

  • Guest, it's time once again for the massively important and exciting FoH Asshat Tournament!



    Go here and give us your nominations!
    Who's been the biggest Asshat in the last year? Give us your worst ones!
Kharzette

Kharzette

Watcher of Overs
5,445
4,411
I've been having better luck lately with hands with the negative prompt bits
Code: 
extra fingers, crooked fingers, mangled hands

Might be coincidence, but I'm keeping it in my usual negatives.
 
  • 1Like
Reactions: 1 user
Vuuxo

Vuuxo

Karen
<Gold Donor>
1,214
5,345
Mist said:
It's all actually anime's fault. Anime is the metavirus of degeneracy that broke down the doors for all the rest.
Click to expand...
I've been saying this shit for years!
The Asian invasion and anime are 100% responsible for it all. Reinforced by fucking tiktok and other social communist media.
 
Bandwagon

Bandwagon

Kolohe
<Silver Donator>
24,674
66,338
1708234443327.png
 
  • 4Like
Reactions: 3 users
Kharzette

Kharzette

Watcher of Overs
5,445
4,411
I've been doing runs of 100 on a prompt to try to achieve an effect I've seen in anime, probably ghost in the shell, where you can see the contents of a screen reflected in the eyes of the subject.

Didn't get any of that really, but I did get some very unusual / interesting results:

Several have this strange sort of double eyelid:
22173-1954837405-closeup portrait of the eyes of a beautiful Nordic girl, coding on a powerful...png
22165-1954837397-closeup portrait of the eyes of a beautiful Nordic girl, coding on a powerful...png


Some have these distorted sort of fish eye lense look:
22091-1954837323-closeup portrait of the eyes of a beautiful Nordic girl, coding on a powerful...png


These have a bit of reflect but not really what I wanted, but I like the image overall:
22178-1954837410-closeup portrait of the eyes of a beautiful Nordic girl, coding on a powerful...png


Weird pupils on this one, looks like a pair of lungs, with a sort of armour:
22106-1954837338-closeup portrait of the eyes of a beautiful Nordic girl, coding on a powerful...png
 
  • 6Like
Reactions: 5 users
Bandwagon

Bandwagon

Kolohe
<Silver Donator>
24,674
66,338
All of the reality TV shows lately that feature people with down syndrome got me thinking about what other genres would be good with an all-downs cast. I thought a down syndrome wizard would be hilarious, but Bing wasn't cooperating....

OIG4.iTlqjv3yPcbpok.jpeg
OIG4 (23).jpeg
OIG4 (22).jpeg
 
  • 4Like
  • 1Worf
Reactions: 4 users
Palum

Palum

what Suineg set it to
27,812
44,618
Fadaar said:
can you AI up a future where George RR Fatfuck finishes his books?
Click to expand...

Impossible, AI can only comprehend various reflections of reality. What you ask for is outside the scope of human experience and therefore beyond the ken of AI.
 
  • 1Like
Reactions: 1 user
Kharzette

Kharzette

Watcher of Overs
5,445
4,411
I wonder if someday we'll have chatbots with no prompt size limits. You could just paste all the completed books and ask it to write the finale.

Pic unrelated
22322-4096871889-closeup portrait of the eyes of a beautiful Nordic girl, near a powerful comp...png
 
  • 2Like
Reactions: 1 users
Bandwagon

Bandwagon

Kolohe
<Silver Donator>
24,674
66,338
Masakari said:
Sora is too much.

Click to expand...

Safety​

We’ll be taking several important safety steps ahead of making Sora available in OpenAI’s products. We are working with red teamers — domain experts in areas like misinformation, hateful content, and bias — who will be adversarially testing the model.
For example, once in an OpenAI product, our text classifier will check and reject text input prompts that are in violation of our usage policies, like those that request extreme violence, sexual content, hateful imagery, celebrity likeness, or the IP of others. We’ve also developed robust image classifiers that are used to review the frames of every video generated to help ensure that it adheres to our usage policies, before it’s shown to the user.

We’ll be engaging policymakers, educators and artists around the world to understand their concerns and to identify positive use cases for this new technology. Despite extensive research and testing, we cannot predict all of the beneficial ways people will use our technology, nor all the ways people will abuse it. That’s why we believe that learning from real-world use is a critical component of creating and releasing increasingly safe AI systems over time.
Click to expand...
 
You must log in or register to reply here.