[โ€“] 4 points 2 months ago (2 children)

Nothing is reported to NCMEC and I hope it never will. Some keywords are changed backend and the output is something generic and very well clothed. Trying to bypass it will generate some horror and distorted images in most cases. If you are worried about csam you can prevent it with simple regex using the function beforeGenerate(), constantly erasing the user's suspicious prompt keyword will make them grow tired and give up using your generator.

  • source
  • [โ€“] 3 points 9 months ago

    There are many ways, one simple is to use .replace("and wearing random", ""), so when the random is selected, "wearing random" will be replaced by an empty string "" (nothing). you put it in wAcc in the prompt, like: wAcc.replace("and wearing random", "")

  • source
  • [โ€“] 2 points 1 year ago

    The old bot also says the same thing, it changes the acting between: trying hard to hide while showings signals of fear and discomfort (it's explicit that they are interpreting like chloe in the img), straight up tells the truth with western bias, tells the "chinese truth", try to change de subject.

  • source
  • [โ€“] 1 point 1 year ago (1 child)

    Was Stable Diffusion 1.5, the checkpoints are unknown i guess? somewhere in this forum someone was saying that one of the checkpoints was deliberate, but they are just guesses.

  • source
  • [โ€“] [S] 1 point 1 year ago

    There is, gallery and comments have nsfw, the gallery may be a bit difficult because there's 3 or 4 filters to prevent "accidental viewing", but the comments not, people always asks "what prompt to make a woman doing that" or "how to make big sticks", that's why the 'self-warning' is in there and it exists before this automatic content warning.

  • source
  • parent
  • context
  • [โ€“] 3 points 1 year ago (2 children)

    Ok after some tests, "aesthetic" is not needed, just use numbers, and it works only for anime, even illustrations or 3d-ish do not seems to work. Here the tests: number scores

    Also the model was updated somewhere after june 30th, and I'm not saying it because "i feel the images are better now", but because ALL seeds before that date are -very- different, not the same usual difference that seeds already have, but a complete change between all variations from before X all variations now.

  • source
  •  

    Open my generator in private mode: https://perchance.org/ai-art-generator-advanced, there's no content, the page is almost blank, but it is labeled as NSFW, I deleted everything over 8 hours ago before creating this post. Edit: I had to put the gen back to normal because there are people who uses it. But I took a screenshot, look, there's nothing nsfw:

    Another problem that i will just copy paste from another comment: "the 'Content Warning' should detect when the 'nsfw words' are from the generator content warning, if i put a warning message i get another and then the gen is set automatically to private and the meta don't appears on google... But if i remove the message from my page, that have potential nsfw content created by others or that can be found in searchs, then the message is gone and now i have a generator with nsfw content without any message..."

    The problem could be solved by using an imported page, so I can put lists and regex to prevent people from creating nsfw without being punished for it... But things are different with the Ai art generator advanced, is there any way to solve this?

    view more: next โ€บ