No Stupid Questions
No such thing. Ask away!
!nostupidquestions is a community dedicated to being helpful and answering each others' questions on various topics.
The rules for posting and commenting, besides the rules defined here for lemmy.world, are as follows:
Rules (interactive)
Rule 1- All posts must be legitimate questions. All post titles must include a question.
All posts must be legitimate questions, and all post titles must include a question. Questions that are joke or trolling questions, memes, song lyrics as title, etc. are not allowed here. See Rule 6 for all exceptions.
Rule 2- Your question subject cannot be illegal or NSFW material.
Your question subject cannot be illegal or NSFW material. You will be warned first, banned second.
Rule 3- Do not seek mental, medical and professional help here.
Do not seek mental, medical and professional help here. Breaking this rule will not get you or your post removed, but it will put you at risk, and possibly in danger.
Rule 4- No self promotion or upvote-farming of any kind.
That's it.
Rule 5- No baiting or sealioning or promoting an agenda.
Questions which, instead of being of an innocuous nature, are specifically intended (based on reports and in the opinion of our crack moderation team) to bait users into ideological wars on charged political topics will be removed and the authors warned - or banned - depending on severity.
Rule 6- Regarding META posts and joke questions.
Provided it is about the community itself, you may post non-question posts using the [META] tag on your post title.
On fridays, you are allowed to post meme and troll questions, on the condition that it's in text format only, and conforms with our other rules. These posts MUST include the [NSQ Friday] tag in their title.
If you post a serious question on friday and are looking only for legitimate answers, then please include the [Serious] tag on your post. Irrelevant replies will then be removed by moderators.
Rule 7- You can't intentionally annoy, mock, or harass other members.
If you intentionally annoy, mock, harass, or discriminate against any individual member, you will be removed.
Likewise, if you are a member, sympathiser or a resemblant of a movement that is known to largely hate, mock, discriminate against, and/or want to take lives of a group of people, and you were provably vocal about your hate, then you will be banned on sight.
Rule 8- All comments should try to stay relevant to their parent content.
Rule 9- Reposts from other platforms are not allowed.
Let everyone have their own content.
Rule 10- Majority of bots aren't allowed to participate here.
Credits
Our breathtaking icon was bestowed upon us by @Cevilia!
The greatest banner of all time: by @TheOneWithTheHair!
view the rest of the comments
It would be nice if all NSFW was annexed to their own instance and left out of generally populated ones. There’s no need for it to be side-by-side with generalized content.
You seem to not grasp how this federation thing works. All servers which are not actively blocking the NSFW instance will see it as well.
Funny thing is that AI tech is turning NSFW into one of the best starting points and introductions to the subject. I'm all for separating it, but the separation turns out to have its own complexities. After messing with some of the tools, a large chunk of NSFW is from Stable Diffusion. There are certain aspects that are hard to generate and only really apparent with some practice writing prompts. It is far easier to quantify the types of issues that arise from bad prompts using a human body where we are much better equip to detect very subtle mistakes at a glace once we know where to look. It is an easy path into using SD for other endeavors. Admittedly, it ruins a bit of the primal appeal, and totally flips the subject where you're then browsing looking for clever prompting. Funny thing is, the like count often correlates with prompt cleverness rather than output. It is the primary driver of engagement.
No idea what you’re talking about. It’s just picture of naked people. It needs to be in its own place.
i agree, that comment reads like a fever dream. i have no idea what theyre talking about at all.
https://en.m.wikipedia.org/wiki/Stable_Diffusion
This has the most basic guide to what is happening if you wish to crawl out from under that rock. It includes a built in SFW text to image prompt:
https://stable-diffusion-art.com/beginners-guide/
All one has to do is look at the NSFW images marked as being from AI and note the watermark to find where to generate images. Once you make a few, you'll see small problems that are present in many other image categories. The main issues have to do with excluding certain prompt key words to make the output look real, then stuff like genitalia is not easy to get dialed in well unless you are running the software on your own hardware. This requires a powerful video card to generate the images and a lot of storage space. Once you know this a lot of images become obviously AI generated. There are aspects of lighting, eyes, fingers and toes, easy lighting text prompts and other small details that are harder to avoid in the image output. These start to stand out more once you know.
This tech is moving very fast right now. The next iteration of Stable Diffusion is set to release this month and it will likely make it impossible to tell what is real and what is fake. Right now SD must start with a low res image, then it can be scaled higher. SDXL will be able to start with a high res image and modify details which has not been possible. With a bit of effort, it will be possible to modify video frame by frame and use a simple text prompt to alter details. I doubt people will do more than clips at first, but with some good scripting using Blender, I could see it working for larger projects.
Follow the second posted link. And read it. This is FOSS. Combine this with an open source text to text LLVM running on native hardware and you have a real game changing set of technology.
https://generativeai.pub/how-to-setup-and-run-privategpt-a-step-by-step-guide-ab6a1544803e
No one understands how your ramblings are relevant to the OP or even the comment you originally replied to is the thing
"crawl out from under that rock" ya nah im good ill stay right here
They are talking about NSFW images in the fediverse. How does that correlate with AI-generated NSFW images?
Originally, I mentioned how there is more complexity in the NSFW AI space than just the imagery, and that it is actually an interesting tool and introduction to the text to image AI. The mods and users in that space are more positive and supportive than average too.
My main interest in text2img/Stable Diffusion is as a product design tool in Blender. I was hesitant to upgrade a workstation to try out SD, but the NSFW stuff was novel enough give it a try using an internet hosted AI instance. Previously, I tried publicly hosted AI text prompts for product design images, but I didn't think I would be able to make it work for me. Now I have a much better understanding of the tool and how it works. I don't regularly visit NSFW stuff, but an article on Stable Diffusion mentioned how it is easier to learn by starting with generating images of humans because we have an innate ability to identify subtle detail in faces and bodies. And hey, if I'm going to try, why not be a connoisseur.
Like I said, I'm all for keeping NSFW separate. It is just worth mentioning that the prudish stigma attached to anything related to human sexuality, and writing it off as as useless vice is not very intelligent. There is a crossover with useful utility found within this space. I didn't expect to discover this myself based on my prior assumptions and cultural stigma. I wanted to make mention that this exists if others are interested and looking deeper into the NSFW subject/coexistence situation on Lemmy via this post.
Clean up on aisle 5, someone threw up a thesaurus over here