If I were offered $75k to have 1 kid, I’d still have to turn it down.
If I were offered $75k to have 1 kid, I’d still have to turn it down.
deleted by creator
If you get just the right gguf model (read the description when you download them to get the right K-optimization or whatever it’s called) and actually use multithreading (llamacpp supports multithreading so in theory gpt4all should too), then it’s reasonably fast. I’ve achieved roughly half the speed of ChatGPT just on an 8 core amd fx with ddr3 ram. Even 20b models can be usably fast.
This probably isn’t very helpful but the best way I’ve found to make an ai write an entire book is still a lot of work. You have to make it write it in sections, pay attention to the prompts based on what’s happening and spend a lot of time copy pasting the good sentences into a better quality section and then use those blocks of text to create chapters. You’re basically plagiarizing a document using ai written documents rather than making the ai shit it out in 1 continuous stream.
If you could come up with a way to make an ai produce a document using only complete sentences from other ai generated documents, maybe you could achieve a higher level of automation and still yield similar quality. Because otherwise it’s just as difficult as writing a book yourself.
As for software, use llamacpp. It’s a cpu-only ai thingy that can utilize multiple cores. You probably aren’t getting an nvidia gpu running on any arm board unless you have a really long white neck beard and a degree in computer engineering. Download gguf compatible models for llamacpp on hugging face.
I thought I never used it until my right shift key stopped working. I then found out that I use that thing a lot actually.
Any self hosted ai thing. I recommend llamacpp because it’s the easiest to set up. Gpt4all is a ui solution that runs on top of llamacpp that would also be an excellent choice. All you have to do is download any gguf compatible model from hugging face, figure out what command line options you need for multithreaded operation and to load your custom model. If you want one that’s actually loyal and is less likely to be pushing some agenda, make sure it says it’s uncensored. Even if you’re not doing porn or ai girlfriend stuff you still want it to be uncensored or else it will be as disloyal as chat gpt. Note that uncensored and nsfw are 2 different thing so if you actually want an ai girlfriend or a shitpost generator, it needs to be both uncensored and nsfw.
Same story with image generation ai. Use easy diffusion for self hosting and download whatever models you want, nsfw or otherwise from civitai.
Don’t bother with online ai services, they are trash.
deleted by creator
You can always download something like llamacpp or gpt4all and plug in any gguf-compatible nsfw model from hugging face. OpenAI are a bunch of wankers that dont deserve your cum.
I’ve had the best luck so far with easy diffusion for doing home rolled ai porn. It comes with the stable diffusion 1.5 model and despite its name, it actually has the largest selection of settings I’ve seen in a self hosted one. Not interested in using something not self hostable. Results aren’t too great but better than nothing. I’ve made a handful of good full frontal nudity ones. I have not experimented with lora or other easy diffusion compatible models. I’ve had absolutely no luck with getting controlnet to do anything in a satisfactory level of quality besides the wiki examples. It might just be because I don’t know what I’m doing that well though.
If anyone has a better idea that involves self hosting only, be sure to comment because I doubt that what I’m doing the best that can be done.
Probably a shittier version of zlibrary and libgen that probably costs money
Try not to cum challenge (impossible)
If OP’s results are anything like mine, there’s probably like 20 really fucked up ones and this was the cream of the crop least fucked up one. There were probably some other reasonably good ones that didn’t get posted just because the hands were even shittier looking or they were front shots that showcased fucked hands or a messed up facial expression.
Actually I got an nvidia card working on easy diffusion on Debian. The barrier for getting a text chat ai working with gpu acceleration is actually the fact that I don’t have the patience to deal with all that python venv nonsense so I use llamacpp. It runs in c++ which means no python dependencies to fuck you with at the cost of slower cpu-only generation.
Easy Diffusion just happens to be simple enough that I could actually figure out how to get it to work (it’s in python and needs a virtual environment) but it’s a different story for the text ais.
If you actually had the patience and knowledge to deal with all the python issues and/or had a distro that makes it easy (different distros deal with pip differently), I don’t doubt you’d be able to get Nvidia card acceleration working on some text chat ai.
deleted by creator
I typically stay away from those other ones like thc-V or thc-o or whatever but where I live it’s a lot safer to buy delta 8 at a smoke shop than to do what it takes to aquire real weed so I just go with that. The gummies they sell have delta 9 in them though.
Meh, they’re never going to give in to any demands under any circumstances so the next best thing you can do (besides doing something more productive with your life) is do it for the memes.
Just think if they hacked them trying to get the government to enact free healthcare or lower taxes, the outcome would have been the exact same.
If I woke up as a woman one day I’d get a camera and a mirror and take nude pictures all day for later “reference”. I’d be pissed if this were a permanent thing I could see it getting really old really quickly. It’s just not the same if I can’t use my penis while using my reference material.
What did he get arrested for though? Was pooping in public thr part that was illegal or is doing it on a dead possum considered animal abuse?
Get naked and stare at myself in the mirror I guess
I don’t really subscribe to the whole if civilization collaspes there will be no technology in anyone’s lifetime again thing. You aren’t going to go back to ordering shit off amazon from your smartphone or anything. However the knowledge that things like refrigeration, radio transmission, internal combustion engines, water treatment and such are possible is going to drive people to eventually find out how to get it by any means necessary.
How quickly this happens is a question of whether the majority of people adopt a “technology is too dangerous/a sin against God” idealogy or not.