DudeWTF
I don’t want to encourage that. I otherwise thought the output was kinda interesting perspective and cute. However, I am removing this to avoid pushing the grey area. I was just going to add my previous and this one as a humorous “getting started with AI” kinda thing. These were the best of the first several dozen failures before they got better.
Agreed, but it is my first exposure to image generation. I’m curious if I want to try and build a comp and setup for non porn applications. I don’t have the API or even know what models/LoRA are loaded on the instance. I’m just feeling out what is and is not possible intuitively. Just getting the instance to show a pussy was an initial noob challenge. I’m just hacking around. Seems better than much of what I’ve seen posted here. Might be my tastes, might be because the instance is so rate limited the parameter changes are more thought out than I might do on my own hardware. You wouldn’t believe the nonsense I’ve seen when trying to specify better detailed female anatomy with this instance host.
The hosted instance that generated the image (not mine) is hard to tweak for what “skinny” means, and even if it will generate an output that uses the term. I have no way to analyze anything but the parameters and image and am rate limited to a free account. Like, if you read the parameters the image should be completely different, but it did its own thing. I only post for others that may need baseline ideas and maybe seeds to start from. All of these are so deep in the noise that it is unlikely they can be pushed any further. I just wish I had more easily accessible example sources that could work on this hosted instance. If I feel this way, others may too. So posting can maybe help them.
That said, the big legs are probably the biggest error in the image, but I’m calling it perspective lens distortion and posting it bc I think it’s pretty.
These are alternates for this post and notes for a few others that were not worth posting on their own. These notes and posts may be silly if your perspective is someone hosting your own software where iteration takes a few seconds. For someone online, on a rate limited account, the perspective is very different.
This is what “tan lines” really does on this instance. It just doesn’t work and becomes clothing like tan bikini bottoms.
This is (very loosely) “leaning back with arms behind back resting on elbows” taken WAY out of context.
Crazy, broken looking results from trying to force a better labia than this instance is capable of producing.
(Loosely)“Fishnet stockings and heels only, with a pink pussy.”
Is anyone here using SD with Blender or for stuff other than NSFW too? Looking to see if a laptop embedded RTX 4050 or 4060 is viable? What is the real limit here? Like can anyone tell me something like “8gbv just can’t do (XYZ)” or the iteration time becomes so long the workflow is not practical/sw crashes. Anyone running Linux on a 4050/4060? What kind of impact is there with storage speeds, what size of DDRx is used in practice?
Why not require a negative prompt leading with child, kid, in the first 10 words? I’m not good at writing a bot, but it might even be possible to intercept images to check that this exists in the meta data before Lemmy wipes it…maybe. It might exclude a few ups, but it would greatly reduce the moderation load.