The initial image was generated with Nova 3DCG with InstantID that used a korean-like girl as the subject. The image was then upscaled with RELH (by AkioAI), which gave it a more doll-like aesthetic. I'm quite happy with how the kitchen turned out and the overall composition. The leg pose is very feminine, and the tilted camera angle is pretty neat ^^
Did a *LOT* of inpainting on this one, and I'm really happy with the finished product! Apparently It's really difficult to prompt for tongue-in-pussy cunnilingus, who knew?
Thanks for info, request added. Also, may I indulge in the logic behind barring users from making such edits themselves? Manual process seems counterintuitive at the first glance. Or at very least, manually deleting the authored posts?
If we allowed users to replace their own posts, one could easily do vandalism with it, such as first uploading something else to get it approved and then replacing it with something completely different. Also, a regular user does not necessarily know what is considered a minor edit what should be a different post.
Manual deletions is also a bad idea since AIBooru is not strictly a self-upload site. A user could upload some other artist's posts and then delete them.
If the edits are minor, you can ask for a replacement in topic #172. If the edits are too big for the criteria, you can just upload it as a new image and use parent/child relationship between the two (help:post relationships).
Thanks for info, request added. Also, may I indulge in the logic behind barring users from making such edits themselves? Manual process seems counterintuitive at the first glance. Or at very least, manually deleting the authored posts?
I'll oblige as much as my lazy ass is capable of :) Also, is there any way to edit the image content of post? I noticed several errors and Photoshopped em out. Might as well upscale even more, Illustrious works quite well with Unity Controlnet.
If the edits are minor, you can ask for a replacement in topic #172. If the edits are too big for the criteria, you can just upload it as a new image and use parent/child relationship between the two (help:post relationships).
Wow, a mothgirl with (semi) accurate moth wings and antennae who's also hairy? Might be my new favorite pic on this site.
(Please make more, preferably with non-transparent wings)
I'll oblige as much as my lazy ass is capable of :) Also, is there any way to edit the image content of post? I noticed several errors and Photoshopped em out. Might as well upscale even more, Illustrious works quite well with Unity Controlnet.
I cannot recreate this. Are you using a lora / where can I find the bad-hands-3 and easynegative? Great gen btw.
Tbh man I don’t really know what I’m doing yet at this point and I usually just completely rip the negative prompts from people I see with really good stuff. I don’t even have any lora for either of those negative prompts and I didn’t use any lora for this. And thanks for compliment, learning new stuff literally every day thanks to others on here.
Insane how this is possible, i mean it's not really good but how everythign kinda fits together is pretty neat, could be a great moodboard for a real animation. Pretty impressive still, is the music AI too?
So I feel like I should probably comment on this, as we've been exchanging messages with @adelinesinclair4 for the last week or two.
First, let's make something perfectly clear - you're not upset about the loli/shota. You've been here and seen those posts for a while, if you thought they were that disturbing, you would've at least switched that setting back to default so as not to see them on a daily basis. But you messaged me today with a screenshot of a bunch of recent loli posts, so that's not the case. Not only that, at one point you literally told me (and I'm sorry that I have to quote a private conversation, but it's just very relevant here):
My argument here isn't even "Hey this website shouldn't have CP on it" My argument is "I shouldn't be sitting here considering posting CP to compete with everyone else, because the bar is sooo much lower for it"
So no, it's not the lolis. Your primary grievance is that your posts are not getting approved. I tried telling you multiple times to just spend a few minutes fixing them, because they're getting rejected for specific reasons (bad fingers, etc.) but you didn't wanna hear it. Instead, you were focused on how you're being treated unfairly and that surely this must be a conspiracy by the NHK/CERN. Eventually you decided to request a replacement for a couple of your posts, but those were just the ones with obnoxious big banners; in other words, all you did was post the original images without the added text - you couldn't be bothered to actually sit down and fix any issues with the images themselves, so you just chose the option that required no additional work.
I don't know what to tell you - you seem convinced that your posts are very good and should be approved. When people don't share that sentiment, you throw a tantrum and start looking for excuses not to fix them. With that attitude you're not gonna get far, I'm afraid.
Sexy. Will always have a soft spot for classic Cammy with her thong leotard, especially with it's famed tendency to wedge up on her like that^. Purely erotic.......
It says img2img in the meta data, so we dont know how much of it is classic digital art and how much AI, but yes this is very nice and creative , very hard to do without controlnet
it says img2img when you use "enchant" function that is basically just sd upscale.
Thanks, I got my start yesterday watching a video from early 2023 and didn’t realize this field moves at light speed. I recently got better models that don’t have this problem and make much better art. I’ll post some of the stuff I made tomorrow. Thank you for the reply.
Oh boy, there's a long road ahead for you, full of delicious knowledge. In short: it's a variational autoencoder. In this context, it's a thing that enhances the generated picture. In this case, it's gonna make it so picture won't look desaturated. As for how to use it - it depends on what are you using to generate pics.
Thanks, I got my start yesterday watching a video from early 2023 and didn’t realize this field moves at light speed. I recently got better models that don’t have this problem and make much better art. I’ll post some of the stuff I made tomorrow. Thank you for the reply.
What is that? Literally just started yesterday and was using this model a tutorial told me. Can you explain that a little more? Whenever I used this model it always seems to come out like that. It’s my favorite model when it comes to the actual art but the coloring looks kinda bad. Here’s the model I was using btw: https://civitai.com/models/135440/breakdomain
Oh boy, there's a long road ahead for you, full of delicious knowledge. In short: it's a variational autoencoder. In this context, it's a thing that enhances the generated picture. In this case, it's gonna make it so picture won't look desaturated. As for how to use it - it depends on what are you using to generate pics.
