I noticed something funny while I was looking for terms to tag this image, the AI tried to generate another two female figures on the wall, one lay down to the left of her head with recognizable boobs and the other one to the right close to her hip, with a recognizable head, face and torso, fascinating and a little bit creepy.
The embedded prompt is very similar to the one used for the initial generation, but this piece took a few steps of inpainting to get many of the surrounding details to be coherent.
it is possible that this illustration was created using Img2img, you know, AIs like NAI have the option to insert an image (sketch or not) and then the AI redraws over it. It is very useful to generate new faces, or in case you want a very specific pose.
It's a futa/newhalf LoRA I trained. Unfortunately, it was pretty overfitted and couldn't do much aside from "from behind" tags, so I got rid of it. I trained a new LoRA that is overall more consistent with other poses as well, and can still do "from behind" tags. Here's the folder: https://mega.nz/folder/XMgjVDja#hSYAT_EsNSokys7oAIKm2A
Your new lora is amazing,it didn't even change my style!Thanks again!
Hey, i'm going crazy trying to get something close to your image. Even using the data you provide, i can't get nothing similar. I'm also using zankuro_e6, concept_pronebone and pyramithrapneuma, but no matter what values i assign, my images look nothing like yours. ¿Can you give me some clues?
Also, thanks for your amazing work!
Hi. I am not using zankuro_e6 in this image. Maybe that is the reason why you can not get something similar. Are you using AOM2?
You can find it on Novelai.net. I have a paid subscription, but I think it's worth it. On the image generation screen there should be an option to choose between three different diffusion options. All you have to do is choose the furry model and you're in business 👍 Feel free to use my images to get started
I prefer to use the UI driven stable diffusion, the ones online are often way to limiting for me, i do appreciate the recomendation though.
any idea were i can find the furry version of novelai?
You can find it on Novelai.net. I have a paid subscription, but I think it's worth it. On the image generation screen there should be an option to choose between three different diffusion options. All you have to do is choose the furry model and you're in business 👍 Feel free to use my images to get started
This is purely the Novelai furry model. I used the plms sampling which produces some damn good results after you tweak the settings. I enhanced the raw output and this is what I got (I'm pretty new at this so hopefully that made sense lol)
is this a merged model?? and if so witch models did you use??
This is purely the Novelai furry model. I used the plms sampling which produces some damn good results after you tweak the settings. I enhanced the raw output and this is what I got (I'm pretty new at this so hopefully that made sense lol)
It's a futa/newhalf LoRA I trained. Unfortunately, it was pretty overfitted and couldn't do much aside from "from behind" tags, so I got rid of it. I trained a new LoRA that is overall more consistent with other poses as well, and can still do "from behind" tags. Here's the folder: https://mega.nz/folder/XMgjVDja#hSYAT_EsNSokys7oAIKm2A
Really apreciate,You're my god! Can't wait to see your next work.
It's just a mix I made myself. Click the AnyDream tag to get info on how to make and use it. This image in particular was a variant using a 50/50 mix of Dreamlike and SimpMaker3k1.
Fantastic imagery. What is the model exactly? I've never heard of Anydream.
It's just a mix I made myself. Click the AnyDream tag to get info on how to make and use it. This image in particular was a variant using a 50/50 mix of Dreamlike and SimpMaker3k1.
The best one from behind i ever seen,besides,i’m curious about the second Lora “epoch-000016” you used,what is it used for？
It's a futa/newhalf LoRA I trained. Unfortunately, it was pretty overfitted and couldn't do much aside from "from behind" tags, so I got rid of it. I trained a new LoRA that is overall more consistent with other poses as well, and can still do "from behind" tags. Here's the folder: https://mega.nz/folder/XMgjVDja#hSYAT_EsNSokys7oAIKm2A
Hey, i'm going crazy trying to get something close to your image. Even using the data you provide, i can't get nothing similar. I'm also using zankuro_e6, concept_pronebone and pyramithrapneuma, but no matter what values i assign, my images look nothing like yours. ¿Can you give me some clues?
