V3
A completely new model that is very different from V1 and V2. The dataset was created entirely by me, and the images in it are in very high resolution. Many popular characters were used in the creation, so the faces and body anatomy had to be as close as possible to what we see in anime.
This version has much more contrast, subtle contours, and is perfect for both SFW and NSFW images.
The goal was to create lora that would blend well with other loras and complement the style tags perfectly. This is also great if you simply want to make a beautiful anime screencap image, as without loras at standard checkpoints, anime screencaps often look either hyper-realistic or lacking in detail.
POSITIVE PROMPT: anime screencap, anime coloring
NEGATIVE PROMPT: 3D, realistic
V1 - V2
Created using anime images from the internet. I happily scavenged and edited them, but the low resolution sometimes made the generated images look blurry. Dataset: 200+ images
Description
Improved lighting
Even more anime aesthetic
Better contours
Much better prompt undertanding
NSFW elements very much improved
FAQ
Comments (6)
like it.
Not sure if it always makes the image better, but I got results I like more than without your lora.
how do you do it in such a high resolution 2048x3072 ? i tried with hires fix, but it is broken with high resolutions...
Hi, I use MultiDiffusion method of upscaling in forge neo
I'll send an instruction in private messages
Hey man, great Lora. I use it all the time and I genuinely love it. Do you have any plans to port it over to Krea 2? I understand that's not exactly easy, but I'd love to see a Krea 2 version one day.
Hi, first of all, thank you so much for your feedback. I'm very pleased and glad you like it.
I don't plan on creating loras for KREA2 yet. Anima is currently my main platform for creating content and loras, but that might change in the future <3
@16_5 No problem, for the time being I'll enjoy this on Anima. Anima is still amazing, after all.