SDXL
SDXL
https://civitai.com/models/601594
UPDATE:
The newest model which I am currently working on the showcase while writing this is an NOOBAI model, Since I've noticed that most models based on NoobAI either are good at showing males, females, femboys etc and have a less than optimal style, or they have a good Style like Indigo or Nova but they have a trash ability to show Males, females and femboys and instead they either make everything Bara or just make it female. So I hope to fix that problem with this model! Acai Overdose Beta is a WIP, I am hoping I can get the quality better than it is but it's at the point where I think it's a decent model, considering how it can do many body types since most models are biased towards the stereotypical female body or the stereotypical male body and sometimes failed at prompt adhearence
Model Information:
A Model made as the successor to my SD1.5 model line called Furation, which was designed to mimic the same style of SD1.5 with everything from SDXL and PonyXL that makes it better than SD1.5. it's meant to have a 2.5D style by default but it can do many styles, I just personally love the 2.5D style. There also is a Noob Version which is currently in BETA since Idk if it's even good.
Prompting:
Noob:
Positive: masterpiece, best quality, amazing quality, very aesthetic, high resolution, ultra-detailed, absurdres, newest, scenery, furry, anthro, detailed background, detailed hair, depth of field, detailed fluffy fur, photorealistic details, volumetric lighting, BREAK
Negative: human, multiple tails, modern, recent, old, oldest, graphic, cartoon, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured, long body, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, very displeasing, (worst quality, bad quality:1.2), bad anatomy, sketch, jpeg artifacts, signature, watermark, username, simple background, conjoined, bad ai-generated
Pony:
This model has way better prompting so using simple prompt templates like the following:
Positive:
detailed background, detailed foreground, depth of field, soft lighting, volumetric lighting, (kemono), realistic, digital media (artwork), commission, absurd res, BREAK
Negative: malformed, worst quality, bad quality, (ahegao), bangs, bad eyes, messy hair, Can produce Great results even without further prompting, But if you do want some suggestions to get even better images, Use Negative hands and Boring SDXL
Also Just use E621 Tags, you could use any Booru tags but it doesn't work as good with Booru tags.
NOTE: The model is very sensitive but I tried to get it to make a better 2.5D style.
