Nova Animal XL
A realistic furry checkpoint model that can have great details on any type of furs, scales and feathers, which aims to be XL-lized Persika Furry
Rules
You cannot use the generated images for commercial use if it's not edited (or just turning it to black and white)
Advertising is always welcome
Recommended settings
Sampler: Euler a
Steps: 20-40
(Pony)
CFG Scale: 6-7
Prompt: score_9, score_8_up, score_7_up, BREAK, furry, anthro, detailed face eyes and fur, {Animal Type}
Negative Prompt: score_6,score_5,score_4, source_anime,source_cartoon, 2d, art, cartoon, blurry, jpeg artifacts, username, watermark, signature, normal quality, worst quality, large head, low quality, text, error, missing fingers, extra digits, fewer digits, bad eye
(Illustrious)
CFG Scale: 3-6
Prompt: masterpiece, best quality, amazing quality, very aesthetic, high resolution, ultra-detailed, absurdres, scenery, photo, realistic, furry, anthro, {Prompt}, BREAK, depth of field, detailed fluffy fur, photorealistic details
Negative Prompt: smooth skin, human, multiple tails, 2d, art, old, oldest, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured, long body, lowres, bad anatomy, bad hands, missing fingers, extra digits, fewer digits, very displeasing, (worst quality, bad quality:1.2), bad anatomy, sketch, jpeg artifacts, signature, watermark, username, simple background, conjoined, bad ai-generated
Description
Realistic details extended from Illustrious v2.0
NoobAI EPS v1.1 + Illustrious v2.0 stable DARE applied
FAQ
Comments (15)
Difference between A and B:
A is more on expression, B is more on realistic
Thank you so much for telling us this!
Great work!
Illustrious V4 series are a bit difficult on I2I. But I guess that's the price of fluffy fur. Great base image generator here
What is the difference between 4a & 4b?
@Crody Thanks
This is the best furry model from V1 to today (illustrious). Next, I explain why this is so.
➤ Prompt execution: it doesn't matter if you are a beginner or already think like an AI, these models will fulfill your prompt up to 90%.
➤Simplicity and convenience: this is actually a modern model that perfectly understands triggers in various forms, including live speech (but it's better to use the Danbooru language).
➤Furry generation: This model allows for a minimal number of errors compared to other models such as human body parts (human hands, fingers, ears, body etc.).
➤Detail, background, and overall appearance: If you don't get lazy and write down things like foreground, middle, and background, then you'll have great detail and a solid composition (I'm using 12 steps with Euler A to generate base picture lol). But if you're still too lazy to describe the background details, then V4 is better than V1 and V2.
➤I won't whine about the fur, it's just never enough for me. (I hope they'll give me some advice on this cause because even Furry Enhancer and KFT Furropean Extreme not well helping me. Maybe the reason is in different samplers).
This model gave me so much pleasure, you can't imagine it. Thank you @Crody 💜
A small addition. 90% of my work is based on this model. I mentioned the other two models in my artwork just to get more attention. One is just random and popular, and the other is to pay homage to the creator (forgive me Crody).
Yeah furry models are usually superior with distinguishing anatomy for some reason.
I'd theorize maybe it's due to the very specific E621 tags for hands, feet, fingers, toes, etc.
amazing :)
Кто создал эту модель, я руки целовал бля!
Definitely one of the best, if not the best, currently available furry models.
My dear friends, if you are generating images using your PC or something like that, then here is a little advice on how to achieve more stable diffusion.
https://civitai.com/articles/15616/one-trick-when-working-with-a-nova-animal-xl-with-sd-controlnet