IcedCoffeeMix

https://civitai.com/models/83538?modelVersionId=263020

Version 5.0 of IcedCoffeeMix! Its come a pretty long way over the last 8 or so months! So, whats new? better quality overall, less reliance on quality tags, its significantly easier to generate furries (thats the whole point right?) to the point where its actually harder to generate a raw human without any anthro features. Oh, I finally baked in a VAE, so, you don't need to download one!

So far it's been very versatile, it can do most species in a variety of styles. I highly recommend using it with the add detail Lora (not required, but think of it like a slider between cartoon to 2.5D).

Example prompt for the tracksuit lion image:

Prompt: A beautiful female fennec fox, Labyrinth, (aged brown leather jacket, canvas pants, baggy white undershirt, black collar:1.2) (detailed face, detailed eyes:1.2), stunning gaze, short wavy hair, (Stylized anime artwork, masterpiece, best quality, absurdres, P.A. Works style, solo) by sligarthetiger, by meesh, by avante92, by ashblueflames, by djpuppeh, by personalami, by kenket, by desubox, by gideon, by taran fiddler, by chunie

Negative prompt: blurry, out of focus, worst quality, bad-hands-5, by bad-artist-anime (bad anatomy, extra limbs, extra ears, bad hands:1.2)

Steps: 20 Sampler: DPM++ 2M CFG scale: 6 Clip skip: 6 Seed: 2111518298 Size: 800x1200

Please note that I am using SDNext for my images, so your results will probably not be like mine unless you are using SDNext with the exact same settings as me, I utilize FreeU and HDR Clamp and Center which both affect the final output. If you're not getting the same results as me, that is probably why.

by iDeNoh

ver1.0→https://pixai.art/model/1673112142349520490