Quick note, images were directly ripped from the last post, if you want to remix them just remove the lora labeled as unstable

Not a new model, just organizing my gallery and this was uploaded separately

Meant to imitate the style of Taranima. Some characters are included, check example images. This artist makes highly detailed art, usually involving fetish content like inflation. Support them if you like the style:

https://www.furaffinity.net/user/taranima/

https://www.patreon.com/Taranimart

Example positive:

anthro, back-tie bikini, back-tie clothing, back-tie swimwear, back boob, big breasts, big butt, bikini, blue body, blue fur, blush, breasts, butt, clothing, curvy figure, female, fur, half-closed eyes, straw hat, headwear, huge breasts, huge butt, huge hips, huge thighs, hyper, hyper breasts, looking at viewer, looking back, looking back at viewer, narrowed eyes, side-tie bikini, side-tie clothing, side-tie swimwear, skindentation, small head, solo, standing, string bikini, swimwear, thick thighs, two-piece swimsuit, voluptuous, white clothing wide hips, krystal, canid, canine, fox, mammal, butt grab, tongue, tongue out, green eyes, <lora:Taranima-civ:0.95>

Negative:

muscular, signature,  zPDXL2-neg, young, child,

Config:

Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 128480652, Size: 896x1152, Model hash: 821aa5537f, Model: autismmixSDXL_autismmixPony, Denoising strength: 0.4, Clip skip: 2, ADetailer model: FacesV1Robust.pt, ADetailer confidence: 0.3, ADetailer dilate erode: 4, ADetailer mask blur: 4, ADetailer denoising strength: 0.4, ADetailer inpaint only masked: True, ADetailer inpaint padding: 32, ADetailer model 2nd: hand_yolov9c.pt, ADetailer confidence 2nd: 0.3, ADetailer dilate erode 2nd: 4, ADetailer mask blur 2nd: 4, ADetailer denoising strength 2nd: 0.4, ADetailer inpaint only masked 2nd: True, ADetailer inpaint padding 2nd: 32, ADetailer version: 24.3.5, Lora hashes: "Taranima-civ: b6e85cc12d79", Mask blur: 4, Inpaint area: Only masked, Masked area padding: 32, TI hashes: "zPDXL2-neg: 29dc1b9b1a2b, zPDXL2-neg: 29dc1b9b1a2b", Version: v1.8.0, Source Identifier: Stable Diffusion web UI

If you like this please upload some images - I get buzz for every image + would love to see what you can do with this

Known issues:

• model does well with hyper / inflation content, but sometimes detail is lost on bigger characters

• images were cherry picked, so only one style was present. Therefore some characters won't work

SD 1.5 version was the winning model of this bounty. Created by ckmlai.

Yeah of course it does not look exactly like the artists style, but it does yield some pretty good results.

ckmlai if you want to upload this yourself or want me to take down the post just drop a comment. Thanks again for the model.

SD 1.5 version:

Trained on 217 images with NAI and fluffyrock-terminal-snr-vpred-e132 so you can use with whatever model you like.

Taranimart_full_v1-0-000020 = NAI based and furry checkpoints

Taranimart_FREF_full_v1-0-1-000020 = vpred furry checkpoints

Module type: Full module Lycoris - quality and concepts are up to par with full dreambooth model training, the best format for knowledge retention and style reproduction.

Positives:

furry, furry female, anthro female,

big belly, fat, plump, gigantic breasts,

traditional media, watercolor \(medium\),

Negatives:

watermark, signature, text, url,

Epoch 20 were the best ones from both modules. X/Y testing included.

Examples made with EasyFluff v10 and v11.2, yiffymix v40, fluffyrock-terminal-snr-vpred-e132 (for sanity check), futanari factor, based64 and based64+counterfeit mix