Read the version details and recommendations in the "About this Version" section first.
LoRA, trained at Civitai based on furry artist DUO
or known as PandionProductions / Big Red Pandion
Support the artist using these links:
https://www.patreon.com/PandionProductions
https://www.furaffinity.net/user/duo/
https://picarto.tv/DuoTheSkunk
https://www.twitch.tv/povertyping
1) Always use the tag by duo
2) This LoRA was based on the Pony V6 version
3) Even though the Pony V6 base model is used, some other models may have some inconsistencies in the images, especially in the eyes and hands, if used in Civitai, use some Embedding / Face Fix to get better results. For those who use Comfyui, the best results will be with some Hirefix / DDetailer to improve the image of the character's face.
4) Don't forget to use tags related to the Pony model
score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up,
5) LoRA weight change in Civitai is at your discretion
6) Add the more details tag to the positive prompt to obtain a better effect of shadows and details in the images simulating the author's art, add these same tags in the negative prompt to remove these effects
7) Add the monochrome, greyscale, sketch tag to the negative prompt if you want colored images, as LoRA was composed of black and white images or just one color palette
8) Check first for a model compatible with your chosen image, some models affect Lora in the final result of the image generation for some types such as: furry, human, realistic images, etc. Therefore, the same model may not always be suitable for different types of images.
9) If you want to force the image generator to use the Lora weight you chose, use the following tag in the positive prompt:
<lora:DUO_Style_Lora:0.8>
Note: the number at the end of the Lora name (0.8) refers to the Lora weight. In image generators, we have a weight slider, but if you want to "force" it, use the same number as the image generator slider in the positive prompt, for example:
Civitai slider = 0.8 positive prompt: <lora:DUO_Style_Lora:0.8>
10) I added tags related to the artist's best-known characters, if you want an image close to the character, don't forget to enter the character's name, I will leave examples of prompt positive right below each character:
Tiffany Valentine
score_9, score_8_up, score_7_up, by duo, more details, tiffany valentine, snow leopard, felid, pantherine, female, furry, anthro, pink eyes, blonde hair, long hair, lipstick, big breasts, huge breasts, ear ring, ear piercing, gloves (marking), heart (marking), leg markings, markings, mature female, mature anthro, multicolored body, multicolored fur, piercing, pink areola, pink nipples, pink nose, ring piercing, spots, spotted body, spotted fur, tan body, tan fur, two tone body, two tone fur, pink lipstick, voluptuous, wide hips, 1girl, solo, *****, anus, ass, hat, furry, earrings, furry female, jewelry, lying, hoop earrings, palm tree, tail, ass focus, looking at viewer, on side, outdoors, leopard print, day, looking back, from behind, tree, beach, smile, straw hat, half-closed eyes
Rosalicia
score_9, score_8_up, score_7_up, by duo, rosalicia, avian, bird, flamingo, furry, female, anthro, elderly, elderly female, big breasts, huge breasts, mature, mature female, mole (marking), mole on breast, slightly chubby, thick thighs, voluptuous, wide hips, purple body, purple fur, green eyes, beak, pubes, black background, 1girl, breasts, furry female, solo, furry, tail, green eyes, ass, body fur, from behind, snout, holding, huge breasts, smoking pipe, claws, animal ears, sideboob, hand up, standing, dress, holding smoking pipe, looking back, choker, mole under eye, no panties, bare shoulders, yellow clothing
Samantha Sundstrom
score_9, score_8_up, score_7_up, by duo, more details, samantha sundstrom, lagomorph, leporid, rabbit, furry, female, anthro, big breasts, black lips, blonde hair, blue eyes, huge breasts, hyper, hyper breasts, mature female, nipples, older female, tan body, tan fur, thick bottom lip, curvy figure, pubes, 1girl, breasts, furry, nipples, solo, furry female, animal ears, blonde hair, nude, snout, animal nose, long hair, pubic hair, female pubic hair, thick thighs, thighs, looking at viewer, wide hips, curtains, tree, large areolae, dark nipples, body fur, day, curvy, standing, lips, towel
Liam
score_9, score_8_up, score_7_up, by duo, liam, ailurid, felid, hybrid, lion, pantherine, red panda, green eyes, beard, big balls, big penis, eyebrows, facial hair, fangs, fluffy, fluffy tail, goatee, huge balls, neck tuft, penis, penis accessory, penis bow, penis ribbon, red body, red fur, red hair, tuft, teeth, vein, veiny penis, overweight, overweight male, tail, tail markings, male focus, bara, 1boy, penis, muscular male, brown fur, solo, muscular, pectorals, stomach, nipples, animal ears, furry male, nude, thighs, feet out of frame, furry, uncensored, abs, male pubic hair, tail, completely nude, testicles, navel, thick thighs, pubic hair, thick eyebrows, large pectorals, looking at viewer, barn, indoors, precum drip, excessive precum, hands on waist
Below is an initial configuration, but any other type of configuration is up to you: Model
Pony Diffusion V6 XL - V6 (Start with this one)
Lora
GreasyMojo Style Lora - 0.5 ~ 1.0 (Preferably 0.8)
Advanced
CFG Scale - 3.0 ~ 9.0 (Preferably 7)
Sampler - DDIM / Euler a / Euler / Heun / DPM2 / DPM++ 2M Karras / Uni PC (Preferably Euler a)
Steps - 20 ~ 60 (Preferably 30)
Clip Skip - 1/2
VAE - SDXL VAE
Prompt (Positive)
score_9, score_8_up, score_7_up, by duo, more details, horse, equid, equine, 1girl, breasts, solo, furry, furry female, jewelry, ring, animal ears, snout, pool, brown hair, sunglasses, nude, *****, huge breasts, female pubic hair, book, tail, pubic hair, large areolae, nipples, eyewear removed, dark nipples, sagging breasts, cup, long hair, earrings, lips, thighs, smile, lying, tail, dark skinned female, beach chair, pool, outdoors, smile, red lipstick, brown eyes, long hair, big nipples
Prompt (Negative)
zPDXL3, 3D, 2D, monochrome, grayscale, sketch
As this model is based on Pony Diffusion there's not much need to specify anything in the negative prompt, because the Pony model is very flexible, but I always leave the zPDXL-neg tag (https://civitai.com/models/332646/pony-pdxl-negative-embeddings).
General Observations:
If possible, give credit to the author DUO while using this LoRA.
Do not sell or commercialize this LoRA
Do not remove metadata from images generated by LoRA.