Read the version details and recommendations in the "About this Version" section first.

LoRA, trained at Civitai based on furry artist Cobatsart

or known as Cobat / Cobatnsfw

Support the artist using these links:

https://www.patreon.com/cobatsart

https://twitter.com/Cobatsart

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

https://www.deviantart.com/cobatsart

https://www.pixiv.net/users/5421515

https://cobatnsfwblog.tumblr.com

https://cobatsart.tumblr.com

https://cobatsart.newgrounds.com

https://cohost.org/Cobatsart

https://www.hentai-foundry.com/user/Cobat

https://www.pillowfort.social/cobatsart

https://bsky.app/profile/cobatsart.bsky.social

https://picarto.tv/Cobatsart

https://nushara.com/cobatsart

1) Always use the tag by cobatsart

2) This LoRA was based on the Illustrious

3) Even though the Illustrious 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) LoRA weight change in Civitai is at your discretion

5) To better use Lora in Civitai, I recommend using VAE (SDXL VAE) to reduce errors in the details of the hands and eyes.

6) 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.

7) If you want to force the image generator to use the Lora weight you chose, use the following tag in the positive prompt:

Illustrious

<lora:Cobatsart_Style_Lora_Illustrious:1>

Note: the number at the end of the Lora name (1) 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:

Illustrious

Civitai slider = 1

positive prompt: <lora:Cobatsart_Style_Lora_Illustrious:1>

8) 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:

Maple

by cobatsart, maple (by cobatsart), furry, furry female, anthro, animal ears, animal nose, snout, dragon, dragon girl, green body, horn, brown horn, dark green hair, long hair, thick eyebrows, eyeslashes, blue eyes, pivoted ears, long ears, freckles, freckled breasts, freckled face, freckled legs, freckled tail, freckled thighs, huge breasts, curvy, voluptuous, thick thighs, wide hips, tail, 1girl, solo, completely nude, plump, inverted nipples, belly, navel, groin, pussy, standing, legs together, hands on own face, hands on own cheeks, breast press, breasts squeezed together, looking at viewer, smile, teeth, blush, embarrassed, cowboy shot, simple background, gradient background, white background, light yellow background

Mary Muffin

by cobatsart, mary muffin (by cobatsart), lalafell, humanoid, female, dark skin, brown body, white hair, long hair, bangs, pointy ears, grey eyes, medium breasts, pear-shaped figure, thick thighs, wide hips, shortstack, 1girl, solo, swimsuit, bikini, micro bikini, black bikini, underboob, abs, stomach, cameltoe, (pussy focus:1.4), ass, black thighhighs, sitting, spread legs, from below, (close-up:1.2), looking down, simple background, gradient background, pink background

Tron Bonne

by cobatsart, tron bonne (by cobatsart), mega man (series), human, female, hair, brown hair, purple hairband, ear piercing, ear ring, eyebrows, eyelashes, green eyes, 1girl, solo, swimsuit, gold bikini, gigantic breasts, alternate breast size, thick thighs, standing, leaning forward, looking at viewer, holding eyewear, eyewear removed, looking at viewer, half-closed eyes, naughty face, seductive smile, teeth, hand on own hip, outdoors, beach, sand, ocean, sunset, purple sky

Mega Man Volnutt

by cobatsart, mega man volnutt (by cobatsart), human, male, hair, brown hair, eyebrows, eyelashes, green eyes, 1boy, solo, completely nude, abs, stomach, navel, large penis, erection, veiny penis, large testicles, standing, three quarter profile, looking away, blush, closed mouth, hands on own hips, simple background, light blue background, white background, gradient background

Note: The artist uses several well-known furry characters (cartoons, movies, comics, etc.), but in the training I left Lora flexible and malleable to be adapted / mixed with other Loras. My recommendation is that you use a character-specific Lora so that the final result is satisfactory.

Below is an initial configuration, but any other type of configuration is up to you:

ILLUSTRIOUS

Model

World Furry Fusion - v2.0 (Refined)

Lora

Cobatsart Style Lora v1.0 (illustrious) - 0.5 ~ 1.0 (Preferably 1)

Advanced

CFG Scale - 3.0 ~ 9.0 (Preferably 5)

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)

masterpiece, best quality, amazing quality, very aesthetic, high resolution, ultra-detailed, absurdres, newest, scenery, depth of field, scenery, volumetric lighting, by cobatsart, mary muffin (by cobatsart), lalafell, humanoid, female, dark skin, brown body, white hair, long hair, bangs, pointy ears, grey eyes, medium breasts, pear-shaped figure, thick thighs, wide hips, shortstack, 1girl, solo, swimsuit, bikini, micro bikini, black bikini, underboob, abs, stomach, cameltoe, (pussy focus:1.4), ass, black thighhighs, sitting, spread legs, from below, (close-up:1.2), looking down, simple background, gradient background, pink background

Prompt (Negative)

bad quality, worst quality, worst detail, lowres, sketch, jpeg artifacts, signature, watermark, username, artist name

General Observations:

• If possible, give credit to the author Cobatsart while using this LoRA.

• Do not sell or commercialize this LoRA.

• Do not remove metadata from images generated by LoRA.