Read the version details and recommendations in the "About this Version" section first.
LoRA, trained at Civitai based on furry artist KobuArt
or known as kobu / juliofurryart / artkobu / kobuartall
Support the artist using these links:
https://www.patreon.com/KobuArt
https://www.furaffinity.net/user/juliofurryart
https://bsky.app/profile/did:plc:7b4def4baxgib2fdlbffzwvn
https://www.facebook.com/ArtKobu
1) Always use the tag by kobuart
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:KobuArt_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:KobuArt_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:
Jira
by kobuart, jira (by kobuart), furry, furry female, anthro, animal ears, animal nose, snout, giraffe, giraffid, giraffe girl, long neck, giraffe ears, giraffe horns, tan fur, body fur, spotted fur, mature female, elderly anthro, elderly female, eye bags, blue eyes, orange hair, hair, plump, overweight female, huge breasts, large areolae, dark nipples, big belly, pussy, thick thighs, wide hips, 1girl, solo, nude, green apron, naked apron, clothes between breasts, between breasts, meme, collarbone, sagging breasts, breast milk, lactation, breasts out, public indecency, groin, holding cup, coffee cup, disposable cup, standing, looking at viewer, embarrassed, blush, smile, :s, indoors, cafe, photo background, (blurry background:1.4), cowboy shotKoba
by kobuart, koba (by kobuart), furry, furry female, anthro, animal ears, animal nose, snout, domestic dog, canine, dog, dog girl, dog ears, light blue fur, grey fur, body fur, two tone fur, floppy ears, thick eyebrows, (red sclera, yellow eyes:1.4), black hair, red hair, two tone hair, medium hair, black nose, plump, voluptuous, large breasts, pink areolae, pink nipples, 1girl, solo, pink shirt, short sleeves, shirt pull, pulling own clothes, cleavage, striped shirt, vertical-striped shirt, collarbone, bursting breasts, breast rest, on table, one breast out, sagging breasts, sitting, on chair, looking at viewer, half-closed eyes, smile, embarrassed, blush, flying sweatdrops, spoken heart, phone, smartphone, indoors, office, photo background, (blurry background:1.4), upper bodyKobu
by kobuart, kobu (by kobuart), furry, furry male, anthro, animal ears, animal nose, snout, domestic dog, canine, dog, dog boy, dog ears, light blue fur, grey fur, body fur, two tone fur, floppy ears, facial hair, (red sclera, yellow eyes:1.4), black hair, short hair, black nose, plump, overweight male, moobs, huge penis, huge testicles, belly, thick thighs, dog tail, 1boy, solo, completely nude, pink nipples, navel, precum, precum drip, sitting, on couch, arm behind head, reclining, looking at viewer, smile, indoors, room, photo background, (blurry background:1.4), upper body, close-upNote: 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 - v1.0 (Refined)
Lora
KobuArt 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 kobuart, furry, furry female, anthro, animal ears, animal nose, snout, animal crossing, (audie (animal crossing):1.4), wolf, half-closed eyes, large breasts, orange fur, body fur, blue eyes, blush, short hair, blonde hair, eyeshadow, makeup, eyeshadow, 1girl, solo, completely nude, huge breasts, nipples, huge belly, pregnant, stretch marks, thick thighs, wide hips, lying, on side, legs together, head rest, on bed, feet out of frame, from side, looking at viewer, smile, simple background, indoors, bedroom, pillow, bed sheet, curtains, window, day, sunlight, close-upPrompt (Negative)
bad quality, worst quality, worst detail, sketch, lowres, jpeg artifacts, signature, watermark, username, artist nameGeneral Observations:
If possible, give credit to the author KobuArt while using this LoRA.
Do not sell or commercialize this LoRA.
Do not remove metadata from images generated by LoRA.
Description
About this version
More distant images may show some artifacts, distortions or disproportions in the face when generating images in Civitai, which is why the recommendation of this LoRA is to use characters closer to the image or use some Embedding / Face Fix to reduce errors in the face.















