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

LoRA, trained at Civitai based on furry artist Karabiner

or known as Notobuko / Nobuhiko Abe / ABE / DEN

Unfortunately the author has deleted all his social networks (VCL / Furaffinity / Web Page Personal)

1) Always use the tag @karabiner (Anima) / by karabiner (Illustrious, Pony)

2) This LoRA was based on the Anima / Illustrious / Pony V6 version

3) Even though the Pony V6 / 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) 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 censored tag to the negative prompt if you wish to see images without any type of censorship, as some images composed by Lora were drawn by the author with some type of censorship

7) To better use Lora in Civitai, I recommend using VAE (SDXL VAE) and also Embedding (Pony PDXL Negative Embeddings) to reduce errors in the details of the hands and eyes

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:

Anima

<lora:Karabiner_Style_LoRA_Anima_anima_3291762_epoch_11:1>

Illustrious

<lora:Karabiner_Style_Lora_Illustrious:1>

Pony

<lora:Karabiner_Style_Lora: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:

Anima

Civitai slider = 1

positive prompt: <lora:Karabiner_Style_LoRA_Anima_anima_3291762_epoch_11:1>

Illustrious

Civitai slider = 1

positive prompt: <lora:Karabiner_Style_Lora_Illustrious:1>

Pony

Civitai slider = 1

positive prompt: <lora:Karabiner_Style_Lora:1>

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:

ANIMA

Model

Anima - base-v1.0

Lora

Karabiner Style Lora v1.0 (Anima) - 0.5 ~ 1.0 (Preferably 1)

Advanced

CFG Scale - 4.0 ~ 6.0 (Preferably 5)

Sampler - DDIM / Euler a / Euler / Heun / DPM2 / DPM++ 2M Karras / Uni PC / er_sde (Preferably Euler a)

Steps - 20 ~ 60 (Preferably 30)

Clip Skip - 1/2

Prompt (Positive)

masterpiece, best quality, amazing quality, very aesthetic, extremely detailed, very detailed, absurdres, newest, highres, score_9, score_8, @karabiner, furry, furry female, anthro, animal ears, animal nose, snout, hyena, hyena girl, hyena ears, spotted hyena, grey fur, yellow sclera, black eyes, black hair, short hair, grey fur, body fur, dark nipples, 1girl, solo, completely nude, huge breasts, breast press, nipples, stomach, navel, groin, pussy, against window, breasts on glass, breast press, looking at viewer, seductive smile, naughty face, open mouth, blush, steam, steamy, steaming body, sweat, sweaty, very sweaty, shiny skin, (condensation, fog, frosted glass:2), cowboy shot, simple background, indoors, bathroom

Prompt (Negative)

worst quality, low quality, score_1, score_2, score_3, blurry, jpeg artifacts, sepia, low quality, worst quality, blurry, bad anatomy, extra limbs, deformed, watermark, text, signature, bareness, artifacts, hands, copyrights name, jpeg_artifacts, scan_artifacts, bad hands, missing fingers, extra digit, fewer digits, artistic error, ye-pop, deviantart, logo, patreon logo

ILLUSTRIOUS

Model

WAI-NSFW-illustrious-SDXL - v12.0

Lora

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

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)

masterpiece, best quality, amazing quality, very aesthetic, high resolution, ultra-detailed, absurdres, newest, scenery, depth of field, scenery, volumetric lighting, by karabiner, furry, furry female, anthro, renamon, digimon, 1girl, solo, outdoors, cloudy, snow, snowing, grey theme, blurry background, yin yang, digimon (creature), solo, looking up, blue eyes, black sclera, tail, ass, fox tail, fox ears, animal ears, gloves, white fur, cowboy shot, fox girl, outdoors, detached sleeves, facial mark, snout, standing, yellow fur, body fur, two-tone fur, from behind, nude, purple gloves, tattoo, purple sleeves, claws, looking up, elbow gloves, back, leg tattoo, breasts, sky, animal nose, thighs, looking back, pussy, nipples

Prompt (Negative)

bad quality, worst quality, worst detail, bad quality, worst quality, worst detail, sketch, censor, multiple tails, modern, recent, old, oldest, graphic, cartoon, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured, long body, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, very displeasing, (worst quality, bad quality:1.2), bad anatomy, sketch, jpeg artifacts, signature, watermark, username, simple background, conjoined, ai-generated, worst quality, low quality, off-topic, old, early, chromatic aberration, abstract, jpeg artifacts, scan artifacts, logo

PONY

Model

WAI-ANI-NSFW-PONYXL - v13.0

Lora

Karabiner Style Lora - v1.0 (Pony) - 0.5 ~ 1.0 (Preferably 1)

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 ~ 50 (Preferably 30)

Clip Skip - 1/2

VAE - SDXL VAE

Prompt (Positive)

score_9, score_8_up, score_7_up, by karabiner, tiger, felid, feline, felis, 1boy, male focus, solo, furry, furry male, tail, beach, day, tongue, goggles, tongue out, outdoors, leopard tail, nipples, sky, bulge, abs, animal ears, leopard ears, swim briefs, ocean, goggles around neck, male swimwear

Prompt (Negative)

zPDXL3, 3D, 2D, human, censored

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://civarchive.com/models/332646/pony-pdxl-negative-embeddings).

General Observations:

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

• Do not sell or commercialize this LoRA, if possible.

• Do not remove metadata from images generated by LoRA.