Read the version details and recommendations in the "About this Version" section first.
LoRA, trained at Civitai based on furry artist AOI Takayuki (Kuro-Gane)
or known as Kuro9ane / Aoi Takayuki
Support the artist using these links:
https://www.pixiv.net/en/users/24517733
1) Always use the tag by kuro-gane
2) This LoRA was based on the Pony V6 version / Illustrious
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 shiny body, glistening body tag to the positive prompt to obtain the author's characteristic effect with oily and shiny bodies, otherwise, 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) Add the censored, bar censor, heart censor, pointless censoring, censored nipples, convenient censoring, mosaic censoring 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
9) 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.
10) If you want to force the image generator to use the Lora weight you chose, use the following tag in the positive prompt:
Illustrious (v1.0)
<lora:Aoi_Takayuki_Kuro-Gane_Style_Lora_Illustrious:0.8>
Pony (v1.0)
<lora:Aoi_Takayuki_Kuro-Gane_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:
Illustrious (v1.0)
Civitai slider = 0.8 positive prompt: <lora:Aoi_Takayuki_Kuro-Gane_Style_Lora_Illustrious:0.8>
Pony (v1.0)
Civitai slider = 0.8 positive prompt: <lora:Aoi_Takayuki_Kuro-Gane_Style_Lora:0.8>
Below is an initial configuration, but any other type of configuration is up to you:
ILLUSTRIOUS
Model
Nova Anime XL - IL v6.0
Lora
Aoi Takayuki (Kuro-Gane) Style Lora - v1.0 (illustrious) - 0.5 ~ 1.0 (Preferably 0.8)
Advanced
CFG Scale - 3.0 ~ 9.0 (Preferably 6)
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 kuro-gane, furry, furry male, anthro, equine, horse, beach, sunset, clouds, horizon, otoko no ko, femboy, solo, 1boy, animal ears, covered erect nipples, male focus, horse ears, blonde hair, horse tail, huge bulge, hooves, dark skin, brown fur, body fur, swimsuit, nipples, choker, hand on hip, fluffy hair, aqua eyes, full body, leaning forward, seduction, seductive pose, wide hips, large thighs, voluptuous, wet, wet dripping, wet hair, wet clothing, tight clothing
Prompt (Negative)
nails, bad quality, worst quality, worst detail, bad quality, worst quality, worst detail, sketch, censor, human, 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
Pony Diffusion V6 XL - V6 (Start with this one)
Lora
Aoi Takayuki (Kuro-Gane) Style Lora - v1.0 (Pony) - 0.5 ~ 1.0 (Preferably 0.8)
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)
score_9, score_8_up, score_7_up, by kuro-gane, shiny body, glistening body, fox, canine, canid, canis, 1girl, breasts, solo, furry, pasties, animal ears, tail, furry female, heart pasties, brown hair, short hair, covered nipples, maebari, armpits, hair over one eye, navel, nude, body fur, pubic hair, fox ears, open mouth, huge breasts, large breasts, fox tail, armpit hair, female pubic hair, arms behind head, looking at viewer, smile
Prompt (Negative)
zPDXL3, 3D, 2D, greyscale, monochrome, censored, bar censor, heart censor, pointless censoring, censored nipples, convenient censoring, mosaic censoring
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 Aoi Takayuki (Kuro-Gane) while using this LoRA.
Do not sell or commercialize this LoRA
Do not remove metadata from images generated by LoRA.