Read the version details and recommendations in the "About this Version" section first.
or known as kizaruya / Kizaru / kiirozaru / 黄猿@単行本発売中 / harebare14 / 黄猿@全年齢向
Support the artist using these links:
https://www.pixiv.net/en/users/338111
https://pawoo.net/@sunnydaynamainichi
1) Always use the tag by kizaru
2) This LoRA was based on the Pony V6 version / Illustrious
3) Even though the Pony V6 base / Illustrious 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) 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
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, mosaic censoring, bar censor, identity censor, heart censor 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:Kizaruya_Kizaru_Style_Lora_Illustrious:1>Pony (v1.0)
<lora:Kizaruya_Kizaru: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 (v1.0)
Civitai slider = 1
positive prompt: <lora:Kizaruya_Kizaru_Style_Lora_Illustrious:1>Pony (v1.0)
Civitai slider = 1
positive prompt: <lora:Kizaruya_Kizaru:1>Below is an initial configuration, but any other type of configuration is up to you:
ILLUSTRIOUS (v1.0)
Model
Nova Furry XL - Illustrious v8B
Lora
Kizaruya (Kizaru) 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 kizaru, furry, furry female, anthro, equine, horse, black body, black fur, body fur, black eyes, long hair, black hair, blonde hair, mohawk (hairstyle), animal ears, animal nose, snout, thick eyebrows, 1girl, solo, pink , , tail, pink , blush, navel, plump, overweight female, belly, wide , large thighs, large , , only, , dripping, , , collarbone, standing, covered , blonde female pubic hair, book, bedroom, bed, indoors, bookshelf, black background, night, light particles, one hand raised, holding , , smile Prompt (Negative)
human, monochrome, greyscale, sketch, censored, mosaic censoring, bar censor, identity censor, heart censor, multiple tails, modern, recent, old, oldest, graphic, cartoon, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured, long body, lowres, bad , bad hands, missing fingers, extra digits, fewer digits, cropped, very displeasing, (worst quality, bad quality:1.2), bad , sketch, jpeg artifacts, signature, watermark, username, simple background, conjoined, bad ai-generatedPONY (v1.0)
Model
Pony Diffusion V6 XL - V6 (Start with this one)
Lora
Kizaruya (Kizaru) Style Lora - 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 Heun)
Steps - 20 ~ 60 (Preferably 30)
Clip Skip - 1/2
VAE - SDXL VAE
Prompt (Positive)
score_9, score_8_up, score_7_up, by kizaru, 1girl bovid, , horns, , , 1boy human, hetero, , colored skin, in , straddling, , , , , purple skin, short hair, , blue eyes, interspecies, sweat, squatting , blush, plump, red hair, thick thighs, muscular, , solo focus, excessive Prompt (Negative)
zPDXL3, 3D, 2D, censored, mosaic censoring, bar censor, identity censor, heart censor, monochrome, greyscale, 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 Kizaruya (Kizaru) while using this LoRA.
Do not sell or commercialize this LoRA.
Do not metadata from images generated by LoRA.
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.
Example Images - (https://civitai.com/posts/18338460)
1. Os direitos dos modelos repostados pertencem aos criadores originais.
2. Criadores originais que desejam reivindicar seus modelos devem contatar a equipe do SeaArt AI pelos canais oficiais. Clique para reivindicar
