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

LoRA, trained at Civitai based on furry artist 925Kyohei (Apashi)

or known as Apashi / あぱしししほほ_Apashi

Support the artist using these links:

https://x.com/925Kyohei

https://apashi925.fanbox.cc

https://www.pixiv.net/fanbox/creator/8276481

1) Always use the tag by 925Kyohei

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) Add the censored, bar censor, mosaic censoring, heart censor, hair 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

7) Add the pasties, covered nipples, choker tag to the negative prompt so as not to directly influence the character's features during image generation.

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:

Illustrious (v1.0)

<lora:925Kyohei_Apashi_Style_Lora_Illustrious_r1:1>

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:925Kyohei_Apashi_Style_Lora_Illustrious_r1:1>

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

ILLUSTRIOUS

Model

World Furry Fusion - v1.0 (Refined)

Lora

925Kyohei (Apashi) 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 925kyohei, furry, furry female, anthro, animal ears, animal nose, snout, fox, canine, orange fur, white fur, two-tone fur, body fur, orange hair, fluffy, pink eyes, tail, 1girl, completely nude, female focus, large breasts, inverted nipples, navel, hand up, gesture, v, head tilt, completely nude, penis on breast, seiza, sitting on kness, looking away, smile, teeth, blush, indoors, room, night, window, curtains, simple background, upper body, 1boy, human, male, dark skin, dark-skinned male, (male standing, side by side:1.4), barefoot, feet, faceless, faceless male, head out of frame, long penis, veiny penis, erection, big testicles, excessive pubic hair, male pubic hair, cum, cum on breasts, cum in body, cum on face, cumdrip, cum string, ejaculation, lots of cum

Prompt (Negative)

bad quality, worst quality, worst detail, sketch, lowres, jpeg artifacts, signature, watermark, username, artist name, censored, bar censor, mosaic censoring, heart censor, hair censor, pasties, choker

General Observations:

• If possible, give credit to the author 925Kyohei (Apashi) while using this LoRA.

• Do not sell or commercialize this LoRA.

• Do not remove metadata from images generated by LoRA.