Usnarbit Style Lora

LORA
Original


Updated:

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

LoRA, trained at Civitai based on furry artist Usnarbit

Support the artist using these links:

https://www.furaffinity.net/user/usnarbit/

https://x.com/usnarbit

https://bsky.app/profile/usnarbit.bsky.social

https://www.patreon.com/usanrbit

1) Always use the tag by usnarbit

2) This LoRA was based on the Pony V6 version

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) 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) 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.

8) If you want to force the image generator to use the Lora weight you chose, use the following tag in the positive prompt:

Pony (v1.0)

<lora:Usnarbit_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:

Pony (v1.0)

Civitai slider = 0.8 positive prompt: <lora:Usnarbit_Style_Lora:0.8>

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:

PONY

Model

WAI-ANI-NSFW-PONYXL - v13.0

Lora

Usnarbit Style Lora - v1.0 (Pony) - 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 DPM++ 2M Karras)

Steps - 20 ~ 50 (Preferably 30)

Clip Skip - 1/2

VAE - SDXL VAE

Prompt (Positive)

score_9, score_8_up, score_7_up, by usnarbit, furry, furry female, anthro, lagomorph, leporid, rabbit, 1girl, solo, mature female, milf, underwear, medium breasts, animal ears, floppy ears, bunny ears, blonde hair, long hair, panties, wide hips, black panties, makeup, navel, off shoulder, thick thighs, shirt, eyeshadow, standing, full body, off-shoulder shirt, smile, pink shirt, crop top, black eyes, barefoot, looking at viewer, orange fur, body fur, animal nose, bare shoulders, :3, plump, long sleeves, buck teeth, lipstick, stomach, highleg panties, hand up, curvy, indoors, midriff, highleg, two-tone fur, collarbone, topknot, pantsless

Prompt (Negative)

zPDXL3, 3D, 2D, human, blurry, jpeg artifacts, username, watermark, signature, normal quality, worst quality, large head, low quality, text, error, missing fingers, extra digits, fewer digits, bad eye

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 Usnarbit while using this LoRA.

  • Do not sell or commercialize this LoRA, if possible, help the author of the images through your Patreon.

  • Do not remove metadata from images generated by LoRA.

Version Detail

Pony
4870
10
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.

Project Permissions

    Use Permissions

  • Use in TENSOR Online

  • As a online training base model on TENSOR

  • Use without crediting me

  • Share merges of this model

  • Use different permissions on merges

    Commercial Use

  • Sell generated contents

  • Use on generation services

  • Sell this model or merges

Related Posts

Describe the image you want to generate, then press Enter to send.