Soviicoon Style Lora (Illustrious / Pony)
Details
Download Files
About this version
Model description
Read the version details and recommendations in the "About this Version" section first.
Preferably use the updated and stable version 2.0 if you use the Pony version
LoRA, trained at Civitai based on artist Soviicoon
Or known as Sovii
Support the artist using these links:
https://www.furaffinity.net/user/soviicoon
https://bsky.app/profile/soviicoon.bsky.social
https://www.twitch.tv/soviicoon
Always use the tag by soviicoon
This LoRA was based on the Pony V6 version / Illustrious
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.
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,
LoRA weight change in Civitai is at your discretion
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
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.
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:Soviicoon_Style_Lora_Illustrious:0.8>
Pony (v2.0)
<lora:Soviicoon_Style_Lora_v2:0.8>
Pony (v1.0)
<lora:Soviicoon_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:Soviicoon_Style_Lora_Illustrious:0.8>
Pony (v2.0)
Civitai slider = 0.8
positive prompt: <lora:Soviicoon_Style_Lora_v2:0.8>
Pony (v1.0)
Civitai slider = 0.8
positive prompt: <lora:Soviicoon_Style_Lora:0.8>
Below is an initial configuration, but any other type of configuration is up to you:
ILLUSTRIOUS
Model
Nova Furry XL - Illustrious v6B
Lora
Soviicoon Style Lora v1.0 (illustrious) - 0.5 ~ 1.0 (Preferably 0.8)
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 soviicoon, furry, furry female, anthro, zootopia, judy hopps, solo, half-closed eyes, eyewear on head, police uniform, tight clothes, animal ears, sunglasses, policewoman, rabbit ears, belt pouch, utility belt, ass, police car, ground vehicle, motor vehicle, looking at viewer, long sleeves, pants, white fur, body fur, blue pants, shirt, rabbit girl, blue shirt, hand up, eyeshadow, cameltoe, teeth, sitting, makeup, animal nose, adjusting eyewear, pocket, arm up, purple eyes, legs up, belt, smile, parted lips, on vehicle, hand on eyewear, :3, on back, thick thighs, medium breasts, blue eyeshadow, lying, leaning back, purple eyeshadow, feet out of frame
Prompt (Negative)
monochrome, greyscale, sketch, bad quality, worst quality, worst detail, bad quality, worst quality, worst detail, 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 (v2.0)
Model
Sym-Pony World - v1.0
Lora
Soviicoon Style Lora - v2.0 (Pony) - 0.4 ~ 1.0 (Preferably 0.8)
Advanced
CFG Scale - 5.0 ~ 9.0 (Preferably 7)
Sampler - DDIM / Euler a / Euler / Heun / DPM2 / DPM++ 2M Karras / Uni PC (Preferably Euler a)
Steps - 20 ~ 50 (Preferably 25)
Clip Skip - 1/2
VAE - SDXL VAE
Prompt (Positive)
score_9, score_8_up, score_7_up, score_6_up, by soviicoon, glistening body, oiled, shiny body, bird, avian, 1girl, breasts, solo, nipples, blue body, blue hair, tail, furry, furry female, animal ears, pussy, blue fur, thick thighs, huge breasts, hands up, open mouth, underwear, wide hips, thick thighs, large areolae, short hair, body fur, smile, white background, panties, blue eyes, standing, looking at viewer
Prompt (Negative)
zPDXL3, 3D, 2D, human
PONY (v1.0)
Model
Pony 🦄FaeTality - v1.1
Lora
Soviicoon Style Lora - v1.0 (Pony) - 0.5 ~ 1.0 (Preferably 0.8)
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 25)
Clip Skip - 1/2
VAE - SDXL VAE
Prompt (Positive)
score_9, score_8_up, score_7_up, by soviicoon, glistening body, oiled, shiny body, equid, equine, horse, horse penis, piercing, nipple piercing, furry, solo, male focus, colored sclera, 1boy, testicles, white hair, red eyes, tail, nipples, pubic hair, cum, lifted by self, erection, open mouth, shirt lift, navel, animal ears, animal penis, furry male, tongue, huge penis, clothes lift, large testicles, black sclera, earrings
Prompt (Negative)
zPDXL3, 3D, 2D, human
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 (/model/332646/pony-pdxl-negative-embeddings).
General Observations:
If possible, give credit to the author Soviicoon while using this LoRA.
Do not sell or commercialize this LoRA
Do not remove metadata from images generated by LoRA.