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 furry artist ZP92
or known as thekid123 / ticklishways / zackdragon / zacksexyscales / komododomain / zeepee92 / itsazack
Support the artist using these links:
https://www.furaffinity.net/user/zp92
https://www.furaffinity.net/user/thekid123
https://www.deviantart.com/zp92
https://inkbunny.net/ZackSexyScales
https://komododomain.tumblr.com
https://zeepee92.newgrounds.com
https://www.pillowfort.social/ZeepZ/original
https://bsky.app/profile/itsazack.bsky.social
https://ko-fi.com/zeepzarthouse
1) Always use the tag by zp92
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) 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.
7) If the pose focuses on the feet, I recommend using the tags toes, feet, soles, foot focus, barefoot in the positive prompt. In some cases it is necessary to specify the number of toes with the tags 5 toes / 4 toes / 3 toes
8) Add the speech bubble, english text tag in the negative prompt as some images in comics format are part of the dataset.
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:ZP92_Style_Lora_Illustrious:0.8>Pony (v2.0)
<lora:ZP92_Style_Lora_v2.0:0.8>Pony (v1.0)
<lora:ZP92_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:ZP92_Style_Lora_Illustrious:0.8>Pony (v2.0)
Civitai slider = 0.8
positive prompt: <lora:ZP92_Style_Lora_v2.0:0.8>Pony (v1.0)
Civitai slider = 0.8
positive prompt: <lora:ZP92_Style_Lora:0.8>10) I added tags related to the artist's best-known characters, if you want an image close to the character, don't forget to enter the character's name, I will leave examples of prompt positive right below each character:
Bessie
by zp92, bessie, bovid, bovine, cattle, furry, furry, furry female, anthro, brown body, brown hair, long hair, brown eyes, big breasts, huge breasts, horns, ear piercing, ear ring, ring piercing, collar, cowbell, voluptuous, 1girl, solo, ???????, animal ears, cow girl, from below, low-angle view, upper body, (zoom:1.4), long hair, cow ears, smile, dark-skinned female, dark skin, yellow background, gradient background, cow horns, open mouth, looking at viewer, ????, looking down, jewelry, teeth, hands behind backAbebi
by zp92, furry, furry female, anthro, abebi, felid, lion, pantherine, snout, jewerly, piercing, ring piercing, thick thighs, large female, blue eyes, yellow sclera, black nails, huge breasts, tan fur, tan body, pink ??????, pink ???????, nails, claws, big butt, savanna, blurry background, 1girl, tail, solo, jewelry, ass, top-down bottom-up, earrings, ????, bracelet, animal ears, hoop earrings, large breasts, smile, looking at viewerChloe Shiwulf
by zp92, chloe shiwulf, canid, canine, canis, wolf, furry, furry female, anthro, grey body, gry fur, body fur, brown hair, black nose, purple eyes, big breasts, tail, 1girl, outdoors, solo, shirt, half-closed eyes, wet, wet clothes, panties, blue shirt, underwear, animal ears, brown hair, navel,purple eyes, open mouth, hands up, body fur, see-through, wolf girl, wolf ears, ???????, short sleeves, covered ???????, tongue, wolf tail, upper bodyMargret Stalizburg
by zp92, margret stalizburg, reptile, scalie, snake, furry, furry female, anthro, green body, green scales, mature female, red eyes, yellow sclera, big breasts, huge breasts, tail, thick thighs, voluptuous, wide hips, 1girl, bed, bedroom, solo, ass, lizard tail, ?????, ????, looking back, ass focus, glistening body, shiny body, thick thighs, lying, tongue out, looking at viewer, from behind, open mouth, completely ????, blue background, huge assSebrina Arbok
by zp92, sebrina arbok, snake, arbok, generation 1 pokemon, pokemon (species), purple body, purple scales, scales, green eyes, big breasts, huge breasts, tail, dark ???????, fangs, closed mouth, thick thighs, wide hips, curvy figure, claws, toes, 5 toes, humanoid feet, feet, soles, foot focus, barefoot, 1girl, solo, sitting, claws, looking at viewer, pov, front viewNote: 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:
ILLUSTRIOUS (v1.0)
Model
WAI-NSFW-illustrious-SDXL - v14
Lora
ZP92 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 zp92, furry, furry female, anthro, toriel, undertale, kitchen, kitchen utensil, cake, pie, indoors, 1girl, solo, goat girl, horns, large breasts, blue eyes, goat ears, huge ass, wide hips, thick thighs, voluptuous, apron, ????? apron, ????, areolae, covered ???????, looking back, looking down, seductive smile, eyes narrowed, snout, animal ears, oven mitts, huge breasts, from behind, looking at viewer, huge ass, tail, thighs, white fur, goat horns, thick thighs, body fur, food, smile, mature female, steam, standing, one leg raised, solo, toes, 3 toes, humanoid feet, feet, soles, foot focus, barefoot, from below, cowboy shot, bowl, holding pie, gloves, dutch anglePrompt (Negative)
speech bubble, english text, bad quality, worst quality, worst detail, sketch, censorPONY (v2.0)
Model
WAI-ANI-NSFW-PONYXL - v13
Lora
ZP92 Style Lora - v2.0 (Pony) - 0.4 ~ 1.0 (Preferably 1)
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 30)
Clip Skip - 1/2
VAE - SDXL VAE
Prompt (Positive)
score_9, score_8_up, score_7_up, by zp92, furry, furry female, anthro, canine, fox, 1girl, solo, oil-paper umbrella, tail, animal ears, ass, sitting, seiza, sitting on knees, from behind, petals, japanese clothes, grass, closed eyes, kimono, open mouth, day, smile, outdoors, body writing, sash, body fur, soles, toes, 5 toes, feet, barefoot, holding umbrella, happy, sky, red umbrella, snout, cherry blossoms, full body, holding, blue sky, fox tail, fox ears, furrification, back, obi, animal nose, sideways mouth, flower, looking back, white fur, pawpads, ^ ^, orange kimono, east asian clothingPrompt (Negative)
worst quality,bad quality, jpeg artifacts, source_cartoon, 3d, (censor), monochrome, blurry, lowres, watermark, zPDXL3, speech bubblePONY (v1.0)
Model
Pony Diffusion V6 XL - V6 (Start with this one)
Lora
ZP92 Style Lora- v1.0 (Pony) - 0.5 ~ 1.0 (Preferably 1)
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 30)
Clip Skip - 1/2
VAE - SDXL VAE
Prompt (Positive)
score_9, score_8_up, score_7_up, 1girl, breasts, thick thighs, ???????, solo, thighs, tongue, tail, pink background, colored skin, tongue out, huge breasts, ????, colored sclera, furry, furry female, completely ????, green skin, navel, gradient background, gradient, shiny skin, long tongue, looking at viewer, lizard tail, large areolae, multicolored skin, glowing, wide hips, simple background, by zp92, margret stalizburg, snake, scalie, reptile, red eyes, green body, green scales, green ???????, mature female, claws, deep skin, scales, yellow sclera, lizard tail, larger female, curvy figure, big breasts, big butt, voluptuousPrompt (Negative)
zPDXL-neg, 3D, 2D, monochrome, greyscale
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 ZP92 while using this LoRA.
Do not sell or commercialize this LoRA.
Do not remove metadata from images generated by LoRA.
Description
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.
Lora improvements added compared to version v1.0
- Faces, eyes and hands with more definition and fewer errors
- Greater compatibility with the various Pony models
- Reduction of errors in image generation in Civitai
- Reduction of errors in local image generation (A111, ComfyUI, etc.)
- Improvements in training and better adaptation to the model's style
Example Images - (https://civitai.com/posts/15922069)
FAQ
Details
Files
Available On (5 platforms)
Same model published on other platforms. May have additional downloads or version variants.



