Read the version details and recommendations in the "About this Version" section first.
Preferably use the updated and stable version 2.0
LoRA, trained at Civitai based on furry artist Cherrikissu
Support the artist using these links:
https://www.patreon.com/cherrikissu
https://www.furaffinity.net/user/cherrikissu
https://www.deviantart.com/cherrikissu
https://cherrikissu.tumblr.com
https://cherrikissu.newgrounds.com
https://www.pillowfort.social/cherrikissu
https://ko-fi.com/cherrikissu
https://x.com/cherrikissu
1) Always use the tag by cherrikissu
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) 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) 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:Cherrikissu_Style_Lora_Illustrious:0.8>
Pony (v2.0)
<lora:Cherrikissu_Style_Lora_v2:0.8>
Pony (v1.0)
<lora:Cherrikissu_Style_Lora-000013:1>
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:Cherrikissu_Style_Lora_Illustrious:0.8>
Pony (v2.0)
Civitai slider = 0.8
positive prompt: <lora:Cherrikissu_Style_Lora_v2:0.8>
Pony (v1.0)
Civitai slider = 1
positive prompt: <lora:Cherrikissu_Style_Lora-000013:1>
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:
Mabel
by cherrikissu, furry, furry female, anthro, mabel, domestic dog, canid, canine, canis, hunting dog, saluki, sighthound, ???????????, ????????????, brown eyebrows, yellow eyes, blonde hair, brown ??????, brown ???????, brown body, brown fur, mature female, slightly chubby, thick thighs, long hair, inverted ???????, thick thighs, tail, snout, large ???????, bathroom, bathtub, water, indoors, 1girl, wet, wet hair, wet dripping, glistening body, shiny body, navel, cleavage, solo, foam, ????????????, looking at viewer, sitting, smile, completely ????, wide ????, curvy, inviting, ?????????, front view, above view
Caramel
by cherrikissu, furry, furry female, anthro, caramel, cattle, bovid, bovine, ???????????, ????????????, brown body, brown fur, brown hair, ear piercing, facial piercing, long ears, long hair, lipstick, nose ring, nose piercing, piercing, ring piercing, yellow eyes, slightly chubby, thick thighs, brown horns, small horns, stripes horns, 1girl, solo, pool, water, reflection, outdoors, sunset, sky, clouds, sunlight, one piece swimsuit, gold swimsuit, mole on ??????, covered ???????, blush, smile, body freckles, mole on thigh, looking at viewer, mole on stomach, full body, seiza, sitting on knees
Apollo
by cherrikissu, apollo, wolf, canid, canine, canis, black nose, blue eyes, curled tail, ear piercing, eyebrows, fluffy, fluffy hair, grey hair, grey fur, white fur, muscular male, large pectorals, 1boy, solo, animal ears, outdoors, trees, plant, running, blue shirt, black pants, sportswear, viewed from side, cowboy shot, movement lines
Olive (Rawk Manx)
by cherrikissu, olive, deer, new world deer, reindeer, antlers, blue eyes, ???????????, brown body, brown fur, brown hair, ear tuft, fur, hair, hair bun, horn, ????????????, tuft, thick thighs, tied hair, wide ????, long hair, pink ??????, pink ???????, two tone body, two tone fur, white body, white fur, braided hair, multicolored body, multicolored fur, 1girl, solo, long hair, animal ears, snout, lying on bed, on side, black panties, ?????????, ???????, very long hair, smile, deer ears, body fur, navel, large ???????, animal nose, looking at viewer, pillow, heart, bedroom
Below is an initial configuration, but any other type of configuration is up to you:
ILLUSTRIOUS
Model
WAI-NSFW-illustrious-SDXL - v13
Lora
Cherrikissu 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 cherrikissu, furry, furry female, anthro, bear, white fur, body fur, bedroom, sitting on bed, indoors, window, sky, night sky, city, cityscape, night, moon, crescent moon, 1girl, ?????????, blue eyes, long hair, animal ears, navel, drinking glass, cleavage, solo, jewelry, cup, ????????????, necklace, looking at viewer, petals, wine glass, candle, smile, white hair, clothes lift, ?????????????, thick thighs, bear ears, wide ????, snout, dress, curvy, pink panties, animal nose, holding cup, petals on liquid, edge
Prompt (Negative)
monochrome, greyscale, sketch, bad quality, worst quality, worst detail, bad quality, worst quality, worst detail, sketch, 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 digit, fewer digits, cropped, very displeasing, (worst quality, bad quality:1.2), bad ???????, 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
Pony Diffusion V6 XL - V6 (Start with this one)
Lora
Cherrikissu Style Lora - v2.0 (Pony) - 0.4 ~ 1.0 (Preferably 0.8)
Advanced
CFG Scale - 5.0 ~ 9.0 (Preferably 5)
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 cherrikissu, caramel, cattle, bovid, bovine, ???????????, ????????????, brown body, brown fur, brown hair, ear piercing, facial piercing, long ears, long hair, lipstick, nose ring, nose piercing, piercing, ring piercing, yellow eyes, slightly chubby, thick thighs, horns, 1girl, ???????, freckles, mole, solo, ???????, brown hair, mole on ??????, long hair, gloves, animal ears, thighhighs, bell, lactation, one eye closed, elbow gloves, cow print, body freckles, ????????????, mole on thigh, animal print, lips, looking at viewer, cowbell, ???????, neck bell, mole on stomach
Prompt (Negative)
zPDXL3, 3D, 2D, human
PONY (v1.0)
Model
SakuraSakuma Mix -Pony- v1.0-Exclusive Marge
Lora
Cherrikissu Style Lora - v1.0 (Pony) - 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 25)
Clip Skip - 1/2
VAE - SDXL VAE
Prompt (Positive)
score_9, score_8_up, score_7_up, by cherrikissu, lucario, 1girl, furry, solo, pokemon (creature), ???, furry female, blue fur, tail, ?????, looking back, black fur, wolf ears, thick thighs, simple background, wolf tail, red eyes, white background, ???????????, ????, blush, body fur, thighs, wolf girl, animal ears, ?????????, looking at viewer, multicolored fur, uncensored, yellow fur, pawpads
Prompt (Negative)
zPDXL-neg, 3D, 2D, score_6, score_5_up, score_4_up, 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 (https://civitai.com/models/332646/pony-pdxl-negative-embeddings).
General Observations:
If possible, give credit to the author Cherrikissu while using this LoRA.
Do not sell or commercialize this LoRA
Do not remove metadata from images generated by LoRA.
