Difetra Style Lora (Illustrious / Pony)

LoRA, trained at Civitai based on furry artist Difetra or known as hooves4hands / StaresAtHeadlights

Support the artist using these links:

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

https://www.furaffinity.net/user/hooves4hands/

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

https://twitter.com/DifetraArt

https://inkbunny.net/Difetra

https://difetra.sofurry.com/

https://www.weasyl.com/~difetra

https://furrynetwork.com/difetra/

https://itaku.ee/profile/difetra

https://picarto.tv/difetra

https://www.difetra.com/

https://x.com/Hooves4Hands

1. Always use the tag by difetra

2. This LoRA was based on the Pony V6 version / Illustrious

3. Even though the Pony V6 base / Illustrious 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 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:Difetra_Style_Lora_Illustrious:1

Pony (v1.0)

lora:Difetra_Style_Lora: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:Difetra_Style_Lora_Illustrious:1

Pony (v1.0)

Civitai slider = 1

positive prompt: lora:Difetra_Style_Lora: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:

Eve

by difetra, furry, furry female, anthro, eve, procyonid, raccoon, animal ears, animal nose, snout, long hair, brown hair, black nose, blue eyes, brown body, brown fur, eyebrows, eyelashes, raccoon tail, 1girl, solo, looking back, rear view, sitting, day, forest, nature, grass, dirt floor, blurry foreground

Juniper

by difetra, furry, furry female, anthro, juniper, deer, animal nose, animal ears, snout, tan body, tan fur, body fur, orange eyes, 1girl, solo, outdoors, handrail, beach, sand, ocean, horizon, day, clouds, bluesy, sun, lensflare, big breasts, nipples, areolae, curvy figure, huge ass, deer tail, bent over, leaning forward, pussy, anus, presenting, presenting ass, looking back, looking at viewer, upper body, completely nude, glistening body, shiny body

Penelope (anthro)

by difetra, furry, furry female, anthro, penelope, gulonine, marten, mustelid, musteline, pine marten, animal ears, animal nose, snout, pussy, bedroom eyes, brown body, brown fur, body fur, purple eyes, claws, narrowed eyes, 1girl, solo, small breasts, nipples, tail, sitting, spread legs, spreading, front, on back, looking at viewer, on floor, paws, barefoot, white background, gradient background, simple background

Penelope (feral)

by difetra, furry, furry female, feral, penelope, gulonine, marten, mustelid, musteline, pine marten, animal ears, animal nose, snout, bedroom eyes, brown body, brown fur, body fur, purple eyes, claws, narrowed eyes, solo, tail, walking, looking at viewer, dirt floor, paws, pawspads, barefoot, light green background, gradient background, simple background, full body

Tera

by difetra, furry, furry female, feral, quadruped, tera, equine, horse, mature female, my little pony, animal ears, animal nose, snout, blue eyes, brown hair, long hair, fluffy hair, tan fur, body fur, full body, hooves, tail, solo, wide hips, smile, black latex, body suit, glistening latex, sitting on bed, on side, looking at viewer, bedroom, bed, bedsheet, pillows, window

Orion

by difetra, furry, furry male, anthro, orion, deer, animal nose, animal ears, snout, tan body, tan fur, body fur, green eyes, deer tail, 1boy, solo, night, outdoors, mountains, standing, hands on hips, sheath, big testicles, smile, looking at viewer, cowboy shot 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:

ILLUSTRIOUS (v1.0)

Model

Hassaku XL (Illustrious) - v2.2

Lora

Difetra Style Lora - v1.0 (illustrious) - 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 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 difetra, furry, furry female, anthro, domestic cat, feline, animal nose, animal ears, snout, orange fur, body fur, red eyes, fluffy hair, 1girl, huge breasts, solo, bag, day, dress, voluptuous, plump, wide hips, sun hat, grey dress, tight clothes, tail, indoors, lodge, hands up, covered nipples, standing, looking at side, thick thighs, collarbone, open mouth, smile, teeth, fangs, tongue, sundress, cowboy shot, cleavage, holding bag, handbag, no bra, sleeveless dress, bare shoulders, hand up, shoulder bag, smile, white headwear, holding strap, from below

Prompt (Negative)

bad quality, worst quality, worst detail, sketch, censor

PONY (v1.0)

Model

Pony Diffusion V6 XL - V6 (Start with this one)

Lora

Difetra Style Lora - v1.0 (Pony) - 0.5 ~ 1.0 (Preferably 1)

Advanced

CFG Scale - 3.0 ~ 9.0 (Preferably 4)

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 - none

Prompt (Positive)

score_9, score_8_up, score_7_up, by difetra, snow, gray fur, 1girl, breasts, nipples, solo, furry, nude, blue eyes, furry female, arms behind head, armpits, navel, animal ears, smile, looking at viewer, traditional media, onsen, water, body fur, pussy, spot color, snout, arms up, outdoors, large breasts, wolf, medium breasts, wading, closed mouth, animal nose

Prompt (Negative)

score_6, score_5_up, score_4_up, 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 Difetra while using this LoRA.

Do not sell or commercialize this LoRA.

Do not remove metadata from images generated by LoRA.