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

LoRA, trained at Civitai based on furry artist Duase

or known as duase_nsfw

Support the artist using these links:

https://www.patreon.com/duase

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

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

https://x.com/Duase_NSFW

1) Always use the tag by duase

2) This LoRA was based on the Illustrious

3) Even though the Illustrious 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) LoRA weight change in Civitai is at your discretion

5) To better use Lora in Civitai, I recommend using VAE (SDXL VAE) to reduce errors in the details of the hands and eyes.

6) Add the tags high heels, platform heels, platform footwear, in the prompt positive if you want to make images of characters with high heels

7) Add the tags high heels, platform heels, platform footwear, in the prompt negative if you want to make images of characters without high heels, add the tag feet in the prompt positive to create images with ???? feet

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:Duase_Style_Lora_Illustrious_r1:0.8>

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:Duase_Style_Lora_Illustrious_r1:0.8>

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:

Rasa

by duase, rasa (duase), furry, furry female, anthro, wolf, canine, animal ears, animal nose, snout, white fur, body fur, blue eyes, thick eyebrows, grey hair, long hair, ????????????, fluffy tail, muscular female, abs, huge wips, wide ????, thick thighs, 1girl, solo, beach, outdoors, sand, ocean, horizon, hands up, arms above head, open mouth, teeth, fangs, tongue out, black ??????, swimsuit, tail, wolf ears, wolf tail, wolf girl, navel, dutch angle

Zinny

by duase, zinny (duase), furry, furry female, anthro, wolf, canine, animal ears, animal nose, snout, brown fur, tan fur, body fur, multicolored fur, red eyes, white hair, long hair, ????????????, fluffy, fluffy tail, curvy figure, voluptuous, wide ????, thick thighs, 1girl, solo, completely ????, outdoors, blue sky, clouds, ???, disposable cup, holding cup, drinking straw in mouth, long socks, thigh socks, ponytail, wolf tail, wolf ears, wolf girl, looking at viewer, looking down, from below, white socks, baseball cap, collar, rear view, cowboy shot, ??? focus

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

Model

Artofura | Furry mix - Illustrious++ - v2.0

Lora

Duase Style Lora v1.0 (illustrious) - 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 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 duase, furry, furry female, anthro, procyonid, raccoon, animal nose, snout, animal ears, black hair, bangs, medium hair, blunt bangs, (grey fur:1.4), body fur, 1girl, solo, ????????????, ???????, cleavage, plump, navel, large ???????, covered ????? ???????, open mouth, tongue, fangs, blue ??????, swimsuit, thick thighs, raccoon ears, hands on ????, raccoon tail, sweat, sweaty, sweat dripping, glistening body, shiny body, raccoon girl, looking at viewer, purple background, nightclub, lights, blurry background

Prompt (Negative)

high heels, platform heels, platform footwear, bad quality, worst quality, worst detail, sketch, censor

General Observations:

• If possible, give credit to the author Duase while using this LoRA.

• Do not sell or commercialize this LoRA.

• Do not remove metadata from images generated by LoRA.