LoRA, trained at Civitai based on furry artist Tecnicide
Support the artist using these links:
1) Always use the tag by tecnicide
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) 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.
Observation 1:
To create a sex scene between two characters (male/female), you need to copy some tips I will give (obviously you can change them later, but this is a starting point), due to the artist mostly creating futanari characters:
Lora Weight = 0.8
Positive Prompt
masterpiece, best quality, amazing quality, very aesthetic, high resolution, ultra-detailed, absurdres, newest, scenery, depth of field, scenery, volumetric lighting, by tecnicide, furry, furry female, anthro, animal ears, animal nose, snout, animal crossing, (audie (animal crossing):1.4), canine, wolf, half-closed eyes, large breasts, orange fur, body fur, blue eyes, blush, short hair, eyeshadow, makeup, eyeshadow, 1girl, female focus, *****, saliva, drooling, heart symbol, tongue out, orgasm, vaginal penetration, completely nude, lying, on back, spread legs, hetero, ahegao, 1boy, pov, sex, missionary, cum, blush, ejaculation, cum on breasts, cum in *****, cum on body, huge penis, on bed, bed, (motion lines:1.4), simple background
Negative Prompt
futa, futanari, female penis, bad quality, worst quality, worst detail, sketch, censor
Observation 2:
To create a sex scene between two characters (male/female "futa/futanari") with the penetration of one penis into another penis, it is necessary to follow some tips that I will give (in this case, you don't need to use tags like "penis in penis, urethral, urethral penetration, penile penetration"), the Lora already does this automatically, due to the artist mostly creating futanari characters:
Lora Weight = 1
Positive Prompt
masterpiece, best quality, amazing quality, very aesthetic, high resolution, ultra-detailed, absurdres, newest, scenery, depth of field, scenery, volumetric lighting, by tecnicide, furry, furry female, anthro, animal ears, animal nose, snout, (pinkie pie (mlp):1.4), equine, horse, pony, gigantic breasts, large areolae, nipples, puffy nipples, pink fur, body fur, grey eyes, blush, long hair, dark pink hair, 1girl, female focus, *****, saliva, drooling, heart symbol, tongue out, orgasm, vaginal penetration, sweat, sweaty, sweat dripping, completely nude, lying, on back, spread legs, hetero, ahegao, 1boy, pov, sex, missionary, cum, blush, ejaculation, cum on breasts, cum on body, huge penis, simple background
Negative Prompt
futa, futanari, female penis, bad quality, worst quality, worst detail, sketch, censor
In this case, you might find it strange that the prompt indicates the sex of a woman, but the resulting image shows a girl/futanari. This happens because the Lora weight is higher and is influenced by the dataset obtained from the artist's training.
7) 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:Tecnicide_Style_Lora_Illustrious: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:Tecnicide_Style_Lora_Illustrious:1>
8) 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:
Vanessa (Futanari Version)
by tecnicide, vanessa (tecnicide), furry, furry female, anthro, animal ears, animal nose, snout, deer, new world deer, reindeer, brown fur, body fur, brown hair, long hair, black eyes, antlers, horns, jewelry, bracelet, collar, bell, bell collar, slightly chubby, curvy figure, wide hips, voluptuous, thick thighs, huge breasts, small penis, testicles, futa, futanari, 1girl, solo, nipples, looking at viewer, blush, smile, completly nude, plump, navel, sitting, on chair, fork, holding, one hand holding plate, food, one hand holding fork, smile, belly, spreading, spread legs, presenting, front view, light blue background, simple background
Vanessa (Female Version)
by tecnicide, vanessa (tecnicide), furry, furry female, anthro, animal ears, animal nose, snout, deer, new world deer, reindeer, brown fur, body fur, brown hair, long hair, black eyes, antlers, horns, jewelry, bracelet, collar, slightly chubby, curvy figure, wide hips, voluptuous, thick thighs, huge breasts, short tail, 1girl, solo, swimsuit, bikini, huge ass, striped, striped bikini, embarrassed, from behind, looking back, smile, open mouth, teeth, tongue, micro bikini, back, sideboob, naughty face, yellow background, simple background
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
WAI-illustrious-SDXL - v14.0
Lora
Tecnicide Style Lora v1.0 (illustrious) - 0.5 ~ 1.0 (Preferably 1)
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 tecnicide, furry, furry female, anthro, animal ears, animal nose, snout, helluva boss, mythology, loona (helluva boss), canine, ear piercing, ear ring, red sclera, blue eyes, spiked collar, grey hair, long hair, teeth, grey fur, body fur, tail, 1girl, solo, huge breasts, large areolae, areola slip, covered erect nipples. huge ass, plump, overweight female, belly, thick thighs, fingerless gloves, black gloves, swimsuit, black bikini, micro bikini, bikini top only, phone, smartphone, cellphone, dildo, sex toy, smile, grin, teeth, wolf girl, wolf ears, wolf tail, selfie, holding phone, collar, spiked collar, ***** juice drip, ***** juice leaking, ***** juice puddle, ***** juice string, squatting, bottomless, barefoot, shiny body, glistening body, looking at viewer, from side, simple background, dark grey background
Prompt (Negative)
bad quality, worst quality, worst detail, sketch, censor
General Observations:
If possible, give credit to the author Tecnicide while using this LoRA.
Do not sell or commercialize this LoRA.
Do not remove metadata from images generated by LoRA.