Read the version details and recommendations in the "About this Version" section first.
LoRA, trained at Civitai based on furry artist Syn-6
or known as Tesamo Saba / SYN6 / fantaleaves
Support the artist using these links:
https://www.furaffinity.net/user/fantaleaves/
https://e621.net/posts?tags=syn-6
1) Always use the tag by syn-6
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) For ANTHRO characters, add FERAL at the negative prompt, for FERAL characters, add ANTHRO at the negative prompt. Doing this should force some characters into Lora at the prompt you typed, avoiding inconsistencies, remembering that this is not MANDATORY, but it is my recommendation.
8) 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:Syn-6_Style_Lora_Illustrious:1>
Pony (v1.0)
<lora:Syn-6_Style_Lora:0.8>
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:Syn-6_Style_Lora_Illustrious:1>
Pony (v1.0)
Civitai slider = 0.8 positive prompt: <lora:Syn-6_Style_Lora:0.8>
8) I added tag related to the artist's best-known character, if you want an image close to the character, don't forget to enter the character's name, I will leave example of prompt positive right below each character:
Jessica (Feral)
by syn-6, jessica, dobermann, pinscher, domestic dog, canid, canine, canis, feral, furry, female, eyelashes, bedroom eyes, makeup, narrowed eyes, grey nose, grey fur, grey body, pawpads, paws, claws, female focus
Jessica (Anthro)
by syn-6, jessica, dobermann, pinscher, domestic dog, canid, canine, canis, anthro, furry, female, eyelashes, bedroom eyes, makeup, narrowed eyes, grey nose, grey fur, grey body, flat chested, anatomically correct, animal genitalia, solo, panties, underwear, hood, thighhighs, tail, furry female, hood down, jewelry, male focus, animal ears, black thighhighs, snout, blush, pubic hair, hoodie, bracelet, navel, 1boy, earrings, no pants, smile, cowboy shot, bangle, bulge, standing, highleg panties, animal nose
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
Syn-6 Style Lora - v1.0 (illustrious) - 0.5 ~ 1.0 (Preferably 1)
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 syn-6, furry, furry female, anthro, domestic dog, canine, labrador, retriever, yellow fur, body fur
Prompt (Negative)
feral, teats, multibreasts, human, multiple tails, modern, recent, old, oldest, graphic, cartoon, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured, long body, lowres, bad anatomy, bad hands, missing fingers, extra digits, fewer digits, cropped, very displeasing, (worst quality, bad quality:1.2), bad anatomy, sketch, jpeg artifacts, signature, watermark, username, simple background, conjoined, bad ai-generated
PONY (v1.0)
Model
Pony Diffusion V6 XL - V6 (Start with this one)
Lora
Syn-6 Style Lora - v1.0 (Pony) - 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)
score_9, score_8_up, score_7_up, by syn-6, absol, generation 3 pokemon, pokemon, canid, canine, female focus, 1girl, furry female, feral, 4 toes, toe claws, claws, toes, anatomically correct, pawpads, paws, nipples, presenting, looking back, lying, yellow background
Prompt (Negative)
zPDXL3, 3D, 2D, human, anthro
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 SYN-6 while using this LoRA.
Do not sell or commercialize this LoRA.
Do not remove metadata from images generated by LoRA.