LoRA, trained at Civitai based on furry artist Ellshed
Support the artist using these links:
https://www.dlsite.com/maniax/circle/profile/=/maker_id/RG06609.html/?locale=ja_JP
1) Always use the tag by ellshed
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 censored, mosaic censoring, pointless censoring tag to the negative prompt if you wish to see images without any type of censorship, as some images composed by Lora were drawn by the author with some type of censorship
7) 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.
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:Ellshed_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:Ellshed_Style_Lora_Illustrious:1>
9) 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:
Kurumi
by ellshed, kurumi (ellshed), human, female, long hair, purple hair, bangs, twintails, green eyes, huge breasts, voluptuous, curvy figure, 1girl, solo, east asian clothing, kimono, haneri, obi, sitting on kness, seiza, hands on legs, smile, teeth, japanese room, temple, indoors, tea, steaming, looking at viewer
Tamami
by ellshed, tamami (ellshed), human, female, futa, futanari, long hair, side ponytail, hair ornament, hair bobbles, black hair, red eyes, huge breasts, huge penis, huge testicles, voluptuous, curvy figure, wide hips, 1girl, solo, large breasts, covered nipples, areolae, lingerie, translucent clothing, bottomless, standing, erection, blush, open mouth, looking at viewer, smile, hands on hips, bedroom, bed, indoors, blurry background, cowboy shot
Christina
by ellshed, christina (ellshed), humanoid, elf, female, long hair, blue hair, purple eyes, long ears, pointy ears, huge breasts, voluptuous, curvy figure, 1girl, breasts, solo, dark blue dress, cleavage, elbow gloves, gloves, blush, looking at viewer, smile, nature, forest, blurry background, cowboy shot
Hina
by ellshed, hina (ellshed), human, female, long hair, brown hair, ahoge, bangs, green eyes, mole under eye, mole, huge breasts, voluptuous, curvy figure, 1girl, solo, large breasts, leaning foward, buruma, white socks, sweat, sweaty, sweat dripping, wet clothing, wet hair, glistening body, shiny body, indoors, gym, blurry background
Linneria Nideus
by ellshed, linneria nideus (ellshed), humanoid, animal humanoid, cat humanoid, domestic cat, feline, feline humanoid, female, long hair, green hair, red eyes, collar, bell, neck bell, huge breasts, voluptuous, curvy figure, tail, 1girl, solo, animal ears, large breasts, nipples, navel, female pubic hair, *****, long hair, sitting, on couch, blush, completely nude, tail, cat ears, smile, spreading, spread legs, indoors, room, blurry background
Below is an initial configuration, but any other type of configuration is up to you: ILLUSTRIOUS
Model
Praeclarus IllustriousXL - v2.0
Lora
Ellshed 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 ellshed, hina (ellshed), human, female, long hair, brown hair, ahoge, bangs, green eyes, mole under eye, mole, huge breasts, voluptuous, curvy figure, 1girl, solo, large breasts, leaning foward, buruma, white socks, sweat, sweaty, sweat dripping, wet clothing, wet hair, glistening body, shiny body, indoors, gym, blurry background
Prompt (Negative)
censored, mosaic censoring, pointless censoring, tears, bad quality, worst quality, worst detail, sketch, censor
General Observations:
If possible, give credit to the author Ellshed while using this LoRA.
Do not sell or commercialize this LoRA.
Do not remove metadata from images generated by LoRA.