用戶LoRA

XL
風格

Furry Dragon Lora v1

#熟女#男性#獸人#龍#女孩#褐色皮膚男性#肌肉男#熟男#男性獸人#雌性獸人
Furry Dragon Lora v1 - AI Model封面圖片
訓練者
Avatar image of homer_26

homer_26

上傳時間
2024年8月12日 晚上7:49
使用數
20.3k
評論
非常好  (1)
許可權
  • 允許圖片生成與分享
  • 允許使用者下載此模型
  • 允許生成圖片用於商業用途

推薦 LoRA

描述

Lora for generating anthropomorphic Dragons (male/female) using different angles, styles, colors and poses.

  1. This LoRA was based on the SDXL version

  2. Even though the Pony V6 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 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.

  3. Don't forget to use related tags if you use the pony model.

score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up,

  1. LoRA weight change in Civitai is at your discretion

  2. Some SDXL/Pony models will have some kind of artifacts, distortions or will not be compatible with this LoRA, it is up to you to choose the best option.

  3. For realistic models, I recommend using a Sampler from the DPM++ family or UNI PC if you are using ComfyUI

  4. Steps and CFG use according to the model / LoRA author's recommendation

Below is an initial configuration, but any other type of configuration is up to you:

Model

Pony Diffusion V6 XL

Lora

Furry Dragon Lora - 0.5 ~ 1.0 (Preferably 1)

Advanced

CFG Scale - 5.0 ~ 9.0 (Preferably 8)

Sampler - DDIM / Euler a / Euler / DPM++ 2M Karras / DPM++ 3M Karras / Uni PC

Steps - 20 ~ 50 (Preferably 30)

Clip Skip - 1/2

VAE - none

Prompt (Positive)

score_9, score_8_up, score_7_up, dragon, furry, anthro, mythological creature, mythological scalie, mythology, scalie, tapering penis, erection, genital slit, genitals, membrane (anatomy), wings, tail, dragon wings, bara, muscular male, male focus, solo, muscular, 1boy, pectorals, abs, penis, large pectorals, nipples, erection, standing, horns, nude, thick thighs, looking at viewer, navel, veins, random pose

Prompt (Negative)

score_6, score_5, score_4, zPDXL-neg, 3D, human

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:

Do not sell or commercialize this LoRA

Do not remove metadata from images generated by LoRA.

留言