模型/EthernalDope - v1.0

EthernalDope - v1.0

|
10/23/2023
|
4:15:12 PM
| Discussion|
0

相關關鍵字和標籤

3D render of a cartoon jester with big eyes in a colorful blue and red costume with a jester hat, created using stable diffusion AI model.
AI generated image using stable diffusion of a creepy clown with wide eyes, red cheeks, and a broad grin, dressed in a colorful red and blue jester costume with a matching hat, seated on a red chair
Anime-style athletic woman wearing sportswear with red and blue jacket, black tights, and sneakers. Created using Stable Diffusion.
Anime girl with orange hair standing on a busy urban street. AI generated image using Stable Diffusion.
A beautiful anime girl with white hair, dressed in a traditional kimono, stands among blooming cherry blossoms. This is an AI generated image using Stable Diffusion.
Close-up of an anime-style character with big eyes and short black hair. She appears to be wearing a dark top and has a slightly sad expression.
This is an AI generated image using stable diffusion, depicting a beautiful anime elf girl with white hair and blue eyes, wearing an intricately designed white and gold robe, posing in a forest with lush green leaves in the background.

推薦提示詞

masterpiece,best quality,ultra-detailed

best quality,solo,1girl,looking at viewer

推薦反向提示詞

EasyNegativeV2,bad-hands-5,blurry,bad anatomy,long legs,poorly detailed,sketch,multiple views,worst quality, low quality:1.4

推薦參數

samplers

DPM++ 2M Karras

steps

20 - 25

cfg

7

clip skip

2

resolution

512x768

vae

vae-ft-mse-840000-ema-pruned.safetensors

other models

makima_offset, Tohru, gotoh_hitori, anime, JinxLol, amber_genshin, Fiolina

推薦高解析度參數

upscaler

R-ESRGAN 4x+ Anime6B, 4x-AnimeSharp

upscale

2

steps

10 - 13

denoising strength

0.4

提示

The generation of hands can be somewhat bad 😿, so it is recommended to use a ControlNet or Lycoris model.

Despite being a merge of models that offer 3D results, the model's output can vary to 2D depending on the lora used.

創作者贊助

Try now EthernalDope on Shakker!!! (and new models that I will upload there first)

Recommended settings

Prompt: (masterpiece, best quality, ultra-detailed)

Negative Prompt: EasyNegativeV2, bad-hands-5, blurry, bad anatomy, long legs,

poorly detailed, sketch, multiple views, (worst quality, low quality:1.4)

Sampler: DPM++ 2M Karras

Sampling Steps: 20 -25

Upscaler: 4x-AnimeSharp / R-ESRGAN 4x+ Anime6B

Hires steps: 10-18

Denoising Strength: 0,4-0,6

Notes:

  • The generation of hands can be somewhat bad 😿, so it is recommended to use a ControlNet or Lycoris model

  • Despite being a merge of models that offer 3D results, the results that this model can generate will vary depending on the lora that is used, giving results in 2D.

上一個
Anime Illust Diffusion XL - v0.5-alpha
下一個
DevlishPhotoRealism - v4.0

模型詳情

模型類型

Checkpoint

基礎模型

SD 1.5

模型版本

v1.0

模型雜湊值

45450b551b

創作者

討論

log in以發表評論。

EthernalDope - v1.0 的圖片

cartoon 圖片

cute 圖片

style 圖片