模型/Realism Engine SDXL - v10

Realism Engine SDXL - v10

|
10/25/2024
|
7:44:43 AM
| Discussion|
0
AI generated image of twin models posing in form-fitting winter outfits with gloves, standing in front of a snow-covered forest and tree using stable diffusion
Two women in leather catsuits posing outdoors in a winter setting. AI generated image using Stable Diffusion.
Two athletic models wearing black bodysuits in an outdoor setting, AI generated using stable diffusion.
Mummy woman in detailed Halloween costume, an AI generated image using stable diffusion.
A funny AI generated image using stable diffusion of a bear dressed in a uniform with a red hat, running with an expression of surprise or excitement.
Close-up of a wet female boxer with red boxing gloves, intense eyes, and wet hair. This is an AI generated image using stable diffusion.

推薦提示詞

film,bokeh,professional,4k,highly detailed

推薦反向提示詞

drawing,painting,crayon,sketch,graphite,impressionist,noisy,soft,3d render,deformed,blurry,ugly

推薦參數

samplers

DPM++ 2S a

steps

25

cfg

6 - 9

resolution

896x1152, 832x1216

vae

sdxl_vae_reverted.safetensors (63aeecb90f)

other models

RealismEngine_SDXL_v1.0 (7b399aa4be), RealismEngine_SDXL_v1.0 (e1fb5c7e14)

推薦高解析度參數

upscaler

ESRGAN_4x

upscale

1.5 - 2

steps

30 - 60

denoising strength

0.3 - 0.35

提示

Look for this in Setting -> Stable Diffusion

You can also add hires_fix_refiner_pass to your quick list setting to have it on top of your UI.

版本亮點

Better eyes, even better realistic look

創作者贊助

Version 3.0 of the Realism Engine

In this version we improved the skin realism, the eyes. We also improved the Male anatomy.

Keep in mind that this is not a NSFW model. For that I recommend SDXXXL.

Introducing Version 2.0 of the Realism Engine

We are excited to announce that Version 2.0 of the Realism Engine is now available, featuring significant enhancements.

This updated model exhibits superior prompt responsiveness and offers markedly improved overall coherence, including more facial expressions, a greater variety of faces, more poses, and improved hands.

Additionally, we have addressed several quirks from the previous version, such as the challenges in generating nighttime scenes and the issue where increasing the CFG Scale enhanced color vividness without proportionally adjusting contrast. While being capable of producing NSFW content it is less likely to produce it without asking.

This version include the VAE to help newcomers with their setup.

Happy Prompting

Good news for the fans of the original Realism Engine

Realism Engine SDXL is here

Version 1.0 is officially out.

Here's the recommended setting for Auto1111

Sampler: DPM++ 2S a,

CFG scale range: 5-9,

Hires sampler: DPM++ SDE Karras,

Hires upscaler: ESRGAN_4x,

Refiner switch at: 0.9 (ON THE FIRST PASS ONLY)

Look for this in Setting -> Stable Diffusion
You can also add hires_fix_refiner_pass to you quick list setting to have it on top of you Ui

While this model hit some of the key goals I was reaching for, it will continue to be trained to fix the weaknesses.

I appreciate all the good feedback from the community.

上一個
MixTape Blues - v30 Soul Baked VAE
下一個
Realities Edge XL LIGHTNING Turbo - 20

模型詳情

模型類型

Checkpoint

基礎模型

SDXL 1.0

模型版本

v1.0

模型雜湊值

e1fb5c7e14

創作者

討論

log in以發表評論。