Profile of an elderly woman made up of brittle brown oak leaves showing detailed wrinkles, under warm afternoon sunlight with a dry brush texture.
A solitary traveler walks along a narrow path inside a mystical cave with towering colossal limestone pillars bathed in soft golden light and long shadows.
Hyperdetailed colored pencil portrait of a girl with twin braids wearing a black dress with white polka dot collar, holding a thorny stem with blood, against a cemetery background.
Close-up symmetrical portrait of a robot geisha with detailed cybernetic face, blue metallic makeup, and grunge iron armor on white background.
A detailed, intricate illustration of a black woman with long black hair, wearing transparent gothic golden clothes, adorned with tattoos, and large golden black swan wings, on a neutral background.
A mysterious figure draped in a vibrant red shawl stands on black stairs with delicate line art swirling smoke in the background.

推奨ネガティブプロンプト

cartoon,illustration,anime,painting,CGI,3D render,low quality,watermark,logo,label

cartoon, illustration, anime, painting, CGI, 3D render, low quality, watermark, logo, label

推奨パラメータ

samplers

DPM++ 2M SDE Karras, DPM++ 2M SDE

steps

30

cfg

3 - 5

resolution

832x1216, 896x1152, 832x1216

推奨ハイレゾパラメータ

upscaler

4x_NickelbackFS_72000_G, 4x_foolhardy_Remacri, 4x_NMKD-Siax_200k

upscale

1.5 - 2

steps

15

denoising strength

0.35

ヒント

No need for complicated prompts - just let your imagination run wild.

Adetailer can be used optionally with face_yolov9c.pt model to refine faces.

To refine only the main face, set 'Mask only the top k largest' to 1 in Adetailer.

バージョンのハイライト

This updated version of CyberRealistic SDXL features a number of improvements: I've cleaned up some elements, added new details, and enhanced the rendering of light and effects for a more dynamic and polished look.
It can produce more NSFW results than earlier versions - but only if you want it to. It remains fully capable of generating SFW content depending on your prompts.
As always, some people might prefer an earlier version - and that's okay. Every update brings changes, and this is the natural evolution of the model.

クリエイタースポンサー

Want to buy me coffee? (Buy a cup

Civitai onsite generation enabled

This model was built with two key goals in mind: simplicity and versatility. No need for complicated prompts (unless you're into that sort of thing) - just let your imagination run wild.

Have fun and enjoy the ride!

Personal settings

Sampling method: DPM++ 2M SDE Karras 
VAE: is already Baked In
Sampling steps: 30+ Steps
Resolution: 832x1216 / 896x1152
CFG: 3-5
Clip Skip: 1
Upscale: 1.5 upscale (0.3 - 0.35 denoise)
Upscalers: 4x_NickelbackFS_72000_G / 4x_foolhardy_Remacri / 4x_NMKD-Siax_200k

Example negative prompt:

cartoon, illustration, anime, painting, CGI, 3D render, low quality, watermark, logo, label

or use CyberRealistic Negative


Adetailer settings (if you want to use it, it's not always needed.)

Adetailer model: face_yolov9c.pt
If you only want the main face being refined set 'Mask only the top k largest' to 1.

Want to buy me coffee? (Buy a cup)

前の画像
Ernest Normand Style Painting (FLUX) - flux v1
次の画像
Takayanagi Katsuya style | Illustrious - v1.0

モデル詳細

モデルタイプ

Checkpoint

ベースモデル

SDXL 1.0

モデルバージョン

v5.6

モデルハッシュ

4693ce53c2

作成者

ディスカッション

コメントを残すには log in してください。