CyberRealistic XL - v5.7
推薦反向提示詞
cartoon,illustration,anime,painting,CGI,3D render,low quality,watermark,logo,label
sdxl_cyberrealistic_simpleneg
推薦參數
samplers
steps
cfg
resolution
推薦高解析度參數
upscaler
upscale
steps
denoising strength
提示
Adetailer model used: face_yolov9c.pt for face refinement
Set 'Mask only the top k largest' to 1 for refining only main face
版本亮點
A quick refinement release of CyberRealistic XL, blending in select training data from other CyberRealistic models for subtle but effective improvements. Includes minor cleanup, slightly enhanced male rendering, and overall polish. Not a major leap- just a smoother, cleaner version
As always, it’s completely free and no early access nonsense.
創作者贊助
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)