models/CFG_Slider - cfg_slider02

CFG_Slider - cfg_slider02

|
8/9/2025
|
7:11:38 PM
| Discussion|
0
Abstract portrait of a figure with large eyes and swirling patterns in aqua and black, featuring synthetic overlay light and chromatic aberration effects.
A noir-style ink and sketch illustration showing a mysterious character with a shadowed face and wrapped arm, highlighted by a sepia spotlight and textured halftone background
A dark silhouette of a figure standing in a dimly lit room with cobalt blue and ivory fractured light patterns illuminating behind and beneath them, featuring glitch effects and watercolor textures.
A dark silhouette of a figure with glowing orange eyes and mouth, wearing a hoodie with a smiling sun emblem, standing with bandaged leg and heavy shadows.
Anime-style girl with blue hair and pink streak, wearing a pastel rose and blue floral dress, leaning on a wooden bridge with roses and water background.

Recommended Parameters

samplers

DPM, Euler_a

steps

10

cfg

1 - 15

Tips

Higher CFG (10-15) images with positive lora weight are less overexposed and less cartoon-like.

Lower CFG (1-3) images with negative lora weight are very realistic but can be boring; use negative lora weight to add mood.

For Euler_a sampler, CFG around 4 with steps ~10 and lora weight between -0.4 and -0.8 works like a turbo setting.

In portrait generation, adding negative lora weight at low CFG (e.g., 2) can create messier, more interesting hair.

Plus lora weight at high CFG (e.g., 12) can yield more realistic images.

Version Highlights

smaller, only a bit different


*** Its a Tool - LORA ! ***

...

higher CFG(10-15) images with a plus-lora are not so overexposed or have that cartoon style.

same meaning in the other way, low CFG(1-3) images mostly very real but also very boring, so with negativ-lora weight you can "pimp up" the moody.

...


in short words let me explain...

It seems that this is a kind of CFG slider (but more), for example

CFG ~ 2 -> loraweight:-0.5 (in this combiniation you get good images)

CFG ~ 12 -> loraweight: 0.5 (in this combiniation you get good images)

for DPM Sampler

...

for Euler_a it seems some kind of turbo

CFG~4

Steps ~10

loraweight: -0.4 to -0.8


  • maybe its useful for turbo/lcm models to have a smoother cfg/slider ?!?

  • for abstract art -> minus is more real, plus is more abstract/fantasy

  • for face portraits, lets say you have a prompt:

eg

"portrait photo of a 20yo messy blond haired woman. wears a offices suite."

cfg 2 - hair ist not that messy and borring surrounding

cgf 5 - hair is messy

cgf 12 - the hair are more messy, but somehow overexposed/cartoon

on cgf 2: you can use that lora with a weight arround -0.5 to get a more interesting image with very messy hair ;)

on cgf 12: you can use it with weight arround 0.5 to get mroe real images

.


dont blame me its a tool, maybe you can play with it and tell me more ;)


:*


Previous
ALF mix (IL, 8 steps generation) - v4.3 [final]
Next
Quality Embeddings For Furries - Quality - updn

Model Details

Model type

LORA

Base model

SDXL 1.0

Model version

cfg_slider02

Model hash

7f81a13630

Discussion

Please log in to leave a comment.

Images by CFG_Slider - cfg_slider02

art Images

tool Images