⚙️ Recommended Settings
🌸 Qwen Image 2.1
Tested with:Qwen Image 2.1 int8_convrot
LoRA weight:
0.8CLIP strength:
0.8Steps:
25CFG Scale:
1.0Sampler:
EulerScheduler:
Simple
🎨 Krea 2
Tested with:
DaSiWa Krea2
Steps:
10CFG Scale:
1.2Sampler:
EulerScheduler:
SimpleDenoise:
1.0
✨ Illustrious
Tested with:CyberIllustrious Semi and WAI
LoRA weight:
0.8Steps:
40CFG Scale:
3.0–4.0Sampler:
DPM++ 3M SDE GPUScheduler:
Karras
🐰 Anima
LoRA weight:
0.8Steps:
40CFG Scale:
3.0Sampler:
er_sde/normalScheduler:
Beta
🐴 SDXL / Pony
Tested with:CyberRealistic Pony and Pony checkpoints by Stable_Yogi
LoRA weight:
0.8Steps:
40CFG Scale:
3.0–4.0Sampler:
DPM++ 3M SDE GPUScheduler:
Karras
These settings are recommended as a starting point. Adjust the LoRA weight and CFG scale depending on your checkpoint, prompt, and desired style.
Description
The training principle has been greatly changed, which has led to improved diversity in image generation

















