⚙️ Recommended Settings

🌸 Qwen Image 2.1

Tested with:
Qwen Image 2.1 int8_convrot

• LoRA weight: 0.8

• CLIP strength: 0.8

• Steps: 25

• CFG Scale: 1.0

• Sampler: Euler

• Scheduler: Simple

🎨 Krea 2

Krea 2 checkpoints may require different sampling parameters, so these settings are not universal.
I personally tested this LoRA with the following model and settings:

Tested with:
muse ByStableYogi 3 turbo int 8/realism ByStableYogi 2 turbo int8

• Steps: 10

• CFG Scale: 1.2

• Sampler: Euler

• Scheduler: Simple

• Denoise: 1.0

Other Krea 2 models may work better with different Steps, CFG, Sampler, and Scheduler values. These are simply the settings I used for testing.

✨ Illustrious

Tested with:
CyberIllustrious Semi and WAI

• LoRA weight: 0.8

• Steps: 40

• CFG Scale: 3.0–4.0

• Sampler: DPM++ 3M SDE GPU

• Scheduler: Karras

🐰 Anima

• LoRA weight: 0.8

• Steps: 40

• CFG Scale: 3.0

• Sampler: er_sde/normal

• Scheduler: Beta

🐴 SDXL / Pony

Tested with:
CyberRealistic Pony and Pony checkpoints by Stable_Yogi

• LoRA weight: 0.8

• Steps: 40

• CFG Scale: 3.0–4.0

• Sampler: DPM++ 3M SDE GPU

• Scheduler: Karras

These settings are recommended as a starting point. Adjust the LoRA weight and CFG scale depending on your checkpoint, prompt, and desired style.