Thank you, I'm glad you liked the model.

Thank you!

Здравствуйте, спасибо за ваш отзыв! Рад, что вам нравится эта модель.

Hello,

When using DMD2 Speed ​​LoRA, I use the following settings:

Clip Skip: 1 or 2

Steps: 9 (lower values ​​are possible)

LoRA Weight: 0.7 or 1.0

Sampler: LCM

Scheduler: Normal

CFG: 1.2 or 1.4

Noise Multiplier for img2img: 1.1

I enable ADetailer, but disable the ADetailer detector.

For normal generation, three settings are available. 1.

Clip Skip: 1 or 2

Sampler: DPM++ 2M SDE

Templates: Karras

Steps: 42

CFG: 5.5

Noise Multiplier for img2img: 1.1

ADetailer on

ADetailer detector on "face_yolov8n.pt", but you can use any other.

2.

Skip Clip: 1 or 2

Sampler: DPM++ 2M SDE

Templates: Karras

Steps: 31

CFG: 4.0

Noise Multiplier for img2img 1.1

ADetailer on

ADetailer detector on "face_yolov8n.pt", but any other detector can be used.

3.

Skip Clip: 1 or 2

Sampler: DPM++ 2M SDE

Templates: Karras

Steps: 30

CFG: 6.0

Noise Multiplier for img2img 1.1

Turn on ADetailer

Turn on ADetailer detector "face_yolov8n.pt", but any other detector will do.

I enhance the image.

Recommended settings

Highres.fix: Scaling 1.5

Scaling 4x_foolhardy_Remacri (1xDeNoise_realplksr_otf or OmniSR_X4_DIV2K)

Highres steps: 10

Noise reduction level: 0.1 or 0.28; 0.4; 0.48; 0.50; 0.58 (I most often use 0.1)

But you can experiment, no one is stopping you from using other settings!

I noticed that many LoRA for Pony (lighting, realism, body shape) work with this model.