Description
No fan base, if you have any questions, contact us on WeChat: laoxiatiao518 Email:
[email protected] and simply
The prompt runs straight ahead
Reverse hint words: (no trigger words)
This model uses 512-1024 Picture Training
The drawing is detailed, clear and beautifulRecommended image size: 512, 768, 1024,
Full body support:
(Close View, Medium View, Long View, Full Body)Sampling method:
dpm++ 2m karrasHigh resolution recommendations:
8x-nmkd-superscale, r-esrgan_4x+ anime6b,4x-ultrasharp(Recommended when high resolution is not turned on,
Add words such as captions (8k) and (Ultra HD) to enhance the image quality.)Recommended number of samples: Default recommendation 25
(Can also be upgraded and adjusted according to PC configuration)Cue guidance coefficient: 7-10