I'm on a very niche model again, and if anyone likes it, I'll continue to optimize it.

First of all, thanks to @遇见清风 for providing the materials and creating with me.

-----------------------------------------------------------------

[Model introduction and parameter

suggestions] Can produce a skeletal body~ ( (Obvious)

The

trigger

word is: skeleton skeleton

The weight recommendation for LORA is around 0.6, which is suitable for simple hints. Large models can be paired with realistic models or two-dimensional animations.

The large models used in the example are these two: dreams and everyday life, and dreams and fantasies.

Because of a website problem, I didn't post a link. You can search directly or use it with other big models.

-----------------

All the parameters are complete on the example image! Everyone is welcome to try it!

Welcome back to the picture! Thanks.

Here is the size of the parameter I used the most in my example image:

512x768 (I usually only drive this big for speed, then turn on HD repair) Sampler: DPM++3M SDE Karras

Steps: 30

Hires upscaler: R- ESRGAN 4x+

Denoising

strength: 0.5,

Clip skip: 2,

Hires upscale: 2,

Hires steps: 20,