HosekiMix

https://civitai.com/models/312836

Parameters I use : Positive prompt : masterpiece, best quality

Negative prompt : (worst quality, low quality:1.4), signature, watermark, username, blurry

Sampler : DPM++2M Karras - 25 steps

CFG Scale : 5

Hiresfix : 4x-AnimeSharp-lite - 0.4 denoising

Clip Skip : 2

VAE : kl-f8-anime2

The VAE is not baked in, so you can download it or use another one if you'd prefer.

I also used the EasyNegative embedding for the negative prompt, and adetailer for more detailed faces.

The models in the merge are DivineEleganceMix (v6), YesMix (v1.5), GalenaREDUX (v2), seizaMix, AingDiffusion (v9), and Sudachi.

This is my first merge, so I'm probably going to update this at some point, let me know if there's any problems!