









This was originally intended to be an update of another mix of mine, but I thought it ended up being unique enough to maintain as its own thing.
It is prone to generating ??????????? women.
Images generated using Berry's Mix VAE and 4X AnimeSharp Upscaler at Clip Skip 2
VAE is already baked in
My typical settings for images:
Sampler - DPM++ 2M SDE Karras / Euler a
Sampling Steps - 35 to 40
HiRex Fix - Upscaled by 2 at 15 to 20 steps, 0.35 Denoising Strength
Dimensions - 512x512, 512x768, or 768x512
CFG Scale - 5.5 to 7
Two passes of ADetailer
1st pass: face_yolov8n.pt
2nd pass: mediapipe_face_mesh_eyes_only or hand_yolov8n.pt
See images for examples of how I prompt. I prefer short, simple, tag-based prompts, but there is probably a lot of room for flexibility/improvement here
1. Hak untuk model yang diposting ulang adalah milik pembuat aslinya.
2. Pencipta asli yang ingin mengklaim model harap hubungi staf SeaArt AI melalui saluran resmi. Klik untuk mengklaim
