HEZI Fifth personality Illustration 2.0<HEZI_第五人格插画2.0>

LORA
Original


Updated:

Bottom mold recommendation: The whole net first | SHMILY classical colorful _v1.0,

VAE is recommended: vae- FT-MSE-84000-EMA-Pruned.safetensors

Recommended sampler: DPM++ 3M SDE,DPM++ 2M Karras, Euler a,

Recommended number of iteration steps: 30

It is recommended to open the HD repair: the magnification algorithm is R-ESRGAN 4x+ Anime6B, magnification is 2 times, and the redraw amplitude is 0.3~0.6

ADetailer is enabled. Recommended AD model: face_yolov8n.pt

The recommended weight for lora is 0.5-0.75

CFG: 5.5

CLIP Recommended: 2

The generalization is very good and can be combined with other lora, I hope you can return more pictures and praise more, thank you


底模推荐:全网首发|SHMILY古典炫彩_v1.0,

VAE推荐开:vae-ft-mse-840000-ema-pruned.safetensors

采样器推荐:DPM++ 3M SDE,DPM++ 2M Karras,Euler a,

迭代步数推荐:30

推荐开启高清修复:放大算法为R-ESRGAN 4x+ Anime6B,放大2倍,重绘幅度为0.3~0.6

ADetailer开启,AD模型推荐:face_yolov8n.pt

lora权重推荐0.5-0.75

CFG为:5.5

CLIP推荐:2

泛化性很好可结合其他lora,希望大家多返图多点赞,谢谢

Version Detail

SD 1.5

Project Permissions

    Use Permissions

  • Use in TENSOR Online

  • As a online training base model on TENSOR

  • Use without crediting me

  • Share merges of this model

  • Use different permissions on merges

    Commercial Use

  • Sell generated contents

  • Use on generation services

  • Sell this model or merges

Comments

Related Posts

No posts yet
Describe the image you want to generate, then press Enter to send.