Sign In

HEZI_League of Legends v2<HEZI_英雄联盟v2>

13

40

1

Updated: Jul 7, 2025

style

Verified:

SafeTensor

Type

Checkpoint Trained

Stats

40

0

Reviews

Published

Jul 7, 2025

Base Model

SDXL Hyper

Hash

AutoV2
093386E81F
default creator card background decoration
Zcase's Avatar

Zcase

The material uses the League of Legends American promotional illustration material collection, which can well restore the texture of the American promotional illustrations.

This version 2 model has been tested to be more in line with the League of Legends style: strong light and shadow to shape the atmosphere and delicate hand - painted texture processing.

Sampler recommendation: Any sampler is acceptable, and it has good applicability.

Recommended number of iteration steps: About 30.

It is recommended to turn on high - definition restoration: the upscaling algorithm is R - ESRGAN 4x+ Anime6B, upscale by 2 times, and the redraw amplitude is 0.3.

ADetailer is turned on, and the recommended AD model is face_yolov8n.pt.

CFG is 5.5.

CLIP recommendation: 2.

VAE recommendation: It can be turned on or off. The model comes with a built - in VAE encoder, and sdxl_vae can also be turned on, both of which work well.

It has good generalizability. We hope everyone can send back more pictures and give more likes. Thank you.

This model is only for communication and learning and cannot be used for commercial purposes. It is open for download on various platforms. If you fuse it, please mark the original model to avoid unnecessary troubles.素材使用英雄联盟美宣插画素材集,能很好的还原美宣插画的质感,

这一版v2模型经过测试会更像英雄联盟风格:强烈光影塑造氛围细腻的手绘质感处理

采样器推荐:任意都可以,适用性还不错

迭代步数推荐:30左右

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

ADetailer开启,AD模型推荐:face_yolov8n.pt

CFG为:5.5

CLIP推荐:2

VAE推荐:可开启也可不开,模型自带vae编码,也可以开启sdxl_vae,效果都不错。

泛化性很好希望大家多返图多点赞,谢谢

此模型仅用作交流和学习,不可商用,在各个平台开放下载,如果融合请标注原模型以免不必要的麻烦。