ghost
Sign In

DunhuangMix 敦煌 飞天 古风

364
1.8k
19
Updated: Oct 5, 2024
styleanimesexywomanrealistic敦煌
Verified:
SafeTensor
Type
Checkpoint Merge
Stats
1,201
Reviews
Published
Jul 17, 2023
Base Model
SD 1.5
Trigger Words
dunhuang
dunhuang_background
dunhuang_face
Hash
AutoV2
63FE8C365E
default creator card background decoration
ArienTOP's Avatar
ArienTOP

敦煌大模型,使用了大批量的敦煌素材进行训练,并且多次筛选融合而来。

大模型与敦煌lora有什么区别:

1.模型的训练集合更大,更高清,细节还原更好

2.更趋向与真实的质感和光影,dunhuangV3版本为了兼容动漫和真实模型,更偏向于2.8D,衣物流线型更飘逸,各有取舍

3.对真实场景的泛化性更强

4.出图稳定性增强,简单提示加抽卡,可以获得高质量作品,上手门槛更低

5.肢体和脸更稳定

以下为推荐参数:

vae:840000

采样:DPM++ 2M SDE Karras

步数:20-30

高分辨率修复 (Hires. fix):高清修复一定要开!!!

高清迭代步数:15-20

放大算法:8x_NMKD-Superscale_150000_G或者R-ESRGAN 4x+

重绘幅度:0.25-0.4

放大倍数:2或者2以上

cfg:7(可自由尝试)

特别鸣谢:墨幽、Majic,融合的大模型中包含MajicV6,墨幽完整版V1010

Dunhuang large model, using a large number of Dunhuang materials for training, and several screening fusion.

The following are recommended parameters:

vae: 840000

Sample: DPM++ 2M SDE Karras

Number of steps: 20-30

Hires: HD fix must be on!!

Hd iteration steps :15-20

Amplification algorithm: 8x_NMKD-Superscale_150000_G or R-ESRGAN 4x+

Redraw range: 0.25-0.4

Magnification: 2 or more

cfg: 7 (Free to try)