Verified: 5 months ago
SafeTensor
Type | |
Stats | 1,221 7,679 |
Reviews | (147) |
Published | Jun 26, 2024 |
Base Model | |
Trigger Words | XUER martial arts style |
Hash | AutoV2 B358927F58 |
针对SD画不好武术做的强化训练,
例图为用2次元画底图在用写实模型来强化细节(不会的可以去看我的B站教程)
直出图可以看我返图区例图,
直接用写实可能构图没有2次元好采样器:画底图推荐DDIM,跑图随意。
步数推荐33-55,高清步数推荐22-33,
V1版这个LORA提供武术动作和烟雾背景,
V2版飞天,主要提供轻功的动作构图,
V3版偏插画风,主要提供武术动作和插画风构图
提示词看例图,V2触发词:Qing Kung(非必要)
V3触发词: martial(非必要)
I found a new AI tool Shakker, a best image to image tool. You can try it via ,it can help you:
-Remix: Upload a picture. Just switch the prompts, and you can create stunning images in the same style.
-Style Transfer: Shakker not only extracts the style,but also switches among various styles.
Besides, Shakker also offers Object Control,Composition Control,Collage Redrawing etc.