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.
Description
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主页链接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，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，V2触发词：Qing Kung（非必要）
V3版偏插画风，主要提供武术动作和插画风构图V3触发词： martial（非必要）
Intensive training for SD's poor martial arts,
Example picture with 2 dimensional drawing base map in the use of realistic model to strengthen the details (will not go to my home page link B station tutorial)
Straight out diagram can see my backmap area example diagram,
Direct realistic composition may not have a 2-dimensional good sampler: DDIM is recommended for drawing the bottom map, and the map is at will.
Steps recommended 33-55, HD steps recommended 22-33,
V1, featuring martial arts action and smoke background,
V2 version of Feitian, mainly provides light Kung action composition, V2 trigger word: Qing Kung (not necessary)
V3 version partial illustration style, mainly provides martial arts action and illustration style composition V3 trigger word: martial (not necessary)