Models>

Shadow Puppets Art Style | 皮影戏

piying, piying ride a horse, simple_background, weapon, white_background <lora:piying-000010:1>
piying, masterpiece, upper body, best quality, 1girl, smile, odanobunaga, <lora:piying-000010:1> <lora:odanobunagaFGO-000010:0.8>
piying, odanobunaga, porttrait, white_background <lora:piying-000010:0.6> <lora:odanobunagaFGO-000010:1>
Quick Generate
Select a style, write what you want to see and click Generate
What you want in the image.
Clear
Random
* This model is available for use and will generate similar character to the ones seen in the images.

Model Description by Creator

皮影戏是一种以兽皮或纸板做成的人物剪影以表演故事的民间戏剧,是一种中国民间古老的传统艺术。

Shadow puppetry is a folk drama that uses cut-out figures made of animal hide or cardboard to perform stories. It is an ancient traditional art form in China.

(你好,这是我上传到本站的第二个lora,它由皮影戏小人训练而成,具有很强的剪纸风格、平面风格、复古色彩风格与反复的装饰线条。和上一个兰那罗生成器一样,是一个怪怪的但很有趣的模型。希望你喜欢它!:)

Hello, this is my second Lora uploaded to this website. It was trained using shadow puppetry figures and is characterized by strong paper-cutting style, flat style, retro color style, and repeated decorative lines. Like the previous Lora generator, it is a strange but interesting model. I hope you like it! :))

触发词: piying

通过添加“piying ride a horse”来触发经典的皮影骑马小人动作。通过添加“lingzi hat”来触发翎子,也就是皮影小人头上长长的羽毛。当附加词未起作用时,可以尝试使用括号来加强它,例如“(((lingzi)))”。使用“Beijing Opera”、"Beijing opera costume"等tag或许能产生更好效果。

基于anythingV4.5训练,在大部分二次元风格模型中适应良好,但也有概率生成“非人之物”,需要多尝试合适提示词多抽卡。未尝试在写实风格模型中使用,感觉会产生邪神。如果有人尝试出成果,请务必传上来让我看看。

与其他风格化、人物Lora适应性良好,但需要调试二者的强度比例来达到预期效果。当人物lora权重较低,本lora权重较高时,倾向于产生具有角色特征与色调的皮影小人,当本lora权重较低时,则倾向于产生具有皮影戏风格的、平面的、装饰繁复的人物(或者兰那罗)。你或许可以使用较低的权重把它当做一个东方复古风格的风格化lora来使用。具体强度还请亲自试试或者参考我的样例图片。

Trigger word: piying

Adding "piying ride a horse" triggers the classic action of a shadow puppet riding a horse. Adding "lingzi hat" triggers "lingzi," 翎子 which refers to the long feathers on top of a shadow puppet's head. When the additional words do not work, try using parentheses to strengthen them, for example, "(((lingzi)))". Using tags such as "Beijing Opera" or "Beijing opera costume" may produce better results.

Trained on anythingV4.5, it adapts well to most anime-style and2-D models. However, there is also a probability of generating "inhuman things", and you need to try more suitable prompt words and draw more cards. I have not tried it on realistic models as it may produce a terrifying figure. If anyone has achieved any results, please share them with me.

It adapts well to other stylized and character Loras, but the strength ratio of the two needs to be adjusted to achieve the desired effect. When the weight of the character Lora is low and the weight of this Lora is high, it tends to produce shadow puppets with character features and color tones. When the weight of this Lora is low, it tends to produce flat, intricately patterned characters (or Aranara). You may use the lower weight as an oriental retro-style stylized Lora. Please experiment with the strength personally or refer to my sample pictures.

本模型基于互联网图片训练而成,lora所生成图片禁止用于任何商业活动。如果生成了任何有趣的结果,欢迎上传让大家都乐乐 :)

This model was trained on internet images. The generated images by Lora are not to be used for any commercial activities. If any interesting results are generated, please upload and share with everyone. : )

Images Generated With This Model

Loading...

Train Models

Train AI Models On Your Own Pictures

You can use your own pictures to train AI models. Reimagine yourself in new ways with our AI-powered image generator.
Create pictures of yourself around the world, in your dream outfit, as a video game character, or in countless art styles. The possibilities are endless.
Train Your Own Model

Generate AI Images. Simple and Easy

AIEasyPic is the #1 AI image generator. Generate images with simple prompts, swap faces, train models to reimagine yourself, and more.