Tensor.Art
在线生图

May猫娘/cat girl Lora

LORA
原创 · 创作者激励计划

513

大家好,我是chosen鲷,这次带来的是May猫娘lora。

这是一个风格类lora,训练集采用的may老师的p站图,我记得她以前叫naru的,一个韩国画师,不知道啥时候改名叫may了。比较出名的就是那个红衣服的猫娘图,在几年前非常广为流传,大家估计多少在各种地方看到过。

lora不会过拟合,建议权重0.8。触发词:catgirl

推荐的tag:

(masterpiece:1.2),best quality,PIXIV,cat girl,
这里写你想要的内容
<lora:cat girl-000018:0.8>,
Negative prompt: EasyNegative,badhandsv5-neg,Subtitles,word,
Steps: 32, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 2955709983, Size: 512x768, Model hash: c3ff8d00a6, Model: chosen irises bake vae, VAE hash: ab33ad55c6, VAE: ClearVAE_V2.3.safetensors, Denoising strength: 0.5, Clip skip: 2, Hires upscale: 2, Hires steps: 12, Hires upscaler: R-ESRGAN 4x+, Lora hashes: "cat girl-000018: 635f3c27969e", TI hashes: "EasyNegative: 66a7279a88dd, badhandsv5-neg: aa7651be154c", Version: v1.6.0-2-g4afaaf8a

大模型我推荐用我的chosen irises(就是下方推荐里第一个)vae用clear,其他的常见模型诸如ghost一类的也都可以,这模型的兼容性还不错,推荐使用兼容性好的二次元大模型.

感谢大家的下载使用,如果喜欢的话欢迎关注我,我的bilibili pixivID均为chosen鲷,欢迎大家关注我的频道https://space.bilibili.com/3867754?spm_id_from=333.1007.0.0https://www.pixiv.net/users/40911695谢谢。

The following content is from Google Translate

Hello everyone, I'mchosen鲷, and this time I bring you cat girl lora.

This is a style-based lora model trained on images from May's Pixiv account. I remember she used to be called "naru," a Korean artist, but I don't know when she changed her name to May. One of her most famous artworks is the cat girl in a red dress, which gained a lot of popularity a few years ago and was widely circulated in various places.

Lora doesn't overfit, so I recommend a weight of 0.8. Trigger phrase: cat girl

Recommended tags:

(masterpiece:1.2), best quality, PIXIV, cat girl, [Here you can write your desired content] <lora:cat girl-000018:0.8>, Negative prompt: EasyNegative, badhandsv5-neg, Subtitles, word, Steps: 32, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 2955709983, Size: 512x768, Model hash: c3ff8d00a6, Model: chosen irises bake vae, VAE hash: ab33ad55c6, VAE: ClearVAE_V2.3.safetensors, Denoising strength: 0.5, Clip skip: 2, Hires upscale: 2, Hires steps: 12, Hires upscaler: R-ESRGAN 4x+, Lora hashes: "cat girl-000018: 635f3c27969e", TI hashes: "EasyNegative: 66a7279a88dd, badhandsv5-neg: aa7651be154c", Version: v1.6.0-2-g4afaaf8a

For the large model, I recommend using my chosen irises (the first one in the recommended list below). For the VAE, you can use "clear," and other commonly used models like ghost will work fine as well. This model has good compatibility, so I recommend using a compatible anime-style large model.

Thank you for downloading and using it. If you like it, please feel free to follow me on Bilibili and Pixiv. My IDs are bothchosen鲷. You can also check out my channel on Bilibili: https://space.bilibili.com/3867754?spm_id_from=333.1007.0.0, and my Pixiv profile: https://www.pixiv.net/users/40911695. Thank you.

版本详情

SD 1.5

项目权限

严禁转载

    使用权限

  • 使用时无需注明出处

  • 用于模型融合

  • 分享融合模型时使用不同的许可

    商用许可

  • 生成的图片用于商业用途

  • 作为图片生成服务来商用

  • 转售模型或出售融合模型

评论

相关帖子

描述想生成的画面,回车发送