Tensor.Art
Create

原神 | 雷电将军 Raiden Shogun -Genshin Impact

LORA
Original


Updated:

1

MORA:(Pony)All characters Genshin Impact ( 124 characters) 原神全角色 124 位 - v2.0 | Stable Diffusion LoRA | Civitai

pony:

TAG:raiden_shogun_ckxl

Please note that this model's content includes some covers that have been rated as PG-13/R/X

Please choose the appropriate age rating based on your needs.

Training model: Pony

Recommend model: Pony Diffusion V6 XL/T-ponynai3/AutismMix SDXL

Training resolution: 1024*1024

Recommended output resolution: 1024*1280

Discord : https://discord.com/invite/CFpyHceF52

Recommended dataset collection and processing tools: https://github.com/deepghs/waifuc

Possibly the most user-friendly dataset processing UI currently in use: https://github.com/Eugeoter/sd-dataset-

2.0版本:

使用了400张单人图片进行了训练,优化了服装和画面细节,更小的体积

触发词:1girl,raiden_shogun,kimono,obi,solo,mole,hair_ornament,armor,ribbon,shoulder_armor,breasts,

2.0 Version:

Trained using 400 individual images, optimizing clothing and visual details, with a smaller file size.

Trigger words: 1girl, raiden_shogun, kimono, obi, solo, mole, hair_ornament, armor, ribbon, shoulder_armor, breasts.

1,5版本:

32dim版本的最后一个模型,从后面起,原神系列不会出现dim32的lora了,因为8dim的lora效果更好,体积更小。

这个版本是在1.33版本上面的优化,使得手部和四肢的问题得到改善,继承了1.33版本的换装自由,遗憾的是,眼睛的问题依旧没有得到改善。

请注意!模型的权重不要拉太高,0.6~0.8这样最好。

Version 1.5:

The last model of the 32-dimensional version. Starting from this point, there won't be any more 32-dimensional Lora models for the Genshin Impact series. The 8-dimensional Lora model performs better and has a smaller size.

This version is an optimization based on version 1.33, addressing issues with the hands and limbs. It inherits the outfit swapping feature from version 1.33. Unfortunately, the issue with the eyes has not been improved

Please note that it's best not to set the model weights too high, around 0.6 to 0.8.

1.33版本

在这一版本中,雷电将军lora可以实现更加自由的换装:泳衣、职业制服、旗袍、运动服、内衣等等。但是遗憾的是,因为在训练集中混进了较多的手部特写,因此在生成图片的时候需要额外注意手的形状。

In version 1.3:

Raiden Shogun can have more freedom in changing outfits, such as swimsuits, professional uniforms, cheongsams, sportswear, underwear, and so on. However, unfortunately, due to the inclusion of a significant number of close-ups of hands in the training set, extra attention is required when generating images to ensure the shape of the hands.

1.0版本

雷电将军的XL版lora

触发词:leishen,raiden shogun,purple eyes, purple hair

建议权重0.8左右

推荐的大模型

MK系列:https://civitai.com/models/125721/finalyuananimeandcg

琥珀青叶的二次元模型:https://civitai.com/models/136389/kohaku-xl

Version Detail

SDXL 1.0
<p>This version allows for more free reloading</p>

Project Permissions

    Use Permissions

  • Use in TENSOR Online

  • As a online training base model on TENSOR

  • Use without crediting me

  • Share merges of this model

  • Use different permissions on merges

    Commercial Use

  • Sell generated images

  • Use on generation services

  • Sell this model or merges

Comments

Related Posts

No posts yet
Describe the image you want to generate, then press Enter to send.