AI

建议搭配脸部的lora模型使用，素材来自某宝店铺 使用chilloutmix 模型权重大约0.8 使用动漫模型时，权重大约0.5 It is recommended to use with the L

2.0 updated 用了192张图片训练,使用了更好的采样方式,更多的衣服款式 更好的训练质量,祝你玩的愉快 示例图像由 pastellines-mix 生成 Use 192 pictures f

Demon Slayer / Kimetsu No Yaiba anime style LoRA Making models can be expensive. Do you like what I

当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。 您可以通过如下git clone命令，或者ModelScope SDK来下载模型 SDK下载 #安装ModelS

A LoRa model trained with dropout & block weights. This is a LoRa model that trained by 100+ img gen

works quite well between 0.4 and 0.8 Other Trigger Words - Holding fire with her 2 hands - Firebal

[I have a form for requests now; check it out if you want to request a character.](https://docs.goog

Trained on 593pics for 2epochs, 4000steps. atago for her face, origin for original skin, summermarch

for that late 80's early 90's anime aesthetic Trained on Satoshi Urushihara artwork and OVA stills

Mouth Hold Clothes Lift (Concept LoRA) Made this concept lora to help fix clothes lift with mouth. S

V1.0 Weight = 0.8 Works best and adheres to the prompt. V2.0 Weight = 0.4 Works best and adheres to

SSS: you can try superrobotjoints ============= Thanks to the original author 搞事德·乔斯达's wonderful th

Shingeki no Kyojin (Attack on Titan) Anime style LoRA (season 1) Making models can be expensive. Do

This is a LoCon model trained from 87 images about flatcolor small town background,the bright colors

weight 0.7~0.8 is best. I created this LoRA as requested. Randomly, the shirt colors of outfit 1 a

Tsunade (Naruto) LoRA Making models can be expensive. Do you like what I do? feel free tobuy me a co

Recommended settings: Make sure you are aware on the usage instructions of LORA VAE: vae-ft-mse-840

Trigger word: yuzuriha_inori You can change her clothes more easily without the trigger word. 不加触发词的

1girl, solo, thighhighs, paimon (genshin impact), long sleeves, white dress, dress, halo, thighhighs

Some of these images have been processed using dynamic thresholding, which means that the CFG scale