
自分用に作ったLoRAの共有用です,
画質のよい絵を出す目的ではなく、アニメっぽい絵を再現することを目的としています,
promptは一番上が共通部分になっていて、下が服装毎になっています,
今回少々promptに追加が必要です(特に悪魔の方)
LoRAの学習はponyですが、サンプルの画像出力はHassakuです,
Pony Diffusion V6 XL:https://civitai.com/models/257749/
Hassaku XL (Hentai):https://civitai.com/models/376031/
This is a LoRA I made for myself.
The image quality is low because the purpose is to reproduce an anime-like image.
The top prompt shows the common part, and the bottom ones are for each outfit.
This time we need to add a few prompts (especially to the demons)
LoRA training is done with pony, but sample image output is done with Hassaku.
prompt
<lora:OgataKanna-XL-v1:0.7>,
(ogatakanna,black_hair,aqua_eyes,horns,wings,:1.0),(black_gloves,sleeveless_dress,frilled_blue_dress,high_heel_boots,black_boots,:1.0),(one wing,one horn:1.05),short hair,
[Negative prompt](both wing,both horn:1.05),
(ogatakanna,brown_hair,blue_eyes,:1.1),(pink_jacket,white_dress,:1.0),short hair,
描述:
训练词语: ,,(ogatakanna,black_hair,aqua_eyes,horns,wings,:1.0),(black_gloves,sleeveless_dress,frilled_blue_dress,high_heel_boots,black_boots,:1.0),,(ogatakanna,brown_hair,blue_eyes,:1.1),(pink_jacket,white_dress,:1.0),
名称: OgataKanna-XL-v1.safetensors
大小 (KB): 223102
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success