
Well, here goes my another attempt at LoRA. This LoRA is based on older style of the artist Oono Tsutomu. He is known mostly for his hentai works.
I trained this LoRA on game CGs from games D'ark and D'ark Gaiden.
Attention!
0) Preferable weights 0.6 - 1.0 (depends on checkpoint and other LORAs used in generation)
1) No additional tags needed for using this LoRA. Just add and it's ready to go.
2) It displays artist style even with score tags.
3) As my testing shows, this LoRA works with every checkpoint. If you want to use this LoRA on other checkpoints, then you should adjust the weight of this LoRA (0.8 is good enough for most cases).
4) Yes, you can use it to generate hentai images on Civitai.
5) I advise you to use hires-fix or adding tag "blur" if the image is too grainy (well, the source pictures have very small resolution and using upscalers makes result even worse) AND adding tag for eye color.
描述:
First version
训练词语:
名称: 1162019_training_data.zip
大小 (KB): 9455
类型: Training Data
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success
名称: Oono-Tsutomu-Style.safetensors
大小 (KB): 223110
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success