
Well, here goes my second attempt at LoRA. This LoRA is based on style of the game Armist for PC98, its artist was Mon-Mon.
Attention!
0) Preferable weights 0.6 - 1.2 (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) If you want images to look like that VN style, then you can use score tags in positive and negatives. But it heavily depends on Checkpoint. About that...
3) I checked this lora with different checkpoints. The best results come out with duchaitenPonyXL and tPonynai3 and Autismix. And original PonyXL. As my testing shows, if you want to use this LoRA on other checkpoints, then you should adjust the weight of this LoRA.
4) Yes, you can use it to generate hentai images on Civitai.
5) If there is something wrong with faces, then, please, use Adetailer or Facefix.
描述:
First version.
训练词语:
名称: 1010319_training_data.zip
大小 (KB): 669
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: Armist_Mon-Mon.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