To the original prompter:
对不起了, drunkard大佬. 你的画风真的是非常好非常好有感觉. 只是说只用来做hi3有点可惜. 所以拿了你的画风, 这样就可以冲其他的角色了.
如果你不想要, 可以dm我拿下.
Credit to the original prompter: drunkard (https://www.pixiv.net/en/users/78771327) (https://discord.com/invite/dVcQh7FM)
Trained on Pixai using 100 images from drunkard.
This lora is trained without permission (basically every lora ever ¯_(ツ)_/¯), so I might delete it if asked too. Until then…
Weight: 1.0-1.3 or 0.7-1.0. Either Euler or Euler a works fine.
Update Tested using following models: (low steps because cheaper token cost to test result)
Best- VXP_ASC vPred (Anime ScreenCap) - 8 steps, CFG 4
Decent- WAI-illustrious-SDXL v17 & v15 - 10 steps, CFG 5
Not really, hard to follow prompt- Illustrious XL personal merge (noob v-pred0.5 test merge updated) CFG 1.1
Or
any other better checkpoints or control settings of your preferences.
My go-to checkpoints for everything:
1st - VXP_ASC vPred (Anime ScreenCap) [only on Pixai]
1st - VXP IL Base Model (NSFW alert!)
3rd- WAI-illustrious-SDXL v15
Enjoy!
