Weight : 0.6～0.7?
The model for the illustration for the sample is based on 7th_anime_v3_A and has been merged several times, including AOM3.
7th_anime_v3_A will be a close illustration.
Please use it in an environment where LoCon is available.
ACertainThing.ckpt is used as the model for the study.
Description
FAQ
Comments (3)
Dear Author
It seems that the recommended Weight 0.6-0.7 is not the only one, and it seems that we can look at it up to about 1. Difficult.
Also, the supply of old ANIME ROLAs, including the other Lime LORA, is very small, so I think it is a so-called "blue ocean".
I would like to see more of this kind of work in the future, but I think it is possible that civitai users will not respond to it.
I hope you will not be discouraged and keep up the good work.
Thank you very much.
The optimal weight strength may vary depending on the model you are using.
I will continue to create LoRA for characters that interest me in the future. However, gathering training images for nostalgic characters is proving to be quite challenging...
okay.. after i found two useful and extreme powerful prompts, i got this model running without any problems. these prompts are
(official style, style parody) ...
set them after quality prompts and then load this model and set the trigger. works right from the start without any negative generated things in images.