LoRA for Lisa Simpson from the Death Note Parody Episode
I trained this LoRA with 60 pics, which 53 were screenshots and 7 fan art. I trained it at 9 epochs with a dim/alpha of 16/8.
Please play around with the LoRA weights. Let me know how it goes for you. Read stuff below on guidelines and known issues :)
Triggers:
The global activation tag is "LisaNote, 1girl"
To get her typical outfit: you may want to add, "red dress, jacket, skirt". Though I found it totally unnecessary as the lora really likes to generate her clothes. "skirt" is helpful though because it make sure her dress is shorter.
NB: can place clothes in negative prompts if the clothes are stubbornly appearing and you don't want them.
Crucial Tips:
I recommend using " (anime coloring, blurry :1.4) " in the negatives if you don't want it to look like it's an anime screencap.
If you're struggling to make her use a different outfit other than the default then lower the LoRA weight to around 0.7 or even less
Notes:
My experience has shown scale 0.7 ~ 1.4 works best; my best results were 0.8.
My prompt order shown in the sample pictures worked best for me.
Works on different models though weights may need to change for good results.
I used mainly the AnyLoRA_Default, anyLoRA_Anime_Mix and Midnight Maple model.
Refer to my pictures for examples and what upscaler I used, keep in mind I have used other textual inversions to help with poses and negatives.