If you like the LoRA, please feel free to share your generated images here and leave a review (or at least a rating) for the sake of motivation and stuff ;D
For usage guidance, look into the About this version box for more information and click on Show more to get all trigger words and combinations (The trigger words in the Details box are a pain to manage).
Please contact me here on civitAi or on Twitter if you want to provide the LoRa in a generation service.
Originally, I wanted to make a LoRa of Honey Lemon in the actual Big Hero 5 movie, but she just didn't get enough screen time there, and the fact that she was wearing a helmet for half the movie didn't help at all.
So I used the animation series instead. I do not really like the art style, the clothes she is wearing here look like a sack of potatoes most of the time, and in general Honey Lemon does not really look like the character in the actual film.
But there was a lot of potential training data (and besides; it's completely 2D, so another challenge :D), so I was hooked. ^^
I stuck to the new normal (at least as far as animated stuff goes) and looked for good scenes of Honey Lemon in the whole series, I barely managed to get 50 pics together as she's quite underplayed.
Seriously, the rich guy got several episodes that mostly told his story. Honey Lemon only got one episode where she was the centre of attention.
But okay... that's one of the problems we have to live with when doing (western) animated stuff, changing clothes is not allowed.
Changelog
Noise offset set to zero
How to use the LoRa
Basic prompt, no weight adjustment required
Honey Lemon, glasses <lora:HoneyLemon_v2:1>1. Dieses Modell dient nur Lernzwecken. Urheber- und Auslegungsrechte liegen beim Originalautor.
2. Bist du der Originalautor eines Modells, kontaktiere uns bitte zur Authentifizierung über unsere offiziellen Kanäle. Wir schützen die Rechte aller Schöpfer. Hier klicken, um es zu verifizieren.
