
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.
About
Hilda (the show, not the character) is quite interesting, I watched the first season years ago and forgot about it. Last week I binge-watched the 2nd season and got hooked. The whole thing is a nice mix of Nordic mythology and modern elements. The music is also great. One character I really liked is Kaisa, even though she was cooler in the first season, its kida nice how she warmed up in the second :D So I did what I always do when I like a show or a character, I created a LoRA. Maybe I will make another LoRA for Woodman and Hilda's mum (but for both of them I have to watch the first seasons again!)
Training
I used 50 images for training, 70% in her cape outfit and about 30% in the boiler suit outfit (still not sure if that's the right tag, I would call it overalls but every SD model I use uses that tag for dungarees.
描述:
How to use the LoRa
Basic prompt, no weight adjustment required
kaisa, sleeveless sweater, long sleeved shirt, cape, nametag, skirt, pantyhose, black shoes <lora:kaisa_v1:1>
训练词语: kaisa
名称: kaisa_v1.safetensors
大小 (KB): 147570
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success