All the content I make is and will be completely free on CivitAI.
But if you want to support me with a coin, then you can do it here.
Trained on AbyssOrangeMix2 with clip skip 2.
Recommended embeddings:
1. easynegative
2. bad-hands-5
Strength 0.6-0.8 is optimal.
PLEASE CHECK YOUR LORA NAME AFTER DOWNLOAD.
You may add white jacket, corset, skirt, pants, colored hair, braids, makeup, choker in positive prompt if you want Classic outfit.
Or you can add same tags to the negative prompt for any other outfit you want.
Also you may improve it with prompt: athletic, (wide hips, thick thighs:0.7)
Negative prompt: loli, kid, child, old
Enjoy and share your feedback.
Description
FAQ
Comments (6)
how did you manage to achieve such flawless eyes?when I created a loba lora, my model was unable to produce such eyes. any suggestions, kindly
no idea, honestly. Probably it may be because i have some realistic close-up shots in my dataset, so it helps lora to remeber eyes and face more properly.
@sadxzero Do you think that using 20 to 35 photos and 1800 steps for each model is appropriate?
@Gogeta depends of your images. I'm usually using up to 20 for character with 100 steps per image, but i'm trying to collect high quality images only, and often overpaint or edit them in Photoshop. So i guess there is a quality over quantity.
Wattson please :)
Hi, I don't get loba, but a girl dressed as a bride and I don't know why
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.