This is trained with 71 images (768x768) at 30 steps and 15 epoch. For better results, try using more specific prompts like silver_hair and yellow_neckwear.









This LoRAs are to be used with their original danbooru tag which is elaina_(majo_no_tabitabi) or elaina_\(majo_no_tabitabi\). Also can be used with other LORA. You need to describe how you want her, as the lora is not overfitted as sometimes it will generate images with different outfits and hair color. If the image is weird, try lowering the weight.
Version 2 is out which I personally prefer more. Feel me to credit me and leave feedbacks on what I can improve on!
This is trained with 71 images (768x768) at 30 steps and 15 epoch. For better results, try using more specific prompts like silver_hair and yellow_neckwear.
1. The rights to reposted models belong to original creators.
2. Original creators should contact SeaArt.AI staff through official channels to claim their models. We are committed to protecting every creator's rights. Click to Claim
