









You should use the trigger word HKMagic
This LoRA works very well in adding details to images!
Most of the images in dataset has a book in one hand so try to prompt spellbook in one hand.
The LoRA weight I have been using is 0.85, but feel free to try and experiment!
I have used ComfyUI when generated pictures and the settings im using are:
Sampler: dpmpp_3m_sde
Scheduler: Karras
Steps: 40
cfg: 3.6
Example prompts used:
"A beautiful fairy with glowing wings reads an ancient book of magic and spells. She has detailed facial features and there is a glowing green light in the background with cinematic lighting, fairycore, hkmagic"
First image is with my LoRA and second is without my LoRA, same prompt and model.
Recomended vae that I use is the official sdxl_vae
The LoRA weight I have been using is 0.85 - 1, but feel free to try and experiment!
Steps: 40
cfg: 3.6
Example prompts used version 2:
"An evil necromancer witch casting colorful magic from her skeleton wand, purple black necrotic green, necrotic dark green armour made of bones and skulls, magical particles in the air, rusty skull armour, casting screaming tranparent skulls, face covered in glowing skull mask, hkmagic"
First image is with my LoRA and second is without my LoRA, same prompt and model.
1. 转载模型仅供学习与交流分享,其版权及最终解释权归原作者。
2. 模型原作者如需认领模型,请通过官方渠道联系海艺AI工作人员进行认证。我们致力于保护每一位创作者的权益。 点击去认领
