Tipo
LORA
Data di pubblicazione
2024-09-24
Modello Base
Flux.1 D
Parola Chiave
Copia
Model Parameters
Parametri di Allenamento
Epochs：1
Steps：0
Introduzione alla versione
Fantasy Wizard & Witches
Hello friends!
Flux version 2 is now out with more magical images!!
This model works good with my other fantasy model FS Anime Fantasy Aesthetics | Flux (https://civitai.com/models/716364?modelVersionId=801100)
Things To know:
- 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.
XL Usage Tips :
- 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_sdeScheduler: KarrasSteps: 40cfg: 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
Flux Usage Tips:
- The LoRA weight I have been using is 0.85 - 1, but feel free to try and experiment!
- Steps: 40cfg: 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.