this model was trained on 14000 captioned images, it can pretty much do anything.
to get the Yu-Gi-Oh! style it's best to prompt these keywords into your prompt
glowing, yugioh style, yugioh monster, duel monsteryou can also use these to enhance the style even more
level: 9 (change to a number u want)
Attribute: Aqua/Beast/Beast-Warrior/Cyberse/Dinosaur/Divine-Beast/Dragon/Fairy/Fiend/Fish/Insect/Machine/Plant/Psychic/
Pyro/Reptile/Rock/Sea Serpent/Spellcaster/Thunder/Warrior/Winged Beast/Wyrm/Zombie
Type: Dark/Divine/Earth/Fire/Light/Water/Wind
Attack: 2600 (change to a number u want)
Defense: 1900 (change to a number u want)
outline, digimon, pokemon, sparkleDescription
FAQ
Comments (17)
This is amazing! Thank you for making such a great LoRA, and please make more yu-gi-oh related LoRAs.
I have a little problem, I've used the same generation data and checkpoints as you but the results are always blurry
try highres fix
@nicolai256 oke, i will try it. Thanks
Great Lora man, but I'm having trouble creating vehicle duel monsters and the magician cards I'm making are missing their scepters. Any tips, please?
best is probably using a vehicle lora in combination https://civitai.com/?tag=vehicle
and for extra weapons this could work https://civitai.com/models/69323/unlimited-blade-works-ubw-or-weapon-loha-official-release-axe-bows-dualwielding-fan-katana-knife-kunai-lightsaber-mastersword-planted-swords-scythe-sheathed-shield-spear-staff-tomahawk-trident-unsheathing-warhammer-whip
@nicolai256 I'll give them a try, Thanks.
I can't run SD locally, so im using mage.space. Could we please get permission to request your lora to their devs? 🙏 Been really wanting to try this and experiment with it for a long time.
Amazing! It seems that many values can be use, such as atk, def and etc. How could you generate captions for such pictures?
this had to be done ! thanks. i bet konami is gonna use something like this pretty soon btw
but still have respect for the OG Artist.. R.I.P. Kazuki Takahashi
as far you you are concerned, am i able to use this in my video game ?
any chance you can make your source dataset available? would love to see this trained for sdxl and have the ability to refine captioning.
https://civitai.com/models/130658/yu-gi-oh-card-art-sdxl I released an SDXL model a couple months ago
Can you try to made them in Pony or Illustrious versions?
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.