
This model is trained on around 80 final fantasy character art pics. (Think Booklet Art from Tactics on PS1).
Best outputs are 512x768 and 768x768 although at 768 and higher, your chance of getting multiple subjects (people/characters) goes up greatly. if you want single character only then 512: x640 and x768 are best. actually worked really well on 1600x400 too.
Example Prompt:
final fantasy character concept <lora:finfan:0.75> finfan, blue and pink thief rogue, high quality, crisp lines, fine detail
**final fantasy character concept isnt needed but it can help a bit if youre having issues**
Example Negative:
ugly, low quality, blurry, pixelated, holding weapon
If you would like to support my efforts, please consider checking out my other content:
Https://linktr.ee/pookienumnums
描述:
训练词语: finfan
名称: finfan.safetensors
大小 (KB): 36976
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success