1.1 - I updated the Lora with cropped photos to exclude extra people as well as trying to add more fan art/cosplays to give some more variety for stylization. The eyes are still not 100% but it's better than the original.
This is my first Lora ever, so if there is anything I can improve somehow, please let me know!
Weight: Suggested: 0.5-0.8
Trigger + Appearance: Benimaru
Sample Outfit: Japanese clothes, black shirt, kimono
Add black hair and red eyes if necessary.
Other trigger words that help: 1male, symbol-shaped pupils, solo, solo focus, male focus, glowing eyes, (this is for specifically for his pyrokinetic ability/fighting scenes), hair in front of face, looking at viewer, clothes around waist, holding weapon, (mop specifically), (right eye "o"), (left eye "x"), white colored pupils, yukata, Benimaru from Fire Force, dynamic pose.
I did use ADetailer on every picture as well as 4k-UltraSharp UpScaler.
The results of your generations are dependent on the additional LoRAs, weights, and models you use, so it may not work or come out as consistent as my sample images.
1.1 - I updated the Lora with cropped photos to exclude extra people as well as trying to add more fan art/cosplays to give some more variety for stylization. The eyes are still not 100% but it's better than the original.
This is my first Lora ever, so if there is anything I can improve somehow, please let me know!
Weight: Suggested: 0.5-0.8
Trigger + Appearance: Benimaru
Sample Outfit: Japanese clothes, black shirt, kimono
Add black hair and red eyes if necessary.
Other trigger words that help: 1male, symbol-shaped pupils, solo, solo focus, male focus, glowing eyes, (this is for specifically for his pyrokinetic ability/fighting scenes), hair in front of face, looking at viewer, clothes around waist, holding weapon, (mop specifically), (right eye "o"), (left eye "x"), white colored pupils, yukata, Benimaru from Fire Force, dynamic pose.
I did use ADetailer on every picture as well as 4k-UltraSharp UpScaler.
The results of your generations are dependent on the additional LoRAs, weights, and models you use, so it may not work or come out as consistent as my sample images.