Fuwa Minato/不破湊 | hunyuan video

Details

Download Files

Model description

This lora depicts the character Fuwa Minato(不破湊) from Nijisanji

Trigger Word :Fuwa Minato, anime-style boy. The image features an anime-style character with a unique hairstyle. The hair is predominantly white with streaks of purple and blue, styled in a messy, voluminous manner that falls over the shoulders. The character has striking purple eyes.The character's clothing consists of a dark-colored suit jacket with a high collar, layered over a matching shirt. They are wearing a dark purple suit with a matching shirt and a bow tie. The suit has gold buttons and a decorative pin on the lapel.

Trigger Word2:Fuwa Minato, anime-style boy. The image features an anime-style character with a unique hairstyle. The hair is predominantly white with streaks of purple and blue, styled in a messy, voluminous manner that falls over the shoulders. The character has striking purple eyes and is wearing a jacket with a mix of dark and light purple colors, along with some green accents. The jacket has multiple buttons and a white shirt underneath. The character is also wearing a necklace with a pendant.

Trained: musubi-tuner, 30 images

Caption: adjusted caption from Qwen2.5-VL-3B (includes described background)

lr:(2e-4,flow_shift7.0)

epoch:120

train_step:3600

lora_strength:0.8

sample prompt:Fuwa Minato, anime-style boy. The image features an anime-style character with a unique hairstyle. The hair is predominantly white with streaks of purple and blue, styled in a messy, voluminous manner that falls over the shoulders. The character has striking purple eyes.The character's clothing consists of a dark-colored suit jacket with a high collar, layered over a matching shirt. They are wearing a dark purple suit with a matching shirt and a bow tie. The suit has gold buttons and a decorative pin on the lapel. (she is dancing:2.5), (chibi Nendoroid:3.5) in bedroom.

アクションは強調promptによって2.0~4.0に調整する必要があります。またはモーションloraを併用ください。

Action prompt should be adjusted to 2.0 to 4.0 depending on emphasis prompt. Or motion lora use together.

Images made by this model

No Images Found.