Naraka/奈羅花 | hunyuan video

详情

下载文件 (1)

模型描述

This lora depicts the character Naraka(奈羅花) from Nijisanji

Trigger Word:Naraka, anime-style girl. The image features an anime-style character with long, white hair that flows down to the shoulders. The hair is styled in a loose, flowing manner, giving it a soft and ethereal appearance. The character has red eyes, which stand out prominently against their pale skin. They have pointed ears and two small, purple horns on either side of the head. The character is wearing a traditional-looking outfit with a deep red color. The upper part of the outfit includes a high collar with intricate gold embroidery on the chest area. The sleeves are long and flowy, adding to the character's graceful and elegant appearance. The character is also wearing a headpiece that resembles a fox mask, complete with pointed ears and a small tail, suggesting a connection to a mythical or fantasy theme

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:Naraka, anime-style girl. The image features an anime-style character with long, white hair that flows down to the shoulders. The hair is styled in a loose, flowing manner, giving it a soft and ethereal appearance. The character has red eyes, which stand out prominently against their pale skin. They have pointed ears and two small, purple horns on either side of the head. The character is wearing a traditional-looking outfit with a deep red color. The upper part of the outfit includes a high collar with intricate gold embroidery on the chest area. The sleeves are long and flowy, adding to the character's graceful and elegant appearance. The character is also wearing a headpiece that resembles a fox mask, complete with pointed ears and a small tail, suggesting a connection to a mythical or fantasy theme. (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.

此模型生成的图像