Hayama Marin/葉山舞鈴 | hunyuan video
LORA
Hunyuan Video
LORA
Hunyuan Video
v1.0

Hayama Marin/葉山舞鈴 | hunyuan video

kihh
Creator
⭐ 0.0
⬇ 72 Downloads
👁 1 Views
🖼 7 Images

Trained Words

Hayama Marin
anime-style girl. The image features an anime-style character with light-colored hair styled in a messy bun with a small green leaf accessory. The character has large
expressive eyes that are pinkish-red. They are wearing a pastel-colored outfit consisting of a white hoodie with a pink zipper and a light blue jacket over it. The hoodie has a fluffy collar and is paired with a white skirt. The hoodie is paired with brown suspenders that have gold buckles.

About this model

This lora depicts the character Hayama Marin(葉山舞鈴) from Nijisanji

Trigger Word:Hayama Marin, anime-style girl. The image features an anime-style character with light-colored hair styled in a messy bun with a small green leaf accessory. The character has large, expressive eyes that are pinkish-red. They are wearing a pastel-colored outfit consisting of a white hoodie with a pink zipper and a light blue jacket over it. The hoodie has a fluffy collar and is paired with a white skirt. The hoodie is paired with brown suspenders that have gold buckles.

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:Hayama Marin, anime-style girl. The image features an anime-style character with light-colored hair styled in a messy bun with a small green leaf accessory. The character has large, expressive eyes that are pinkish-red. They are wearing a pastel-colored outfit consisting of a white hoodie with a pink zipper and a light blue jacket over it. The hoodie has a fluffy collar and is paired with a white skirt. The hoodie is paired with brown suspenders that have gold buckles. (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.

Related Models

Similar AI models you may like