Saegusa Akina/三枝明那 | hunyuan video

Details

Download Files

Model description

This lora depicts the character Saegusa Akina(三枝明那) from Nijisanji

Trigger Word:Saegusa Akina, anime-style boy. The image features an anime-style character with dark brown hair styled in a messy, slightly tousled manner. The character has a single streak of bright red hair on the right side of their face, which contrasts with the rest of their dark hair. Their eyes are a striking blue, adding to their expressive appearance.The character is wearing a white hoodie with a high collar,and gold accents on the shoulders, which is open at the front. The hoodie has a black choker around the neck and a small tag on the left side that reads "221B".The character is wearing a black jacket with gold accents, including a white collar and cuffs.The hoodie is paired with dark pants that have a relaxed fit, and they are also wearing white socks and black shoes.

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:Saegusa Akina, anime-style boy. The image features an anime-style character with dark brown hair styled in a messy, slightly tousled manner. The character has a single streak of bright red hair on the right side of their face, which contrasts with the rest of their dark hair. Their eyes are a striking blue, adding to their expressive appearance.The character is wearing a white hoodie with a high collar,and gold accents on the shoulders, which is open at the front. The hoodie has a black choker around the neck and a small tag on the left side that reads "221B".The character is wearing a black jacket with gold accents, including a white collar and cuffs.The hoodie is paired with dark pants that have a relaxed fit, and they are also wearing white socks and black shoes. (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.