詳細
おすすめ
Wan2.2 T2V 14B
v1.0
Kanae/叶 | Wan2.1 & 2.2 14B T2V

Kanae/叶 | Wan2.1 & 2.2 14B T2V

0
1
3
#アニメ
#concept
#Vtuber
#nijisanji

-------------------------

Wan2.2:

Trigger Word:Kanae, anime-style boy. The image features a person with light brown hair styled in a side ponytail. The individual has blue eyes and is wearing a dark-colored outfit consisting of a high-neck sweater over a black coat.The character is also wearing black pants. The character is also holding a plush toy resembling a black cat with yellow eyes and pink paws,

lr:(3e-4,flow_shift7.0,timestep_boundary 885)

epoch:140

train_step:4200

lora_strength:0.8

sample prompt:Kanae, anime-style boy. The image features a person with light brown hair styled in a side ponytail. The individual has blue eyes and is wearing a dark-colored outfit consisting of a high-neck sweater over a black coat.The character is also wearing black pants. The character is also holding a plush toy resembling a black cat with yellow eyes and pink paws, (she is dancing:4.0), (chibi Nendoroid:4.5) in bedroom.

アクションは強調promptによって3.0~5.0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。

lightx2v Wan2.2 v1.1との併用を推奨します。

Action prompt should be adjusted to 3.0 to 5.0 depending on emphasis prompt. Or motion lora use together.

It is recommended to use with lightx2v Wan2.2 v1.1 lora.

-------------------------

Wan2.1:

This lora depicts the character Kanae(叶) from Nijisanji

Trigger Word:Kanae, anime-style boy. The image features a person with light brown hair styled in a side ponytail. The individual has blue eyes and is wearing a dark-colored outfit consisting of a high-neck sweater over a black coat. The character is also holding a plush toy resembling a black cat with yellow eyes and pink paws

Trained: musubi-tuner, 30 images

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

lr:(2e-4,flow_shift3.0)

epoch:200

train_step:6000

lora_strength:0.8

sample prompt:Kanae, anime-style boy. The image features a person with light brown hair styled in a side ponytail. The individual has blue eyes and is wearing a dark-colored outfit consisting of a high-neck sweater over a black coat. The character is also holding a plush toy resembling a black cat with yellow eyes and pink paws (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.

翻訳を表示

評価とレビュー

-- /5
0 件の評価

まだ十分な評価やレビューが集まっていません

no-data
データなし
avatar
kihh
2
161
モデルと会話する
お知らせ
2025-04-29
モデルを公開
2025-08-24
モデル情報を更新
モデル詳細
タイプ
LORA
投稿日時
2025-08-24
基本モデル
Wan Video 2.2 T2V-A14B
トリガーワード
Kanae, anime-style boy. The image features a person with light brown hair styled in a side ponytail. The individual has blue eyes and is wearing a dark-colored outfit consisting of a high-neck sweater over a black coat.The character is also wearing black pants. The character is also holding a plush toy resembling a black cat with yellow eyes and pink paws,
コピー
バージョン紹介

-------------------------

Wan2.2:

Trigger Word:Kanae, anime-style boy. The image features a person with light brown hair styled in a side ponytail. The individual has blue eyes and is wearing a dark-colored outfit consisting of a high-neck sweater over a black coat.The character is also wearing black pants. The character is also holding a plush toy resembling a black cat with yellow eyes and pink paws,

lr:(3e-4,flow_shift7.0,timestep_boundary 885)

epoch:140

train_step:4200

lora_strength:0.8

sample prompt:Kanae, anime-style boy. The image features a person with light brown hair styled in a side ponytail. The individual has blue eyes and is wearing a dark-colored outfit consisting of a high-neck sweater over a black coat.The character is also wearing black pants. The character is also holding a plush toy resembling a black cat with yellow eyes and pink paws, (she is dancing:4.0), (chibi Nendoroid:4.5) in bedroom.

アクションは強調promptによって3.0~5.0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。

lightx2v Wan2.2 v1.1との併用を推奨します。

Action prompt should be adjusted to 3.0 to 5.0 depending on emphasis prompt. Or motion lora use together.

It is recommended to use with lightx2v Wan2.2 v1.1 lora.

許可範囲
モデルソース: civitai

1.転載モデルは学習・共有目的のみで使用し、著作権は原作者に帰属します

2.モデルの認証は公式チャンネルでご連絡ください。クリエイターの権利保護に努めています クリックして認証

創作許可範囲
オンライン画像生成
統合
ダウンロード
商用利用の許可範囲
生成された画像は販売または商業目的での使用
モデルの転売やモデル統合後の販売
QR Code
SeaArt Appをダウンロード
モバイルでAI創作の旅を続けよう