Wan LoRA Arcane Jinx V1

🚀 Wan-LoRA-Arcane-Jinx-v1

本項目是一個文本到圖像/視頻的LoRA模型，基於Wan-AI/Wan2.1-T2V-1.3B基礎模型訓練，可根據輸入的文本描述生成特定風格的圖像或視頻。

🚀 快速開始

模型信息

示例展示

• 輸入文本：'csetiarcane A medium shot frames a J1nx in neon-washed leather, her silhouette sharp against flickering signs. Her long blue hair catches blue light as she moves sideways through the frame. Her mesh top gleams beneath a studded jacket. Behind her, steam rises from street vents into the rainy night.'
  • 輸出視頻：點擊查看
• 輸入文本：'csetiarcane Nfj1nx stands at the edge of a candlelit rooftop terrace overlooking glittering city towers. The camera faces her from the front, capturing every detail of her gentle smile as she meets the gaze of her partner—dressed in a sleek black blazer, collar slightly undone, and he has sporting jet-black hair that frames his face. Soft string lights sway overhead, highlighting her long blue hair and the warm reflection in her eyes. She takes a small step forward, and he carefully places one hand on her cheek before leaning in for a tender kiss, their silhouettes merging at the center of the frame.'
  • 輸出視頻：點擊查看
• 輸入文本：'csetiarcane Nfj1nx moves along a tree-shaded park path, coming directly toward the camera. A matte-black pair of over-ear headphones partially covers her ears, letting most of her bright blue hair remain visible. She wears a simple white athletic hoodie paired with black biker shorts. Pastel-toned running shoes quietly crunch on the gravel, reflecting her relaxed yet confident rhythm.'
  • 輸出視頻：點擊查看
• 輸入文本：'csetiarcane Nfj1nx moves along a tree-shaded park path, coming directly toward the camera. A matte-black pair of over-ear headphones partially covers her ears, letting most of her bright blue hair remain visible. She wears a simple white athletic hoodie paired with black biker shorts. Pastel-toned running shoes quietly crunch on the gravel, reflecting her relaxed yet confident rhythm.'
  • 輸出視頻：點擊查看

✨ 主要特性

• 本模型採用先在圖像上訓練LoRA，再在視頻上繼續訓練的方法。
• 模型偏好長描述性提示詞，使用短提示詞時LoRA效果較弱。

🔧 技術細節

訓練參數

• 學習率（LR）：2e-5
• 優化器：adamw_optimi
• 訓練輪數（epochs）：圖像訓練15輪 + 視頻訓練7輪
• 訓練步數（steps）：圖像訓練2550步 + 視頻訓練2520步
• 數據集：33張圖像和35個視頻
• 重複次數：10
• 秩（rank）：128
• 批量大小（batch size）：2
• 梯度累積步數：1

訓練代碼倉庫

訓練使用了 Diffusion-Pipe 倉庫。

💻 使用示例

推理工具推薦

• ComfyUI原生節點
• Kijai的ComfyUI包裝節點

提示詞建議

• 觸發詞：csetiarcane, Nfj1nx, 藍色頭髮
• 強度：0.9 - 1.0
• 如果僅使用觸發詞無法得到所需風格或角色，建議在提示詞中添加 "animation style"，但可能會使結果過於卡通化。

📄 許可證

本LoRA是作為粉絲項目的一部分創建的，僅用於研究目的，不用於商業用途。它基於受版權保護的電視劇《Arcane》。用戶自行承擔使用該模型的風險，有義務遵守版權法和適用法規。該模型是為非商業目的開發的，無意侵犯任何版權。對於因使用該模型而產生的任何損害或法律後果，本人不承擔任何責任。

👏 致謝

特別感謝 Kijai 為社區所做的不懈努力和出色工作，使我們能夠儘快使用這些解決方案；也感謝 Comfyanonymous 如此迅速且高質量地將其原生集成到ComfyUI中；還要感謝 TDRussel 如此迅速地讓社區能夠進行LoRA訓練。