盲盒3D推理 all-round-chibi

更新日誌：
V3: 輸入一張單個明確主體的圖像，即可給出該主體旋轉不同方位後的圖像（九宮格圖*1張）
[v2: 輸入一張單個明確主體的圖像（工作流自動扣除背景），不需其他參數，即可給出該主體旋轉不同方位後的圖像（*6張）
V1: 輸入一張單個明確主體的簡單背景圖像，和仰角/方位角（0.1±180.0），即可給出該主體旋轉指定方位後的圖像（1張）
更新日誌:
V3: Input an image of a single clear subject, and you can get the image of the subject after rotating to different positions (九宮格圖 * 1 picture)
[v2: Input an image of a single clear subject (the workflow automatically deducts the background), and you can get the image of the subject after rotating to different positions without other parameters (*6 pictures)
V1: Input a simple background image of a single clear subject, 和仰角/方位角 (0.1±180.0), and you can get the image of the subject after rotating to a specified position (1 picture)