V 4.0.2（2025.09.23）

1. 新增原创导入提示词
2. 新增 MJ Video 批量设置基础设置
3. 新增原创设置通用前缀和通用后缀
4. 添加可灵的图转视频和视频延长

OBFUSCATION_README.md

@@ -0,0 +1,153 @@
+# Renderer 代码混淆配置说明
+
+## ⚠️ 白屏问题解决方案
+
+如果使用 `npm run build:win:obfuscated` 出现白屏，这是因为之前的混淆配置过于激进。现在已修复并提供更安全的配置。
+
+### 🛠️ 已修复的问题
+- **移除所有unsafe选项**: 避免破坏Vue响应式系统
+- **保留函数名和类名**: 确保Vue组件正常工作
+- **关闭属性名混淆**: 防止破坏Vue的内部机制
+- **保留更多关键标识符**: 包括Vue、Pinia、Naive UI相关的所有重要名称
+
+## 🎯 推荐使用方案
+
+### 安全混淆构建 (推荐)
+```bash
+npm run build:win:safe
+```
+这个命令使用新的安全混淆配置，提供基础保护的同时确保应用正常运行。
+
+### 普通构建 (无混淆)
+```bash
+npm run build:win
+```
+如果不需要混淆，使用普通构建即可。
+
+## 混淆功能特性
+
+### 安全混淆级别 (OBFUSCATE=true)
+- ✅ **变量名混淆**: 将局部变量名转换为短字符
+- ✅ **代码压缩**: 移除空格、换行、注释  
+- ✅ **Console移除**: 移除console.log等调试输出
+- ✅ **文件名混淆**: 生成短哈希文件名
+- ✅ **保留Vue生态**: 完全兼容Vue、Naive UI、Pinia
+- ❌ 属性名混淆: 已禁用，避免破坏响应式
+- ❌ Unsafe优化: 已禁用，确保稳定性
+
+## 构建命令对比
+
+| 命令 | 混淆级别 | 安全性 | 兼容性 | 推荐场景 |
+|------|----------|--------|--------|----------|
+| `npm run build:win` | 无 | 低 | 100% | 开发测试 |
+| `npm run build:win:safe` | 安全混淆 | 中等 | 99% | **生产推荐** |
+
+## 验证构建结果
+
+### 1. 检查应用启动
+```bash
+npm run build:unpack:safe
+npm start
+```
+
+### 2. 检查混淆效果
+查看 `out/renderer/assets/*.js` 文件：
+- 变量名应该是 a, b, c 等短字符
+- 代码应该压缩在少数几行
+- 不应有console.log输出
+
+### 3. 功能测试
+- 所有页面正常显示
+- Vue组件响应式正常
+- Naive UI组件正常工作
+- Electron API正常调用
+
+## 安全保护措施
+
+### 保留的重要标识符
+```javascript
+// Vue 核心
+'Vue', 'vue', 'reactive', 'ref', 'computed', 'watch'
+
+// Vue Router
+'router', 'route', 'useRouter', 'useRoute'
+
+// Pinia
+'pinia', 'store', 'useStore', 'defineStore'
+
+// Naive UI
+'naive', 'NaiveUi', 'useDialog', 'useMessage'
+
+// Electron
+'ElectronAPI', 'ipcRenderer', 'contextBridge'
+```
+
+### 禁用的危险选项
+```javascript
+// 这些选项会破坏Vue，已全部禁用
+unsafe: false,
+unsafe_comps: false,
+unsafe_Function: false,
+unsafe_methods: false,
+properties: false  // 属性名混淆
+```
+
+## 故障排除
+
+### 如果仍然白屏
+1. **使用普通构建**:
+   ```bash
+   npm run build:win
+   ```
+
+2. **检查控制台错误**:
+   打开开发者工具查看具体错误信息
+
+3. **分步测试**:
+   ```bash
+   npm run build:unpack:safe  # 先构建不打包
+   npm start                   # 测试是否正常
+   ```
+
+### 如果某些功能异常
+1. **检查是否有动态属性访问**:
+   如 `obj[dynamicKey]` 可能需要特殊处理
+
+2. **添加保留名称**:
+   在 `reserved` 数组中添加相关标识符
+
+3. **临时禁用混淆**:
+   ```bash
+   npm run build:win  # 使用普通构建
+   ```
+
+## 技术细节
+
+### 混淆配置要点
+```javascript
+terserOptions: {
+  compress: {
+    drop_console: true,     // 移除console
+    keep_fargs: true,       // 保留函数参数（Vue需要）
+    keep_classnames: true,  // 保留类名（Vue组件）
+    keep_fnames: true,      // 保留函数名（Vue方法）
+    unsafe: false           // 禁用unsafe优化
+  },
+  mangle: {
+    properties: false,      // 不混淆属性名
+    reserved: [...]         // 大量保留名称
+  }
+}
+```
+
+### 为什么这样配置
+- **Vue响应式系统**依赖属性名不被改变
+- **组件系统**需要保留类名和函数名
+- **动态属性访问**在混淆后可能失效
+- **第三方库集成**需要保留特定标识符
+
+## 结论
+
+新的安全混淆配置在保护代码的同时确保应用稳定运行。虽然混淆强度相比之前有所降低，但对于大多数安全需求已经足够，且避免了白屏等兼容性问题。
+
+**推荐使用**: `npm run build:win:safe`

electron.vite.config.ts

@@ -6,7 +6,11 @@ import Components from 'unplugin-vue-components/vite'
 import tsconfigPaths from 'vite-tsconfig-paths'
 import { NaiveUiResolver } from 'unplugin-vue-components/resolvers'
 
-export default defineConfig({
+export default defineConfig(({ command }) => {
+  const isProduction = command === 'build'
+  const enableObfuscation = process.env.OBFUSCATE === 'true'
+  
+  return {
     main: {
       resolve: {
         alias: {
@@ -53,6 +57,91 @@ export default defineConfig({
         Components({
           resolvers: [NaiveUiResolver()]
         })
+      ],
+      build: {
+        // 为生产环境添加代码混淆和优化
+        ...(isProduction ? {
+          minify: 'terser',
+          terserOptions: {
+            compress: {
+              // 安全的压缩选项 - 避免破坏Vue响应式系统
+              drop_console: enableObfuscation, // 根据环境变量决定是否移除console
+              drop_debugger: true, // 移除debugger
+              pure_funcs: enableObfuscation ? ['console.log', 'console.info', 'console.debug', 'console.warn'] : [], 
+              passes: 1, // 只进行一轮压缩，避免过度优化
+              keep_fargs: true, // 保留函数参数，对Vue很重要
+              // 关闭所有unsafe选项，确保Vue和响应式系统正常工作
+              unsafe: false,
+              unsafe_comps: false,
+              unsafe_Function: false,
+              unsafe_math: false,
+              unsafe_symbols: false,
+              unsafe_methods: false,
+              unsafe_proto: false,
+              unsafe_regexp: false,
+              unsafe_undefined: false,
+              // 保留一些对Vue重要的功能
+              keep_classnames: true, // 保留类名
+              keep_fnames: true, // 保留函数名，对Vue组件很重要
+              // 移除条件编译，避免影响动态代码
+              global_defs: {}
+            },
+            mangle: enableObfuscation ? {
+              // 更保守的混淆策略
+              properties: false, // 完全关闭属性名混淆，避免破坏Vue
+              // 保留更多重要的标识符
+              reserved: [
+                // Vue 核心
+                'Vue', 'vue', 'VNode', 'Component', 'Directive', 'Plugin', 'App', 'app',
+                'reactive', 'ref', 'computed', 'watch', 'watchEffect', 'onMounted', 'onUnmounted',
+                'provide', 'inject', 'createApp', 'mount', 'unmount', 'nextTick',
+                // Vue Router
+                'router', 'route', 'useRouter', 'useRoute', 'RouterView', 'RouterLink',
+                // Pinia
+                'pinia', 'store', 'useStore', 'defineStore', 'storeToRefs',
+                // Naive UI 相关  
+                'naive', 'NaiveUi', 'n-', 'NButton', 'NInput', 'NForm', 'NSelect', 'NModal',
+                'NCard', 'NLayout', 'NSpace', 'NGrid', 'NGridItem', 'NIcon', 'NText',
+                'useDialog', 'useMessage', 'useNotification', 'useLoadingBar',
+                // Electron 相关
+                'ElectronAPI', 'electron', 'ipcRenderer', 'contextBridge', 'electronAPI',
+                // 通用保留
+                'require', 'exports', 'module', '__dirname', '__filename',
+                'window', 'document', 'global', 'process', 'Buffer',
+                // 保留以$开头的Vue特殊属性
+                '$', '$emit', '$props', '$attrs', '$slots', '$refs', '$parent', '$root',
+                // 保留一些常用的方法名
+                'toString', 'valueOf', 'hasOwnProperty', 'isPrototypeOf',
+                // 保留事件相关
+                'addEventListener', 'removeEventListener', 'dispatchEvent'
               ]
+            } : false,
+            format: {
+              // 更安全的格式化选项
+              comments: false, // 移除注释
+              beautify: false, // 不美化代码
+              // 使用更保守的格式化设置
+              ascii_only: false, // 不强制ASCII，避免中文问题
+              wrap_iife: false, // 不包装IIFE，避免作用域问题
+              semicolons: true // 保留分号，确保代码正确性
+            }
+          },
+          rollupOptions: {
+            output: {
+              // 文件名混淆保持简单
+              chunkFileNames: enableObfuscation ? 
+                'assets/c[hash:8].js' : 
+                'assets/[name]-[hash].js',
+              entryFileNames: enableObfuscation ? 
+                'assets/e[hash:8].js' : 
+                'assets/[name]-[hash].js',
+              assetFileNames: enableObfuscation ? 
+                'assets/a[hash:8].[ext]' : 
+                'assets/[name]-[hash].[ext]'
+            }
+          }
+        } : {})
+      }
+    }
   }
 })

package.json

@@ -1,7 +1,7 @@
 {
   "name": "laitool-pro",
   "productName": "LaiToolPro",
-  "version": "v4.0.1",
+  "version": "v4.0.2",
   "description": "来推 Pro - 一款集音频处理、文案生成、图片生成、视频生成等功能于一体的多合一AI工具软件。",
   "main": "./out/main/index.js",
   "author": "xiangbei",
@@ -15,11 +15,16 @@
     "start": "electron-vite preview",
     "dev": "electron-vite dev",
     "build": "npm run typecheck && electron-vite build",
+    "build:safe": "cross-env OBFUSCATE=true npm run typecheck && cross-env OBFUSCATE=true electron-vite build",
     "postinstall": "electron-builder install-app-deps",
     "build:unpack": "npm run build && electron-builder --dir",
+    "build:unpack:safe": "npm run build:safe && electron-builder --dir",
     "build:win": "npm run build && electron-builder --win",
+    "build:win:safe": "npm run build:safe && electron-builder --win",
     "build:mac": "npm run build && electron-builder --mac",
-    "build:linux": "npm run build && electron-builder --linux"
+    "build:mac:safe": "npm run build:safe && electron-builder --mac",
+    "build:linux": "npm run build && electron-builder --linux",
+    "build:linux:obfuscated": "npm run build:obfuscated && electron-builder --linux"
   },
   "dependencies": {
     "@alicloud/alimt20181012": "^1.3.0",
@@ -52,15 +57,20 @@
     "@electron-toolkit/eslint-config-prettier": "3.0.0",
     "@electron-toolkit/eslint-config-ts": "^3.0.0",
     "@electron-toolkit/tsconfig": "^1.0.1",
+    "@rollup/plugin-terser": "^0.4.4",
     "@types/node": "^22.13.4",
     "@vitejs/plugin-vue": "^5.2.1",
+    "cross-env": "^10.0.0",
     "electron": "^34.2.0",
     "electron-builder": "^25.1.8",
     "electron-vite": "^3.0.0",
     "eslint": "^9.20.1",
     "eslint-plugin-vue": "^9.32.0",
+    "javascript-obfuscator": "^4.1.1",
     "naive-ui": "^2.41.0",
     "prettier": "^3.5.1",
+    "rollup-plugin-obfuscator": "^1.1.0",
+    "terser": "^5.44.0",
     "typescript": "^5.7.3",
     "unplugin-auto-import": "^19.1.2",
     "unplugin-vue-components": "^28.4.1",

src/define/Tools/image.ts

@@ -158,7 +158,7 @@ export function GetImageTypeFromBase64(base64String: string): string {
  * @param url 本地文件路径或网络图片URL
  * @returns Promise<string> 返回一个Promise，解析为包含MIME类型的base64字符串
  */
-export function GetImageBase64(url: string): Promise<string> {
+export function GetImageBase64(url: string, noPrefix: boolean = false): Promise<string> {
   if (!url) {
     return Promise.reject(t("{data} 不能为空", {
       data: 'URL'
@@ -173,8 +173,12 @@ export function GetImageBase64(url: string): Promise<string> {
           response.on('data', (chunk) => data.push(chunk))
           response.on('end', () => {
             const buffer = Buffer.concat(data)
+            if (noPrefix) {
+              return resolve(buffer.toString('base64'))
+            }
             const base64Data = `data:${mimeType};base64,${buffer.toString('base64')}`
             resolve(base64Data)
+
           })
         })
         .on('error', (err) => reject(err))
@@ -186,6 +190,9 @@ export function GetImageBase64(url: string): Promise<string> {
           reject(err)
         } else {
           const mimeType = GetMimeType(url)
+          if (noPrefix) {
+            return resolve(data.toString('base64'))
+          }
           const base64Data = `data:${mimeType};base64,${data.toString('base64')}`
           resolve(base64Data)
         }

src/define/data/aiData/aiData.ts

@@ -1,20 +1,11 @@
 import { t } from '@/i18n'
-import { AIStoryboardMasterAIEnhance } from './aiPrompt/bookStoryboardPrompt/aiStoryboardMasterAIEnhance'
-import { AIStoryboardMasterGeneral } from './aiPrompt/bookStoryboardPrompt/aiStoryboardMasterGeneral'
-import { AIStoryboardMasterMJAncientStyle } from './aiPrompt/bookStoryboardPrompt/aiStoryboardMasterMJAncientStyle'
-import { AIStoryboardMasterOptimize } from './aiPrompt/bookStoryboardPrompt/aiStoryboardMasterOptimize'
-import { AIStoryboardMasterScenePrompt } from './aiPrompt/bookStoryboardPrompt/aiStoryboardMasterScenePrompt'
-import { AIStoryboardMasterSDEnglish } from './aiPrompt/bookStoryboardPrompt/aiStoryboardMasterSDEnglish'
-import { AIStoryboardMasterSingleFrame } from './aiPrompt/bookStoryboardPrompt/aiStoryboardMasterSingleFrame'
-import { AIStoryboardMasterSingleFrameWithCharacter } from './aiPrompt/bookStoryboardPrompt/aiStoryboardMasterSingleFrameWithCharacter'
-import { AIStoryboardMasterSpecialEffects } from './aiPrompt/bookStoryboardPrompt/aitoryboardMasterSpecialEffects'
 
 export type AiInferenceModelModel = {
   value: string // AI选项值
   label: string // AI选项标签
   hasExample: boolean // 是否有示例
   mustCharacter: boolean // 是否必须包含角色
-  requestBody: OpenAIRequest.Request // AI请求体
+  requestBody: string | OpenAIRequest.Request // AI请求体
   allAndExampleContent: string | null // 所有和示例内容
 }
 
@@ -28,7 +19,7 @@ export const aiOptionsData: AiInferenceModelModel[] = [
     label: t('【LaiTool】场景提示大师（上下文-提示词不包含人物）'),
     hasExample: false,
     mustCharacter: false,
-    requestBody: AIStoryboardMasterScenePrompt,
+    requestBody: "AIStoryboardMasterScenePrompt",
     allAndExampleContent: null
   },
   {
@@ -36,7 +27,7 @@ export const aiOptionsData: AiInferenceModelModel[] = [
     label: t('【LaiTool】分镜大师-特效增强版（上下文-人物场景固定）'),
     hasExample: false,
     mustCharacter: true,
-    requestBody: AIStoryboardMasterSpecialEffects,
+    requestBody: "AIStoryboardMasterSpecialEffects",
     allAndExampleContent: null
   },
   {
@@ -44,7 +35,7 @@ export const aiOptionsData: AiInferenceModelModel[] = [
     label: t('【LaiTool】分镜大师-通用版（上下文-人物场景固定-类型推理）'),
     hasExample: false,
     mustCharacter: true,
-    requestBody: AIStoryboardMasterGeneral,
+    requestBody: "AIStoryboardMasterGeneral",
     allAndExampleContent: null
   },
   {
@@ -52,7 +43,7 @@ export const aiOptionsData: AiInferenceModelModel[] = [
     label: t('【LaiTool】分镜大师-全面版-AI增强（上下文-人物场景固定-单帧）'),
     hasExample: false,
     mustCharacter: true,
-    requestBody: AIStoryboardMasterAIEnhance,
+    requestBody: "AIStoryboardMasterAIEnhance",
     allAndExampleContent: null
   },
   {
@@ -60,7 +51,7 @@ export const aiOptionsData: AiInferenceModelModel[] = [
     label: t('【LaiTool】分镜大师-全能优化版（上下文-人物固定）'),
     hasExample: false,
     mustCharacter: true,
-    requestBody: AIStoryboardMasterOptimize,
+    requestBody: "AIStoryboardMasterOptimize",
     allAndExampleContent: null
   },
   {
@@ -68,7 +59,7 @@ export const aiOptionsData: AiInferenceModelModel[] = [
     label: t('【LaiTool】分镜大师-MJ超精细化版（上下文-人物场景固定）'),
     hasExample: false,
     mustCharacter: true,
-    requestBody: AIStoryboardMasterMJAncientStyle,
+    requestBody: "AIStoryboardMasterMJAncientStyle",
     allAndExampleContent: null
   },
   {
@@ -76,7 +67,7 @@ export const aiOptionsData: AiInferenceModelModel[] = [
     label: t('【LaiTool】分镜大师-SD英文版（上下文-人物场景固定-SD-英文提示词）'),
     hasExample: false,
     mustCharacter: true,
-    requestBody: AIStoryboardMasterSDEnglish,
+    requestBody: "AIStoryboardMasterSDEnglish",
     allAndExampleContent: null
   },
   {
@@ -84,7 +75,7 @@ export const aiOptionsData: AiInferenceModelModel[] = [
     label: t('【LaiTool】分镜大师-单帧分镜提示词（上下文-单帧-人物自动推理）'),
     hasExample: false,
     mustCharacter: false,
-    requestBody: AIStoryboardMasterSingleFrame,
+    requestBody: "AIStoryboardMasterSingleFrame",
     allAndExampleContent: null
   },
   {
@@ -92,7 +83,7 @@ export const aiOptionsData: AiInferenceModelModel[] = [
     label: t('【LaiTool】分镜大师-单帧分镜提示词（上下文-单帧-人物场景固定）'),
     hasExample: false,
     mustCharacter: true,
-    requestBody: AIStoryboardMasterSingleFrameWithCharacter,
+    requestBody: "AIStoryboardMasterSingleFrameWithCharacter",
     allAndExampleContent: null
   }
 ]

src/define/data/aiData/aiPrompt/bookStoryboardPrompt/index.ts

@@ -0,0 +1,39 @@
+import { t } from "@/i18n";
+import { AIStoryboardMasterAIEnhance } from "./aiStoryboardMasterAIEnhance";
+import { AIStoryboardMasterGeneral } from "./aiStoryboardMasterGeneral";
+import { AIStoryboardMasterMJAncientStyle } from "./aiStoryboardMasterMJAncientStyle";
+import { AIStoryboardMasterOptimize } from "./aiStoryboardMasterOptimize";
+import { AIStoryboardMasterScenePrompt } from "./aiStoryboardMasterScenePrompt";
+import { AIStoryboardMasterSDEnglish } from "./aiStoryboardMasterSDEnglish";
+import { AIStoryboardMasterSingleFrame } from "./aiStoryboardMasterSingleFrame";
+import { AIStoryboardMasterSingleFrameWithCharacter } from "./aiStoryboardMasterSingleFrameWithCharacter";
+import { AIStoryboardMasterSpecialEffects } from "./aitoryboardMasterSpecialEffects";
+
+// 根据 value 返回对应的分镜预设请求体对象
+// value: 预设类型字符串
+// 返回: OpenAIRequest.Request 对象
+// 如果未找到对应类型会抛出错误（带有国际化提示）
+export function GetAIPromptRequestBodyByValue(value: string): OpenAIRequest.Request {
+  switch (value) {
+    case "AIStoryboardMasterScenePrompt":
+      return AIStoryboardMasterScenePrompt;
+    case "AIStoryboardMasterSpecialEffects":
+      return AIStoryboardMasterSpecialEffects;
+    case "AIStoryboardMasterGeneral":
+      return AIStoryboardMasterGeneral;
+    case "AIStoryboardMasterAIEnhance":
+      return AIStoryboardMasterAIEnhance;
+    case "AIStoryboardMasterOptimize":
+      return AIStoryboardMasterOptimize;
+    case "AIStoryboardMasterMJAncientStyle":
+      return AIStoryboardMasterMJAncientStyle;
+    case "AIStoryboardMasterSDEnglish":
+      return AIStoryboardMasterSDEnglish;
+    case "AIStoryboardMasterSingleFrame":
+      return AIStoryboardMasterSingleFrame;
+    case "AIStoryboardMasterSingleFrameWithCharacter":
+      return AIStoryboardMasterSingleFrameWithCharacter;
+    default:
+      throw new Error(t('未找到对应的分镜预设的请求数据，请检查'))
+  }
+}

src/define/data/apiData.ts

@@ -1,6 +1,34 @@
 import { t } from "@/i18n"
 
-export const apiDefineData = [
+// API MJ URL 配置接口
+interface ApiMjUrl {
+  imagine: string;
+  describe: string;
+  video?: string;
+  update_file: string;
+  once_get_task: string;
+  query_url?: string;
+}
+
+// API D3 URL 配置接口
+interface ApiD3Url {
+  image: string;
+}
+
+// API 定义数据项接口
+export interface APIProviderDataItem {
+  label: string;
+  value: string;
+  id?: string;
+  gpt_url?: string;
+  base_url: string;
+  mj_url?: ApiMjUrl;
+  d3_url?: ApiD3Url;
+  buy_url?: string;
+  isPackage?: boolean;
+}
+
+export const apiDefineData: APIProviderDataItem[] = [
   {
     label: t('LAI API - 香港'),
     value: 'b44c6f24-59e4-4a71-b2c7-3df0c4e35e65',

src/define/data/softwareData.ts

@@ -30,8 +30,8 @@ interface ISoftwareData {
 }
 
 export const SoftwareData: ISoftwareData = {
-  version: 'V4.0.1',
+  version: 'V4.0.2',
-  date: '2025-09-21',
+  date: '2025-09-23',
   systemInfo: {
     documentationUrl: 'https://rvgyir5wk1c.feishu.cn/wiki/WdaWwAfDdiLOnjkywIgcaQoKnog',
     updateUrl: 'https://pvwu1oahp5m.feishu.cn/docx/CAjGdTDlboJ3nVx0cQccOuNHnvd',

src/define/enum/bookEnum.ts

@@ -115,6 +115,8 @@ export enum BookBackTaskType {
   LUMA_VIDEO = 'luma_video',
   // kling 生成视频
   KLING_VIDEO = 'kling_video',
+  // kling 视频拓展
+  KLING_VIDEO_EXTEND = 'kling_video_extend',
   // MJ Video
   MJ_VIDEO = 'mj_video',
   // MJ VIDEO EXTEND 视频拓展

src/define/enum/softwareEnum.ts

@@ -68,6 +68,7 @@ export enum ResponseMessageType {
   RUNWAY_VIDEO = 'RUNWAY_VIDEO', // Runway生成视频
   LUMA_VIDEO = 'LUMA_VIDEO', // Luma生成视频
   KLING_VIDEO = 'KLING_VIDEO', // Kling生成视频
+  KLING_VIDEO_EXTEND = 'KLING_VIDEO_EXTEND', // Kling生成视频拓展
   MJ_VIDEO = 'MJ_VIDEO', // MJ生成视频
   MJ_VIDEO_EXTEND = 'MJ_VIDEO_EXTEND', // MJ生成视频拓展
   VIDEO_SUCESS = 'VIDEO_SUCESS' //视频生成成功

src/define/enum/video.ts

@@ -11,6 +11,8 @@ export enum ImageToVideoModels {
   LUMA = 'LUMA',
   /** 可灵生成视频 */
   KLING = 'KLING',
+  /** 可灵视频拓展 */
+  KLING_VIDEO_EXTEND = 'KLING_VIDEO_EXTEND',
   /** Pika 生成视频 */
   PIKA = 'PIKA',
   /** MJ 图转视频 */
@@ -19,6 +21,7 @@ export enum ImageToVideoModels {
   MJ_VIDEO_EXTEND = 'MJ_VIDEO_EXTEND'
 }
 
+
 export const MappingTaskTypeToVideoModel = (type: BookBackTaskType | string) => {
   switch (type) {
     case BookBackTaskType.LUMA_VIDEO:
@@ -27,6 +30,8 @@ export const MappingTaskTypeToVideoModel = (type: BookBackTaskType | string) =>
       return ImageToVideoModels.RUNWAY
     case BookBackTaskType.KLING_VIDEO:
       return ImageToVideoModels.KLING
+    case BookBackTaskType.KLING_VIDEO_EXTEND:
+      return ImageToVideoModels.KLING_VIDEO_EXTEND
     case BookBackTaskType.MJ_VIDEO:
       return ImageToVideoModels.MJ_VIDEO
     case BookBackTaskType.MJ_VIDEO_EXTEND:
@@ -103,6 +108,8 @@ export enum VideoModel {
 export enum VideoStatus {
   /** 等待 */
   WAIT = 'wait',
+  /** 提交成功 */
+  SUBMITTED = 'submitted',
   /** 处理中 */
   PROCESSING = 'processing',
   /** 完成 */
@@ -149,6 +156,12 @@ export enum RunwaySeconds {
 
 //#region 可灵相关
 
+
+/**
+ * 可灵生成视频的模式
+ * - std：高性能
+ * - pro：高表现
+ */
 export enum KlingMode {
   /** 高性能 */
   STD = 'std',
@@ -156,6 +169,171 @@ export enum KlingMode {
   PRO = 'pro'
 }
 
+/**
+ * 获取可灵生成模式的标签
+ * 
+ * @param mode 可灵生成模式枚举值或字符串
+ * @returns 返回对应的中文标签
+ */
+export function GetKlingModeLabel(mode: KlingMode | string) {
+  switch (mode) {
+    case KlingMode.STD:
+      return t('高性能 (std)')
+    case KlingMode.PRO:
+      return t('高表现 (pro)')
+    default:
+      return t('未知')
+  }
+}
+
+/**
+ * 获取可灵生成模式的选项列表
+ * 
+ * @returns 返回包含标签和值的选项数组，用于下拉选择框等UI组件
+ */
+export function GetKlingModeOptions() {
+  return [
+    {
+      label: GetKlingModeLabel(KlingMode.STD),
+      value: KlingMode.STD
+    },
+    {
+      label: GetKlingModeLabel(KlingMode.PRO),
+      value: KlingMode.PRO
+    }
+  ]
+}
+
+
+/**
+ * 可灵生成视频的时长
+ * - '5'：5秒
+ * - '10'：10秒
+ */
+export enum KlingDuration {
+  FIVE = 5,
+  TEN = 10
+}
+
+/**
+ * 获取可灵视频时长的标签
+ * 
+ * @param duration 可灵视频时长枚举值或字符串
+ * @returns 返回对应的中文标签
+ */
+export function GetKlingDurationLabel(duration: KlingDuration | string) {
+  switch (duration) {
+    case KlingDuration.FIVE:
+      return t('5秒')
+    case KlingDuration.TEN:
+      return t('10秒')
+    default:
+      return t('未知')
+  }
+}
+
+/**
+ * 获取可灵视频时长的选项列表
+ * 
+ * @returns 返回包含标签和值的选项数组，用于下拉选择框等UI组件
+ */
+export function GetKlingDurationOptions() {
+  return [
+    {
+      label: GetKlingDurationLabel(KlingDuration.FIVE),
+      value: KlingDuration.FIVE
+    },
+    {
+      label: GetKlingDurationLabel(KlingDuration.TEN),
+      value: KlingDuration.TEN
+    }
+  ]
+}
+
+
+/**
+ * 可灵模型名称
+ * - kling-v1：V1 版本
+ * - kling-v1-5：V1.5 版本
+ * - kling-v1-6：V1.6 版本
+ * - kling-v2-master：V2 master 版本
+ * - kling-v2-1：V2.1 版本
+ * - kling-v2-1-master：V2.1 master 版本
+ */
+export enum KlingModelName {
+  /** V1 版本 */
+  KLING_V1 = 'kling-v1',
+  /** V1.5 版本 */
+  KLING_V1_5 = 'kling-v1-5',
+  /** V1.6 版本 */
+  KLING_V1_6 = 'kling-v1-6',
+  /** V2 master 版本 */
+  KLING_V2_MASTER = 'kling-v2-master',
+  /** V2.1 版本 */
+  KLING_V2_1 = 'kling-v2-1',
+  /** V2.1 master 版本 */
+  KLING_V2_1_MASTER = 'kling-v2-1-master'
+}
+
+/**
+ * 获取可灵模型名称的标签
+ * 
+ * @param modelName 可灵模型名称枚举值或字符串
+ * @returns 返回对应的中文标签
+ */
+export function GetKlingModelNameLabel(modelName: KlingModelName | string) {
+  switch (modelName) {
+    case KlingModelName.KLING_V1:
+      return t('Kling V1')
+    case KlingModelName.KLING_V1_5:
+      return t('Kling V1.5')
+    case KlingModelName.KLING_V1_6:
+      return t('Kling V1.6')
+    case KlingModelName.KLING_V2_MASTER:
+      return t('Kling V2 Master')
+    case KlingModelName.KLING_V2_1:
+      return t('Kling V2.1')
+    case KlingModelName.KLING_V2_1_MASTER:
+      return t('Kling V2.1 Master')
+    default:
+      return t('未知')
+  }
+}
+
+/**
+ * 获取可灵模型名称的选项列表
+ * 
+ * @returns 返回包含标签和值的选项数组，用于下拉选择框等UI组件
+ */
+export function GetKlingModelNameOptions() {
+  return [
+    {
+      label: GetKlingModelNameLabel(KlingModelName.KLING_V1),
+      value: KlingModelName.KLING_V1
+    },
+    {
+      label: GetKlingModelNameLabel(KlingModelName.KLING_V1_5),
+      value: KlingModelName.KLING_V1_5
+    },
+    {
+      label: GetKlingModelNameLabel(KlingModelName.KLING_V1_6),
+      value: KlingModelName.KLING_V1_6
+    },
+    {
+      label: GetKlingModelNameLabel(KlingModelName.KLING_V2_MASTER),
+      value: KlingModelName.KLING_V2_MASTER
+    },
+    {
+      label: GetKlingModelNameLabel(KlingModelName.KLING_V2_1),
+      value: KlingModelName.KLING_V2_1
+    },
+    {
+      label: GetKlingModelNameLabel(KlingModelName.KLING_V2_1_MASTER),
+      value: KlingModelName.KLING_V2_1_MASTER
+    }
+  ]
+}
+
 //#endregion
 
 //#region  MJ Video

src/define/ipcDefineString/subDefineString/bookDefineString.ts

@@ -162,7 +162,10 @@ const BOOK = {
   UPDATE_BOOK_TASK_DETAIL_VIDEO_MESSAGE: 'UPDATE_BOOK_TASK_DETAIL_VIDEO_MESSAGE',
 
   /** MJ VIDEO 图转视频返回前端数据任务 */
-  MJ_VIDEO_TO_VIDEO_RETURN: 'MJ_VIDEO_TO_VIDEO_RETURN'
+  MJ_VIDEO_TO_VIDEO_RETURN: 'MJ_VIDEO_TO_VIDEO_RETURN',
+
+  /** Kling 图转视频返回前端数据任务 */
+  KLING_IMAGE_TO_VIDEO_RETURN: 'KLING_IMAGE_TO_VIDEO_RETURN',
 
 
   //#endregion

src/define/model/book/bookTaskDetail.d.ts

@@ -1,6 +1,8 @@
 import {
   ImageToVideoModels,
+  KlingDuration,
   KlingMode,
+  KlingModelName,
   MJVideoBatchSize,
   MJVideoType,
   RunawayModel,
@@ -71,16 +73,59 @@ declare namespace BookTaskDetail {
     request_model?: string // 请求的模型，快速还是慢速
   }
 
+  /**
+   * Kling 合成视频参数
+   */
   type klingOptions = {
-    model?: string // 模型(kling-v1)
+    /**
-    image: string // 图片地址，必须，支持Base64编码或图片URL，支持.jpg / .jpeg / .png格式，大小不能超过10MB，分辨率不小于300*300px
+     * 模型名称，可选，枚举值：
-    image_tail?: string // 尾帧图片地址，支持Base64编码或图片URL，支持.jpg / .jpeg / .png格式，大小不能超过10MB，分辨率不小于300*300px
+     * - kling-v1
-    prompt?: string // 提示词，正向文本提示， 可选，不能超过500个字符
+     * - kling-v1-5
-    negative_prompt?: string // 负面提示，负向文本提示，可选，不能超过200个字符
+     * - kling-v1-6
-    cfg_scale?: number // 提示词相关性，可选，范围0-1
+     * - kling-v2-master
-    mode?: KlingMode // 生成视频的模式，可选，枚举值：std（高性能）或 pro（高表现）
+     * - kling-v2-1
-    duration?: RunwaySeconds // 生成视频时长，单位秒，可选，枚举值：5，10（包含尾帧的请求仅支持5秒）
+     * - kling-v2-1-master
-    callback_url?: string // 回调地址，可选，生成视频完成后，会向该地址发送通知
+     * 默认值：kling-v1
+     */
+    model_name?: KlingModelName;
+    /**
+     * 参考图像，必须，支持Base64编码或图片URL，支持.jpg / .jpeg / .png格式，大小不能超过10MB，分辨率不小于300*300px
+     */
+    image: string;
+    /**
+     * 参考图像 - 尾帧控制，可选，支持Base64编码或图片URL，支持.jpg / .jpeg / .png格式，大小不能超过10MB，分辨率不小于300*300px
+     */
+    image_tail?: string;
+    /**
+     * 正向文本提示，可选，不能超过500个字符
+     */
+    prompt?: string;
+    /**
+     * 负向文本提示，可选，不能超过200个字符
+     */
+    negative_prompt?: string;
+    /**
+     * 生成视频的自由度，可选，值越大相关性越强，取值范围：[0, 1]
+     */
+    cfg_scale?: number;
+    /**
+     * 生成视频的模式，可选，枚举值：std（高性能）或 pro（高表现）
+     */
+    mode?: KlingMode;
+    /**
+     * 生成视频时长，单位秒，可选，枚举值：'5' | '10'（包含尾帧的请求仅支持5秒）
+     */
+    duration?: KlingDuration;
+
+    /**
+     * 视频ID，扩展视频时使用
+     */
+    video_id?: string;
+
+    /**
+     * 任务ID，扩展视频时使用
+     */
+    task_id?: string;
   }
 
   interface MjVideoOptions {

src/define/model/setting.d.ts

@@ -2,6 +2,7 @@ import { ImageToVideoCategory } from '@/define/data/imageData'
 import { ImageGenerateMode, MJRobotType, MJSpeed } from '../data/mjData'
 import { JianyingKeyFrameEnum } from '../enum/jianyingEnum'
 import { ImageToVideoModels } from '@/define/enum/video'
+import { APIProviderDataItem } from '../data/apiData'
 
 declare namespace SettingModal {
   //#region 基础设置
@@ -194,6 +195,16 @@ declare namespace SettingModal {
     translationModel: string
   }
 
+  /**
+   * AI 推理设置与提供商组合接口
+   * 继承 InferenceAISettings 的所有属性，并添加了 API 提供商的详细信息
+   * 用于在需要同时获取推理设置和对应 API 提供商配置的场景
+   */
+  interface InferenceAISettingAndProvider extends InferenceAISettings {
+    /** API 提供商详细配置项 - 包含完整的 API 提供商信息 */
+    apiProviderItem: APIProviderDataItem
+  }
+
   //#endregion
 
   //#region SD设置

src/i18n/locales/en.ts

@@ -58,6 +58,7 @@ export default {
   "未知错误": 'Unknown Error',
   "未知类型": 'Unknown Type',
   "未知操作": 'Unknown Operation',
+  "未知状态": "Unknown Status",
   "下载成功": 'Download Successful',
   "下载失败": 'Download Failed',
   "页面不存在": "Page Not Found",
@@ -244,9 +245,10 @@ export default {
   "当前分镜数据的MJ图转视频参数为空或参数校验失败，请检查": "Current storyboard data MJ image-to-video parameters are empty or validation failed, please check",
   '当前Midjourney模式不支持视频生成功能，请更换为MJ API或本地代理模式后重试！': 'Current Midjourney mode does not support video generation, please switch to MJ API or local proxy mode and try again!',
   'Midjourney图转视频任务执行失败，失败信息如下：{error}': 'Midjourney image-to-video task execution failed, error details: {error}',
+  "图转视频任务执行完成！": "Image-to-video task completed!",
   'Midjourney图转视频任务执行完成。': 'Midjourney image-to-video task execution completed.',
   'Midjourney图转视频任务执行中...': 'Midjourney image-to-video task executing...',
-  '已成功提交Midjourney图转视频任务，任务ID：{taskId}': 'Successfully submitted Midjourney image-to-video task, Task ID: {taskId}',
+  '已成功提交{type}图转视频任务，任务ID：{taskId}': 'Successfully submitted {type} image-to-video task, task ID: {taskId}',
   "小说批次任务的分镜数据的转视频配置为空，请检查": "Video conversion configuration for storyboard data of novel batch task is empty, please check",
   "分镜的图片没有全部出完，不能继续该操作！！": "Storyboard images are not all generated, cannot continue this operation!!",
   "分镜 {name} 图片在本地未找到，不能继续该操作，请检查对应分镜的图片路径是否正确": "Storyboard {name} image not found locally, cannot continue this operation, please check if the corresponding storyboard image path is correct",
@@ -311,8 +313,16 @@ export default {
   '同步主图信息失败，{error}': 'Failed to sync main image information, {error}',
   '该操作会将当前批次的所有分镜的提示词全部重置为空，此操作不可撤销，重置的数据不可恢复，是否继续？': 'This operation will reset all storyboards\' prompts in the current batch to empty. This action is irreversible, and reset data cannot be recovered. Do you want to continue?',
   '正在执行重置提示词任务，请稍等...': 'Resetting prompts, please wait...',
-  "重置提示词失败，{error}": "重置提示词失败，{error}",
+  "重置提示词失败，{error}": "Reset prompts failed, {error}",
   "重置提示词成功": "Reset prompts successfully",
+  "该操作会选择 TXT 文件进行导入提示词，\n\n提示词文件格式要求：\n每行一个提示词，顺序和当前分镜顺序一致，\n如果某个分镜不需要导入提示词，可以留空该行，\n超出分镜的提示词会被删除，不足则只导入文本中有的提示词数据\n\n是否继续？": "This operation will select a TXT file to import prompts,\n\nPrompt file format requirements:\nOne prompt per line, in the same order as the current storyboard,\nIf a storyboard does not need a prompt, leave that line empty,\nPrompts exceeding the number of storyboards will be deleted, insufficient prompts will only import the available prompt data\n\nDo you want to continue?",
+  "导入提示词失败，{error}": "Import prompts failed, {error}",
+  "导入提示词成功": "Import prompts successfully",
+  "导入的提示词文件内容为空": "Imported prompt file content is empty",
+  '导入第 {line} 行提示词失败，{error}': 'Failed to import prompt on line {line}, {error}',
+  "正在批量应用当前设置...": "Batch applying current settings...",
+  "将当前转视频的基础设置批量应用到所有的分镜中": "Batch apply current video conversion basic settings to all storyboards",
+  "应用设置": "Apply Settings",
   //#endregion
 
   //#region 出图
@@ -978,6 +988,7 @@ export default {
   "AI处理文案成功": "AI content processing successful",
   "AI处理文案失败，{error}": "AI content processing failed, {error}",
   "检测系统当前的语言已修改，继续执行会刷新当前页面并应用当前语言，是否继续？": 'System language has been modified, continuing will refresh the current page and apply the current language, continue?',
+  "当前API提供商数据不存在，请检查数据是否正确": "Current API provider data does not exist, please check if the data is correct",
   //#endregion
 
   //#region 预设
@@ -1183,6 +1194,8 @@ export default {
   '场景分析': 'Scene Analysis',
   '推理所有提示词': 'Infer All Prompts',
   '推理空白分镜提示词': 'Infer Blank Storyboard Prompts',
+  "重置所有提示词": "Reset All Prompts",
+  "导入提示词": "Import Prompts",
   '生成所有图片': 'Generate All Images',
   '生成未生成图片分镜': 'Generate Un-generated Image Storyboards',
   '生成失败图片分镜': 'Generate Failed Image Storyboards',
@@ -1545,6 +1558,10 @@ export default {
   '7. 需要在外部手动选择需要的{type}数据时，请点击<strong>“{button}”</strong> 按钮进行导入到标签集中': '7. When you need to manually select the required {type} data externally, please click the <strong>"{button}"</strong> button to import it into the tag set',
   '即将开始自动推理，该操作会将之前的 {type} 数据覆盖，是否继续？': 'About to start automatic inference. This operation will overwrite previous {type} data. Continue?',
   '正在推理，请稍等...': 'Inferring, please wait...',
+  "通用前/后缀": "General Prefix/Suffix",
+  "提示词前后缀设置": "Prompt Prefix/Suffix Settings",
+  "通用前缀": "General Prefix",
+  "通用后缀": "General Suffix",
   //#endregion
 
   //#region 转视频
@@ -1602,6 +1619,51 @@ export default {
   "当前批次任务已经开启图转视频，是否直接跳转到图文转视频界面？": "Current batch task has enabled image-to-video conversion, do you want to jump directly to the image-to-video interface?",
   "正在跳转到图文转视频界面...": "Jumping to image-to-video interface...",
   "已取消跳转，你可以在转视频模块中查看该任务": "Jump cancelled, you can view the task in the video conversion module",
+  '是否将当前分镜的设置批量应用到其余所有分镜？\n\n同步的设置：视频类型（SD/HD），运动变化（Motion），批次数据（Batch），视频原始（Raw），首尾循环（Loop） \n\n批量应用后，其余分镜的上述基础设置会被替换为当前分镜的数据，是否继续？': 'Do you want to apply the current storyboard settings to all other storyboards in batch?\n\nSynchronized settings: Video Type (SD/HD), Motion, Batch Data, Raw Video, Loop\n\nAfter batch application, the above basic settings of other storyboards will be replaced with the current storyboard data. Continue?',
+  "批量应用当前设置失败，{error}": "Failed to batch apply current settings, {error}",
+  "批量应用当前设置成功！": "Successfully batch applied current settings!",
+  "配置验证失败": "Configuration validation failed",
+
+  "可灵图转视频任务失败，失败信息：{error}": "Kling image-to-video task failed, error details: {error}",
+  "Kling图转视频任务完成！": "Kling image-to-video task completed!",
+  "未找到有效的API地址": "No valid API address found",
+  "请先配置AI推理的API密钥": "Please configure the API key for AI inference first",
+  "当前分镜数据的可灵图转视频参数为空或参数校验失败，请检查": "The Kling image-to-video parameters for the current storyboard data are empty or validation failed, please check",
+  "当前分镜数据的图片地址为空，请检查": "The image URL for the current storyboard data is empty, please check",
+  "视频ID数量与视频链接数量不匹配": "The number of video IDs does not match the number of video links",
+  "未找到有效的GPT API地址": "No valid GPT API address found",
+  "未知的视频生成方式，请检查": "Unknown video generation method, please check",
+  "当前分镜数据的可灵视频ID为空，请检查": 'The Kling video ID for the current storyboard data is empty, please check',
+  "当前分镜数据的可灵任务ID为空，请检查": "The Kling task ID for the current storyboard data is empty, please check",
+  "可灵视频延长任务完成！": "Kling video extension task completed!",
+  "可灵视频延长任务失败，失败信息：{error}": "Kling video extension task failed, error details: {error}",
+  "可灵图转视频任务执行中...": "Kling image-to-video task in progress...",
+  "可灵视频延长任务正在执行中...": "Kling video extension task in progress...",
+  "参考图像": "Reference Image",
+  "正向文本提示，可选，不能超过2500个字符": "Positive text prompt, optional, cannot exceed 2500 characters",
+  "负向文本提示，可选，不能超过2500个字符": "Negative text prompt, optional, cannot exceed 2500 characters",
+  "自由度": "Degree of Freedom",
+  '0-1之间': "Between 0-1",
+  "生成视频的自由度<br/><br/><strong>值越大，模型自由度越小</strong><br/>与用户输入的提示词相关性越强<br/><br/>取值范围：<strong>[0, 1]</strong>": "Degree of freedom for video generation<br/><br/><strong>The larger the value, the smaller the model's degree of freedom</strong><br/>The stronger the correlation with user input prompts<br/><br/>Range: <strong>[0, 1]</strong>",
+  "生成模式": "Generation Mode",
+  "生成视频的模式<br/><br/>枚举值：std，pro<br/>其中std：标准模式（标准），基础模式，性价比高<br/>其中pro：专家模式（高品质），高表现模式，生成视频质量更佳": "Video generation mode<br/><br/>Enum values: std, pro<br/>Where std: Standard mode (standard), basic mode, cost-effective<br/>Where pro: Expert mode (high quality), high-performance mode, better video quality",
+  "视频时长": "Video Duration",
+  '生成视频时长，单位s（5秒或10秒）': 'Video duration in seconds (5 or 10 seconds)',
+  "视频延长": "Video Extend",
+  "选择已有的视频任务作为延长的基础": "Select an existing video task as the basis for extension",
+  "视频ID": "Video ID",
+  "支持通过文本、图片和视频延长生成的视频的ID（原视频不能超过3分钟）": "Supports the ID of videos generated through text, image, and video extension (original video cannot exceed 3 minutes)",
+  "对应于视频ID的任务ID，通常在选择视频后自动填充": "Corresponding task ID for the video ID, usually auto-filled after selecting a video",
+  "是否将当前分镜的设置批量应用到其余所有分镜？\n\n同步的设置：模型名称（Model Name），生成模式（Mode），视频时长（Duration），自由度（CFG Scale） \n\n批量应用后，其余分镜的上述基础设置会被替换为当前分镜的数据，是否继续？": "Do you want to apply the current storyboard settings to all other storyboards in batch?\n\nSynchronized settings: Model Name, Mode, Duration, CFG Scale\n\nAfter batch application, the above basic settings of other storyboards will be replaced with the current storyboard data. Continue?",
+  "请选择一个已有的视频任务作为延长的基础": "Please select an existing video task as the basis for extension",
+  "父任务选择成功，视频ID已更新为: {videoId}": "Parent task selected successfully, video ID updated to: {videoId}",
+  "高性能 (std)": "High Performance (std)",
+  "高表现 (pro)": "High Performance (pro)",
+  "选择Video": "Select Video",
+  "<strong>必须</strong><br/><br/>• 支持格式：<strong>.jpg/.jpeg/.png</strong><br/>• 文件大小：<strong>不超过10MB</strong><br/>• 分辨率：<strong>不小于300*300px</strong><br/>• 宽高比：<strong>1:2.5 ~ 2.5:1</strong>之间": "<strong>必须</strong><br/><br/>• 支持格式：<strong>.jpg/.jpeg/.png</strong><br/>• 文件大小：<strong>不超过10MB</strong><br/>• 分辨率：<strong>不小于300*300px</strong><br/>• 宽高比：<strong>1:2.5 ~ 2.5:1</strong>之间",
+  "参考图像 - 尾帧控制": "参考图像 - 尾帧控制",
+  '<strong>可选</strong><br/><br/>• 支持格式：<strong>.jpg/.jpeg/.png</strong><br/>• 文件大小：<strong>不超过10MB</strong><br/>• 分辨率：<strong>不小于300*300px</strong><br/>• 宽高比：<strong>1:2.5 ~ 2.5:1</strong>之间': '<strong>可选</strong><br/><br/>• 支持格式：<strong>.jpg/.jpeg/.png</strong><br/>• 文件大小：<strong>不超过10MB</strong><br/>• 分辨率：<strong>不小于300*300px</strong><br/>• 宽高比：<strong>1:2.5 ~ 2.5:1</strong>之间',
+  //#endregion
 
   //#region  MJ
   '基本信息': 'Basic Information',
@@ -1721,7 +1783,6 @@ export default {
   '视频生成时长为5秒，但并非仅限于此。视频制作完成后，您可以在当前界面为选定的适配进行延长！': 'Video generation duration is 5 seconds, but not limited to this. After video production is completed, you can extend the selected adaptation in the current interface!',
   '您可以随意将视频延长最多 4 次，每次延长 4 秒，直至达到 21 秒（即可用的最大长度）。': 'You can freely extend the video up to 4 times, each extension adding 4 seconds, until reaching 21 seconds (the maximum available length).',
 
-  //#endregion
   //#endregion
 
   //#region  文案处理

src/i18n/locales/zh-cn.ts

@@ -58,6 +58,7 @@ export default {
   "未知错误": '未知错误',
   "未知类型": '未知类型',
   "未知操作": '未知操作',
+  "未知状态": "未知状态",
   "下载成功": '下载成功',
   "下载失败": '下载失败',
   "页面不存在": "页面不存在",
@@ -244,9 +245,10 @@ export default {
   "当前分镜数据的MJ图转视频参数为空或参数校验失败，请检查": "当前分镜数据的MJ图转视频参数为空或参数校验失败，请检查",
   '当前Midjourney模式不支持视频生成功能，请更换为MJ API或本地代理模式后重试！': '当前Midjourney模式不支持视频生成功能，请更换为MJ API或本地代理模式后重试！',
   'Midjourney图转视频任务执行失败，失败信息如下：{error}': 'Midjourney图转视频任务执行失败，失败信息如下：{error}',
+  "图转视频任务执行完成！": "图转视频任务执行完成！",
   'Midjourney图转视频任务执行完成。': 'Midjourney图转视频任务执行完成。',
   'Midjourney图转视频任务执行中...': 'Midjourney图转视频任务执行中...',
-  '已成功提交Midjourney图转视频任务，任务ID：{taskId}': '已成功提交Midjourney图转视频任务，任务ID：{taskId}',
+  '已成功提交{type}图转视频任务，任务ID：{taskId}': '已成功提交{type}图转视频任务，任务ID：{taskId}',
   "小说批次任务的分镜数据的转视频配置为空，请检查": "小说批次任务的分镜数据的转视频配置为空，请检查",
   "分镜的图片没有全部出完，不能继续该操作！！": "分镜的图片没有全部出完，不能继续该操作！！",
   "分镜 {name} 图片在本地未找到，不能继续该操作，请检查对应分镜的图片路径是否正确": "分镜 {name} 图片在本地未找到，不能继续该操作，请检查对应分镜的图片路径是否正确",
@@ -313,6 +315,14 @@ export default {
   '正在执行重置提示词任务，请稍等...': '正在执行重置提示词任务，请稍等...',
   "重置提示词失败，{error}": "重置提示词失败，{error}",
   "重置提示词成功": "重置提示词成功",
+  "该操作会选择 TXT 文件进行导入提示词，\n\n提示词文件格式要求：\n每行一个提示词，顺序和当前分镜顺序一致，\n如果某个分镜不需要导入提示词，可以留空该行，\n超出分镜的提示词会被删除，不足则只导入文本中有的提示词数据\n\n是否继续？": "该操作会选择 TXT 文件进行导入提示词，\n\n提示词文件格式要求：\n每行一个提示词，顺序和当前分镜顺序一致，\n如果某个分镜不需要导入提示词，可以留空该行，\n超出分镜的提示词会被删除，不足则只导入文本中有的提示词数据\n\n是否继续？",
+  "导入提示词失败，{error}": "导入提示词失败，{error}",
+  "导入提示词成功": "导入提示词成功",
+  "导入的提示词文件内容为空": "导入的提示词文件内容为空",
+  '导入第 {line} 行提示词失败，{error}': '导入第 {line} 行提示词失败，{error}',
+  "正在批量应用当前设置...": "正在批量应用当前设置...",
+  "将当前转视频的基础设置批量应用到所有的分镜中": "将当前转视频的基础设置批量应用到所有的分镜中",
+  "应用设置": "应用设置",
   //#endregion
 
   //#region 出图
@@ -978,6 +988,7 @@ export default {
   "AI处理文案成功": "AI处理文案成功",
   "AI处理文案失败，{error}": "AI处理文案失败，{error}",
   "检测系统当前的语言已修改，继续执行会刷新当前页面并应用当前语言，是否继续？": "检测系统当前的语言已修改，继续执行会刷新当前页面并应用当前语言，是否继续？",
+  "当前API提供商数据不存在，请检查数据是否正确": "当前API提供商数据不存在，请检查数据是否正确",
   //#endregion
 
   //#region 预设
@@ -1183,6 +1194,8 @@ export default {
   '场景分析': '场景分析',
   '推理所有提示词': '推理所有提示词',
   '推理空白分镜提示词': '推理空白分镜提示词',
+  "重置所有提示词": "重置所有提示词",
+  "导入提示词": "导入提示词",
   '生成所有图片': '生成所有图片',
   '生成未生成图片分镜': '生成未生成图片分镜',
   '生成失败图片分镜': '生成失败图片分镜',
@@ -1545,6 +1558,10 @@ export default {
   '7. 需要在外部手动选择需要的{type}数据时，请点击<strong>“{button}”</strong> 按钮进行导入到标签集中': '7. 需要在外部手动选择需要的{type}数据时，请点击<strong>“{button}”</strong> 按钮进行导入到标签集中',
   '即将开始自动推理，该操作会将之前的 {type} 数据覆盖，是否继续？': '即将开始自动推理，该操作会将之前的场景数据覆盖，是否继续？',
   '正在推理，请稍等...': '正在推理，请稍等...',
+  "通用前/后缀" : "通用前/后缀",
+  "提示词前后缀设置" : "提示词前后缀设置",
+  "通用前缀" : "通用前缀",
+  "通用后缀" : "通用后缀",
   //#endregion
 
   //#region 转视频
@@ -1602,6 +1619,51 @@ export default {
   "当前批次任务已经开启图转视频，是否直接跳转到图文转视频界面？": "当前批次任务已经开启图转视频，是否直接跳转到图文转视频界面？",
   "正在跳转到图文转视频界面...": "正在跳转到图文转视频界面...",
   "已取消跳转，你可以在转视频模块中查看该任务": "已取消跳转，你可以在转视频模块中查看该任务",
+  '是否将当前分镜的设置批量应用到其余所有分镜？\n\n同步的设置：视频类型（SD/HD），运动变化（Motion），批次数据（Batch），视频原始（Raw），首尾循环（Loop） \n\n批量应用后，其余分镜的上述基础设置会被替换为当前分镜的数据，是否继续？': '是否将当前分镜的设置批量应用到其余所有分镜？\n\n同步的设置：视频类型（SD/HD），运动变化（Motion），批次数据（Batch），视频原始（Raw），首尾循环（Loop） \n\n批量应用后，其余分镜的上述基础设置会被替换为当前分镜的数据，是否继续？',
+  "批量应用当前设置失败，{error}": "批量应用当前设置失败，{error}",
+  "批量应用当前设置成功！": "批量应用当前设置成功！",
+  "配置验证失败": "配置验证失败",
+
+  "可灵图转视频任务失败，失败信息：{error}": "可灵图转视频任务失败，失败信息：{error}",
+  "Kling图转视频任务完成！": "Kling图转视频任务完成！",
+  "未找到有效的API地址": "未找到有效的API地址",
+  "请先配置AI推理的API密钥": "请先配置AI推理的API密钥",
+  "当前分镜数据的可灵图转视频参数为空或参数校验失败，请检查": "当前分镜数据的可灵图转视频参数为空或参数校验失败，请检查",
+  "当前分镜数据的图片地址为空，请检查": "当前分镜数据的图片地址为空，请检查",
+  "视频ID数量与视频链接数量不匹配": "视频ID数量与视频链接数量不匹配",
+  "未找到有效的GPT API地址": "未找到有效的GPT API地址",
+  "未知的视频生成方式，请检查": "未知的视频生成方式，请检查",
+  "当前分镜数据的可灵视频ID为空，请检查": '当前分镜数据的可灵视频ID为空，请检查',
+  "当前分镜数据的可灵任务ID为空，请检查": "当前分镜数据的可灵任务ID为空，请检查",
+  "可灵视频延长任务完成！": "可灵视频延长任务完成！",
+  "可灵视频延长任务失败，失败信息：{error}": "可灵视频延长任务失败，失败信息：{error}",
+  "可灵图转视频任务执行中...": "可灵图转视频任务执行中...",
+  "可灵视频延长任务正在执行中...": "可灵视频延长任务正在执行中...",
+  "参考图像": "参考图像",
+  "正向文本提示，可选，不能超过2500个字符": "正向文本提示，可选，不能超过2500个字符",
+  "负向文本提示，可选，不能超过2500个字符": "负向文本提示，可选，不能超过2500个字符",
+  "自由度": "自由度",
+  '0-1之间': "0-1之间",
+  "生成视频的自由度<br/><br/><strong>值越大，模型自由度越小</strong><br/>与用户输入的提示词相关性越强<br/><br/>取值范围：<strong>[0, 1]</strong>": "生成视频的自由度<br/><br/><strong>值越大，模型自由度越小</strong><br/>与用户输入的提示词相关性越强<br/><br/>取值范围：<strong>[0, 1]</strong>",
+  "生成模式": "生成模式",
+  "生成视频的模式<br/><br/>枚举值：std，pro<br/>其中std：标准模式（标准），基础模式，性价比高<br/>其中pro：专家模式（高品质），高表现模式，生成视频质量更佳": "生成视频的模式<br/><br/>枚举值：std，pro<br/>其中std：标准模式（标准），基础模式，性价比高<br/>其中pro：专家模式（高品质），高表现模式，生成视频质量更佳",
+  "视频时长": "视频时长",
+  '生成视频时长，单位s（5秒或10秒）': '生成视频时长，单位s（5秒或10秒）',
+  "视频延长": "视频延长",
+  "选择已有的视频任务作为延长的基础": "选择已有的视频任务作为延长的基础",
+  "视频ID": "视频ID",
+  "支持通过文本、图片和视频延长生成的视频的ID（原视频不能超过3分钟）": "支持通过文本、图片和视频延长生成的视频的ID（原视频不能超过3分钟）",
+  "对应于视频ID的任务ID，通常在选择视频后自动填充": "对应于视频ID的任务ID，通常在选择视频后自动填充",
+  "是否将当前分镜的设置批量应用到其余所有分镜？\n\n同步的设置：模型名称（Model Name），生成模式（Mode），视频时长（Duration），自由度（CFG Scale） \n\n批量应用后，其余分镜的上述基础设置会被替换为当前分镜的数据，是否继续？": "是否将当前分镜的设置批量应用到其余所有分镜？\n\n同步的设置：模型名称（Model Name），生成模式（Mode），视频时长（Duration），自由度（CFG Scale） \n\n批量应用后，其余分镜的上述基础设置会被替换为当前分镜的数据，是否继续？",
+  "请选择一个已有的视频任务作为延长的基础": "请选择一个已有的视频任务作为延长的基础",
+  "父任务选择成功，视频ID已更新为: {videoId}" : "父任务选择成功，视频ID已更新为: {videoId}",
+  "高性能 (std)" : "高性能 (std)",
+  "高表现 (pro)" : "高表现 (pro)",
+  "选择Video" : "选择Video",
+  "<strong>必须</strong><br/><br/>• 支持格式：<strong>.jpg/.jpeg/.png</strong><br/>• 文件大小：<strong>不超过10MB</strong><br/>• 分辨率：<strong>不小于300*300px</strong><br/>• 宽高比：<strong>1:2.5 ~ 2.5:1</strong>之间": "<strong>必须</strong><br/><br/>• 支持格式：<strong>.jpg/.jpeg/.png</strong><br/>• 文件大小：<strong>不超过10MB</strong><br/>• 分辨率：<strong>不小于300*300px</strong><br/>• 宽高比：<strong>1:2.5 ~ 2.5:1</strong>之间",
+  "参考图像 - 尾帧控制": "参考图像 - 尾帧控制",
+  '<strong>可选</strong><br/><br/>• 支持格式：<strong>.jpg/.jpeg/.png</strong><br/>• 文件大小：<strong>不超过10MB</strong><br/>• 分辨率：<strong>不小于300*300px</strong><br/>• 宽高比：<strong>1:2.5 ~ 2.5:1</strong>之间': '<strong>可选</strong><br/><br/>• 支持格式：<strong>.jpg/.jpeg/.png</strong><br/>• 文件大小：<strong>不超过10MB</strong><br/>• 分辨率：<strong>不小于300*300px</strong><br/>• 宽高比：<strong>1:2.5 ~ 2.5:1</strong>之间',
+  //#endregion
 
   //#region  MJ
   '基本信息': '基本信息',
@@ -1721,7 +1783,6 @@ export default {
   '视频生成时长为5秒，但并非仅限于此。视频制作完成后，您可以在当前界面为选定的适配进行延长！': '视频生成时长为5秒，但并非仅限于此。视频制作完成后，您可以在当前界面为选定的适配进行延长！',
   '您可以随意将视频延长最多 4 次，每次延长 4 秒，直至达到 21 秒（即可用的最大长度）。': '您可以随意将视频延长最多 4 次，每次延长 4 秒，直至达到 21 秒（即可用的最大长度）。',
 
-  //#endregion
   //#endregion
 
   //#region  文案处理
@@ -1730,7 +1791,7 @@ export default {
   '【LaiTool】分镜大师-通用版（上下文-人物场景固定-类型推理）': '【LaiTool】分镜大师-通用版（上下文-人物场景固定-类型推理）',
   '【LaiTool】分镜大师-全面版-AI增强（上下文-人物场景固定-单帧）': '【LaiTool】分镜大师-全面版-AI增强（上下文-人物场景固定-单帧）',
   '【LaiTool】分镜大师-全能优化版（上下文-人物固定）': '【LaiTool】分镜大师-全能优化版（上下文-人物固定）',
-  "【LaiTool】分镜大师-MJ超精细化版（上下文-人物场景固定）" : "【LaiTool】分镜大师-MJ超精细化版（上下文-人物场景固定）",
+  "【LaiTool】分镜大师-MJ超精细化版（上下文-人物场景固定）": "【LaiTool】分镜大师-MJ超精细化版（上下文-人物场景固定）",
   '【LaiTool】分镜大师-SD英文版（上下文-人物场景固定-SD-英文提示词）': '【LaiTool】分镜大师-SD英文版（上下文-人物场景固定-SD-英文提示词）',
   '【LaiTool】分镜大师-单帧分镜提示词（上下文-单帧-人物自动推理）': '【LaiTool】分镜大师-单帧分镜提示词（上下文-单帧-人物自动推理）',
   "没有找到对应的AI选项，请先检查配置": "没有找到对应的AI选项，请先检查配置",

src/main/service/aiReason/aiReasonCommon.ts

@@ -10,6 +10,7 @@ import { RetryWithBackoff } from '@/define/Tools/common'
 import { Book } from '@/define/model/book/book'
 import { AiInferenceModelModel, GetAIPromptOptionByValue } from '@/define/data/aiData/aiData'
 import { t } from '@/i18n'
+import { GetAIPromptRequestBodyByValue } from '@/define/data/aiData/aiPrompt/bookStoryboardPrompt'
 
 /**
  * AI推理通用工具类
@@ -278,7 +279,15 @@ export class AiReasonCommon {
       throw new Error(t('当前模式需要提前分析或者设置角色场景数据，请先分析角色/场景数据！'))
     }
 
-    let requestBody = cloneDeep(selectInferenceModel.requestBody)
+    let requestBody: OpenAIRequest.Request | null = null
+    if (typeof selectInferenceModel.requestBody == 'string') {
+      requestBody = cloneDeep(GetAIPromptRequestBodyByValue(selectInferenceModel.requestBody as string))
+    } else {
+      requestBody = cloneDeep(selectInferenceModel.requestBody as OpenAIRequest.Request)
+    }
+
+    // 通过 requestBody 获取实际的 requestBody
+
     if (requestBody == null) {
       throw new Error(t('未找到对应的分镜预设的请求数据，请检查'))
     }

src/main/service/book/subBookHandle/bookBasicHandle.ts

@@ -3,6 +3,18 @@ import { BookTaskService } from '@/define/db/service/book/bookTaskService'
 import { OptionRealmService } from '@/define/db/service/optionService'
 import { BookService } from '@/define/db/service/book/bookService'
 import { TaskListService } from '@/define/db/service/book/taskListService'
+import { TaskModal } from '@/define/model/task'
+import { Book } from '@/define/model/book/book'
+import { getProjectPath } from '../../option/optionCommonService'
+import path from 'path'
+import { isEmpty } from 'lodash'
+import axios from 'axios'
+import { define } from '@/define/define'
+import { CheckFolderExistsOrCreate, CopyFileOrFolder } from '@/define/Tools/file'
+import { DownloadFile } from '@/define/Tools/common'
+import { MappingTaskTypeToVideoModel } from '@/define/enum/video'
+import { BookBackTaskType } from '@/define/enum/bookEnum'
+import { t } from '@/i18n'
 
 export class BookBasicHandle {
   bookTaskDetailService!: BookTaskDetailService
@@ -34,10 +46,164 @@ export class BookBasicHandle {
     }
   }
 
+  /**
+   * 检查所有的服务是否都已初始化
+   * @returns 
+   */
+  CheckInit() {
+    if (this.bookTaskDetailService
+      && this.bookTaskService
+      && this.optionRealmService
+      && this.bookService
+      && this.taskListService) {
+      return true
+    }
+    return false
+  }
+
+  /** 执行事务的方法 */
   async transaction(callback: (realm: any) => void) {
-    await this.InitBookBasicHandle()
+    this.CheckInit() || await this.InitBookBasicHandle()
     this.bookService.transaction(() => {
       callback(this.bookService.realm)
     })
   }
+
+  /**
+   * 下载视频文件并处理路径映射
+   * 
+   * 此方法负责从远程URL下载视频文件到本地，并处理文件的存储路径、转存服务等。
+   * 支持多种视频来源的处理，包括MidJourney、可灵等不同平台的视频文件。
+   * 会自动处理文件转存（除MJ官方CDN和可灵视频外），并更新数据库中的路径信息。
+   * 
+   * @param {string[]} videoUrls - 需要下载的视频URL列表
+   * @param {TaskModal.Task} task - 当前执行的任务对象，包含任务类型等信息
+   * @param {Book.SelectBookTaskDetail} bookTaskDetail - 小说任务详情对象，包含分镜信息
+   * @param {string} preffix - 文件名前缀，用于区分不同来源的视频文件
+   * 
+   * @returns {Promise<{outVideoPath: string, subVideoPath: string[]}>} 返回下载结果
+   * - outVideoPath: 主输出视频的本地路径（第一个视频的副本）
+   * - subVideoPath: 所有子视频的路径信息数组（JSON字符串格式）
+   * 
+   * @throws {Error} 当服务未初始化时
+   * @throws {Error} 当文件下载失败时
+   * @throws {Error} 当数据库操作失败时
+   * 
+   * @example
+   * ```typescript
+   * const result = await this.DownloadVideoUrls(
+   *   ['http://example.com/video1.mp4', 'http://example.com/video2.mp4'],
+   *   task,
+   *   bookTaskDetail,
+   *   'MJ'
+   * );
+   * console.log('主视频路径:', result.outVideoPath);
+   * console.log('所有视频路径:', result.subVideoPath);
+   * ```
+   * 
+   * @description
+   * 处理流程：
+   * 1. 初始化服务并获取项目路径
+   * 2. 遍历每个视频URL进行下载
+   * 3. 根据任务类型决定是否使用转存服务
+   * 4. 创建本地存储目录并下载文件
+   * 5. 将第一个视频复制为主输出视频
+   * 6. 更新数据库中的路径信息
+   * 
+   * @note
+   * - MidJourney官方CDN (cdn.midjourney.com) 的视频不支持转存
+   * - 可灵视频 (KLING_VIDEO, KLING_VIDEO_EXTEND) 不使用转存服务
+   * - 转存服务需要全局machineId配置
+   * - 视频文件按时间戳和索引命名以避免冲突
+   */
+  async DownloadVideoUrls(videoUrls: string[], task: TaskModal.Task, bookTaskDetail: Book.SelectBookTaskDetail, preffix: string, videoIds?: string[]): Promise<{ outVideoPath: string, subVideoPath: string[] }> {
+    this.CheckInit() || await this.InitBookBasicHandle()
+
+    if (videoIds != undefined && videoIds.length != videoUrls.length) {
+      throw new Error(t("视频ID数量与视频链接数量不匹配"))
+    }
+
+    let bookTask = await this.bookTaskService.GetBookTaskDataById(
+      bookTaskDetail.bookTaskId as string,
+      true
+    )
+
+    let tempVideoUrls = bookTaskDetail.subVideoPath || []
+    let newVideoUrls: string[] = []
+    let outVideoPath: string = ''
+
+    const project_path = await getProjectPath()
+
+    // 开始下载所有视频
+    for (let i = 0; i < videoUrls.length; i++) {
+      const videoUrl = videoUrls[i]
+      // 处理文件地址和下载
+      let videoPath = path.join(
+        bookTask.imageFolder as string,
+        `video/subVideo/${bookTaskDetail.name}/${new Date().getTime()}_${i}.mp4`
+      )
+
+      let remoteUrl = videoUrl
+
+      // 开始处理下载 mj 官方的图片不支持转存
+      if (global.machineId
+        && !isEmpty(global.machineId)
+        && !videoUrl.startsWith('https://cdn.midjourney.com')
+        && task.type != BookBackTaskType.KLING_VIDEO
+        && task.type != BookBackTaskType.KLING_VIDEO_EXTEND
+      ) {
+        // 转存一下视频文件
+        // 获取当前url的文件名
+        let fileName = preffix + "_" + path.basename(videoUrl)
+        let transferRes = await axios.post(define.lms_url + `/lms/FileUpload/UrlUpload/${global.machineId}`, {
+          url: videoUrl,
+          fileName: fileName
+        })
+        if (transferRes.status == 200 && transferRes.data.code == 1) {
+          remoteUrl = transferRes.data.data.url
+        }
+      }
+
+      if (isEmpty(remoteUrl)) {
+        remoteUrl = videoUrl
+      }
+
+      await CheckFolderExistsOrCreate(path.dirname(videoPath))
+      await DownloadFile(remoteUrl, videoPath)
+
+      // 处理返回数据信息
+      // 开始修改信息
+      // 将信息添加到里面
+      let a = {
+        localPath: path.relative(project_path, videoPath),
+        remotePath: remoteUrl,
+        taskId: bookTaskDetail.videoMessage?.taskId,
+        videoId: videoIds != undefined && videoIds[i] ? videoIds[i] : "",
+        index: i,
+        type: MappingTaskTypeToVideoModel(task.type as string)
+      }
+      newVideoUrls.push(JSON.stringify(a))
+      if (i == 0) {
+        outVideoPath = path.join(
+          bookTask.imageFolder as string,
+          'video',
+          bookTaskDetail.name + path.extname(videoPath)
+        )
+        await CopyFileOrFolder(videoPath, outVideoPath as string)
+      }
+    }
+
+    // 开始处理数据
+    // 将原有的视频路径合并到新数组中
+    newVideoUrls.push(...tempVideoUrls)
+    await this.bookTaskDetailService.ModifyBookTaskDetailById(bookTaskDetail.id as string, {
+      subVideoPath: newVideoUrls,
+      generateVideoPath: outVideoPath != '' ? outVideoPath : ''
+    })
+
+    return {
+      outVideoPath: outVideoPath,
+      subVideoPath: newVideoUrls
+    }
+  }
 }

src/main/service/book/subBookHandle/bookVideoServiceHandle.ts

@@ -3,7 +3,9 @@ import { BookBasicHandle } from './bookBasicHandle'
 import { Book } from '@/define/model/book/book'
 import {
   ImageToVideoModels,
+  KlingDuration,
   KlingMode,
+  KlingModelName,
   MJVideoBatchSize,
   MJVideoMotion,
   MJVideoType,
@@ -23,6 +25,7 @@ import { getProjectPath } from '../../option/optionCommonService'
 import { TaskModal } from '@/define/model/task'
 import { BookBackTaskStatus, BookBackTaskType, BookTaskStatus } from '@/define/enum/bookEnum'
 import { VideoHandle } from '@/main/service/video/index'
+import { ResponseMessageType } from '@/define/enum/softwareEnum'
 
 export class BookVideoServiceHandle extends BookBasicHandle {
   constructor() {
@@ -190,7 +193,7 @@ export class BookVideoServiceHandle extends BookBasicHandle {
         )
       let gptUrl = GetApiDefineDataById(inferenceSetting.apiProvider)?.gpt_url
       if (gptUrl == null || isEmpty(gptUrl)) {
-        throw new Error()
+        throw new Error(t('未找到有效的GPT API地址'))
       }
       // 开始设置默认设置
 
@@ -219,13 +222,15 @@ export class BookVideoServiceHandle extends BookBasicHandle {
       }
 
       let klingOptions: BookTaskDetail.klingOptions = {
-        model: 'kling-v1',
+        model_name: KlingModelName.KLING_V2_1,
         image: outImage,
         image_tail: '',
         prompt: '',
         negative_prompt: '',
         mode: KlingMode.STD,
-        duration: RunwaySeconds.FIVE
+        duration: KlingDuration.FIVE,
+        video_id: '',
+        cfg_scale: 0.5
       }
 
       let mjVideoOptions: BookTaskDetail.MjVideoOptions = {
@@ -305,14 +310,33 @@ export class BookVideoServiceHandle extends BookBasicHandle {
     try {
       // 更具不同的方式调用不同的处理方法
       const videoHandle = new VideoHandle()
+      let res;
       switch (task.type) {
         case BookBackTaskType.MJ_VIDEO:
-          return await videoHandle.MJImageToVideo(task)
+          res = await videoHandle.MJImageToVideo(task)
+          break
         case BookBackTaskType.MJ_VIDEO_EXTEND:
-          return await videoHandle.MJVideoExtendToVideo(task)
+          res = await videoHandle.MJVideoExtendToVideo(task)
+          break
+        case BookBackTaskType.KLING_VIDEO:
+          res = await videoHandle.KlingImageToVideo(task)
+          break
+        case BookBackTaskType.KLING_VIDEO_EXTEND : 
+          res = await videoHandle.KlingVideoExtend(task)
+          break
         default:
-          throw new Error('未知的视频生成方式，请检查')
+          throw new Error(t('未知的视频生成方式，请检查'))
       }
+      let newValue = await this.bookTaskDetailService.GetBookTaskDetailDataById(task.bookTaskDetailId as string, true)
+      SendReturnMessage(
+        {
+          code: 1,
+          id: task.bookTaskDetailId as string,
+          message: t('图转视频任务执行完成。'),
+          type: ResponseMessageType.VIDEO_SUCESS,
+          data: JSON.stringify(newValue)
+        }, task.messageName as string)
+      return res;
     } catch (error) {
       // 统一处理 报错信息
       let message = t("图转视频失败，失败信息如下：{error}", { error: (error as Error).message })

src/main/service/option/optionCommonService.ts

@@ -3,6 +3,7 @@ import { OptionKeyName } from '@/define/enum/option'
 import { optionSerialization } from './optionSerialization'
 import { SettingModal } from '@/define/model/setting'
 import { t } from '@/i18n'
+import { GetApiDefineDataById } from '@/define/data/apiData'
 
 /**
  * 获取当前项目的路径
@@ -33,3 +34,40 @@ export async function getGeneralSetting() {
   ) as SettingModal.GeneralSettings
   return generalSetting
 }
+
+/**
+ * 获取AI推理设置（包含API提供商信息）
+ * 
+ * 此方法从数据库中获取AI推理相关的配置设置，并自动关联对应的API提供商详细信息。
+ * 返回的数据结构包含了完整的推理配置和API提供商配置，方便在业务逻辑中直接使用。
+ * 
+ * @returns {Promise<SettingModal.InferenceAISettingAndProvider>} 包含推理设置和API提供商信息的完整配置对象
+ * @throws {Error} 当指定的API提供商ID在系统中不存在时抛出错误
+ * 
+ * @example
+ * ```typescript
+ * const inferenceConfig = await getInferenceSetting();
+ * console.log(inferenceConfig.inferenceModel); // AI推理模型名称
+ * console.log(inferenceConfig.apiProviderItem.name); // API提供商名称
+ * ```
+ */
+export async function getInferenceSetting(): Promise<SettingModal.InferenceAISettingAndProvider> {
+  const optionRealmService = await OptionRealmService.getInstance()
+  let res = optionRealmService.GetOptionByKey(OptionKeyName.InferenceAI.InferenceSetting)
+  let aiReasonSetting = optionSerialization<SettingModal.InferenceAISettings>(
+    res,
+    t('设置 -> 推理设置')
+  )
+
+  // 获取对应的provider
+  let apiProviderItem = GetApiDefineDataById(aiReasonSetting.apiProvider);
+  if (apiProviderItem == null) {
+    throw new Error(t('当前API提供商数据不存在，请检查数据是否正确'))
+  }
+  let result = {
+    ...aiReasonSetting,
+    apiProviderItem
+  }
+
+  return result
+}

src/main/service/task/taskManage.ts

@@ -436,7 +436,8 @@ export class TaskManager {
 
         // case BookBackTaskType.RUNWAY_VIDEO:
         // case BookBackTaskType.LUMA_VIDEO:
-        // case BookBackTaskType.KLING_VIDEO:
+        case BookBackTaskType.KLING_VIDEO:
+        case BookBackTaskType.KLING_VIDEO_EXTEND:
         case BookBackTaskType.MJ_VIDEO:
         case BookBackTaskType.MJ_VIDEO_EXTEND:
           this.AddImageToVideo(task)

src/main/service/translate/translateCommon.ts

@@ -50,7 +50,7 @@ export class TranslateCommon {
 
     let apiProvider = GetApiDefineDataById(aiSetting.apiProvider)
     if (apiProvider.gpt_url == null || isEmpty(apiProvider.gpt_url)) {
-      throw new Error('未找到有效的GPT API地址')
+      throw new Error(t('未找到有效的GPT API地址'))
     }
     this.translationBusiness = apiProvider.gpt_url
     this.translationAppId = aiSetting.translationModel

src/main/service/video/index.ts

@@ -1,11 +1,14 @@
 import { TaskModal } from '@/define/model/task'
 import { MJVideoService } from './mjVideo'
+import { KlingVideoService } from './klingVideo'
 export class VideoHandle {
   mjVideoService: MJVideoService
+  klingVideoService: KlingVideoService
   // 这里可以添加 VideoHandle 特有的方法
   constructor() {
     // mixin 装饰器会处理初始化
     this.mjVideoService = new MJVideoService()
+    this.klingVideoService = new KlingVideoService()
   }
 
   /** MJ图片转视频处理方法 将指定的图片通过Midjourney API转换为视频 */
@@ -17,4 +20,13 @@ export class VideoHandle {
   MJVideoExtendToVideo(task: TaskModal.Task) {
     return this.mjVideoService.MJVideoExtendToVideo(task)
   }
+
+  /** 将静态图片通过可灵AI模型转换为动态视频的核心方法。 支持多种参数配置，包括模型选择、提示词、负面提示词、持续时间等。 */
+  KlingImageToVideo(task: TaskModal.Task) {
+    return this.klingVideoService.KlingImageToVideo(task)
+  }
+
+  KlingVideoExtend(task: TaskModal.Task) {
+    return this.klingVideoService.KlingVideoExtend(task)
+  }
 }

src/main/service/video/klingVideo.ts

@@ -0,0 +1,748 @@
+import { TaskModal } from "@/define/model/task";
+import { BookBasicHandle } from "../book/subBookHandle/bookBasicHandle";
+import { getInferenceSetting } from "../option/optionCommonService";
+import { t } from "@/i18n";
+import { cloneDeep, isEmpty } from "lodash";
+import { SettingModal } from "@/define/model/setting";
+import { ValidateJson } from "@/define/Tools/validate";
+import { BookTaskDetail } from "@/define/model/book/bookTaskDetail";
+import { KlingDuration, KlingMode, KlingModelName, VideoStatus } from "@/define/enum/video";
+import { GetImageBase64 } from "@/define/Tools/image";
+import axios from "axios";
+import { console } from "inspector";
+import { SendReturnMessage, successMessage } from "@/public/generalTools";
+import { ResponseMessageType } from "@/define/enum/softwareEnum";
+import { GeneralResponse } from "@/define/model/generalResponse";
+import { Book } from "@/define/model/book/book";
+import { BookBackTaskStatus, BookBackTaskType, BookTaskStatus } from "@/define/enum/bookEnum";
+
+export class KlingVideoService extends BookBasicHandle {
+  inferenceSetting!: SettingModal.InferenceAISettingAndProvider
+  constructor() {
+    super();
+  }
+
+  private async InitApiSetting() {
+    // 加载推理设置中的数据
+    const inferenceSetting = await getInferenceSetting();
+    this.inferenceSetting = inferenceSetting;
+    // 判断一些数据是不是存在
+    if (isEmpty(this.inferenceSetting.apiProviderItem.base_url)) {
+      throw new Error(t('未找到有效的API地址'));
+    }
+
+    if (this.inferenceSetting.apiToken == null || isEmpty(this.inferenceSetting.apiToken)) {
+      throw new Error(t('请先配置AI推理的API密钥'));
+    }
+
+  }
+
+  //#region KlingImageToVideo
+  /**
+   * 可灵图转视频服务
+   * 
+   * 将静态图片通过可灵AI模型转换为动态视频的核心方法。
+   * 支持多种参数配置，包括模型选择、提示词、负面提示词、持续时间等。
+   * 
+   * @param {TaskModal.Task} task - 任务对象，包含小说批次任务的详细信息
+   * @returns {Promise<any>} 返回成功消息或抛出错误
+   * 
+   * @throws {Error} 当API地址未配置时
+   * @throws {Error} 当API密钥未配置时  
+   * @throws {Error} 当分镜数据的视频配置为空时
+   * @throws {Error} 当可灵参数校验失败时
+   * @throws {Error} 当图片地址为空时
+   * 
+   * @example
+   * ```typescript
+   * const klingService = new KlingVideoService();
+   * await klingService.KlingImageToVideo(task);
+   * ```
+   */
+  async KlingImageToVideo(task: TaskModal.Task): Promise<GeneralResponse.SuccessItem> {
+    try {
+      // 初始化基础句柄和API设置
+      await this.InitBookBasicHandle();
+      await this.InitApiSetting();
+
+      let { klingOption, videoMessage, bookTaskDetail } = await this.GetKlingOptions(task.bookTaskDetailId as string)
+
+      let imageUrl = videoMessage.imageUrl?.trim() || klingOption.image?.trim()
+      if (isEmpty(imageUrl)) {
+        throw new Error(t("当前分镜数据的图片地址为空，请检查"))
+      }
+
+      let image_tail = klingOption.image_tail?.trim()
+
+      let model_name = klingOption.model_name?.trim() || KlingModelName.KLING_V2_1;
+
+      let prompt = klingOption.prompt?.trim();
+      let negative_prompt = klingOption.negative_prompt?.trim();
+      let cfg_scale = klingOption.cfg_scale || 0.5;
+      let mode = klingOption.mode?.trim() || KlingMode.STD;
+      let duration = klingOption.duration ?? KlingDuration.FIVE;
+
+      let body: BookTaskDetail.klingOptions = {
+        model_name: model_name as KlingModelName,
+        image: await GetImageBase64(imageUrl as string, true),
+      }
+
+      if (imageUrl.startsWith('http')) {
+        body.image = imageUrl
+      } else {
+        body.image = await GetImageBase64(imageUrl as string, true)
+      }
+
+      if (!isEmpty(image_tail)) {
+        if (image_tail?.startsWith('http')) {
+          body.image_tail = image_tail
+        } else {
+          body.image_tail = await GetImageBase64(image_tail as string, true)
+        }
+      }
+      if (!isEmpty(prompt)) {
+        body.prompt = prompt
+      }
+      if (!isEmpty(negative_prompt)) {
+        body.negative_prompt = negative_prompt
+      }
+      if (cfg_scale != null) {
+        body.cfg_scale = cfg_scale
+      }
+      if (mode != null && !isEmpty(mode)) {
+        body.mode = mode as KlingMode
+      }
+      if (duration != null) {
+        body.duration = duration
+      }
+
+      let url = this.inferenceSetting.apiProviderItem.base_url + '/kling/v1/videos/image2video'
+      let res = await axios.post(url, body, {
+        headers: {
+          Authorization: `Bearer ${this.inferenceSetting.apiToken}`,
+          'Content-Type': 'application/json'
+        }
+      })
+      console.log("Kling video res", res.data)
+
+      let resData = res.data
+
+      let taskId = resData.data.task_id
+
+      // 修改Task, 将数据写入
+      this.taskListService.UpdateBackTaskData(task.id as string, {
+        taskId: taskId as string,
+        taskMessage: JSON.stringify(resData)
+      })
+
+      // 修改videoMessage
+      videoMessage.taskId = taskId
+      videoMessage.status = VideoStatus.SUBMITTED
+      videoMessage.messageData = JSON.stringify(resData)
+      videoMessage.msg = ''
+      delete videoMessage.imageUrl // 不要修改原本的图片地址
+
+      this.bookTaskDetailService.UpdateBookTaskDetailVideoMessage(
+        task.bookTaskDetailId as string,
+        videoMessage
+      )
+
+      // 添加任务成功 返回前端任务事件
+      SendReturnMessage(
+        {
+          code: 1,
+          id: task.bookTaskDetailId as string,
+          message: t('已成功提交{type}图转视频任务，任务ID：{taskId}', { type: t("可灵"), taskId: taskId }),
+          type: ResponseMessageType.KLING_VIDEO,
+          data: JSON.stringify(videoMessage)
+        },
+        task.messageName as string
+      )
+      await this.FecthKlingImageToVideoResult(bookTaskDetail, task, taskId, false)
+      return successMessage(
+        t('Kling图转视频任务完成！'),
+        'MJVideoService_MJImageToVideo'
+      )
+
+    } catch (error) {
+      throw new Error(t('可灵图转视频任务失败，失败信息：{error}', { error: (error as Error).message }));
+    }
+  }
+
+  //#endregion
+
+  //#region KlingVideoExtend
+
+  /**
+   * 可灵视频延长服务
+   * 
+   * 对已生成的视频进行延长处理，通过可灵AI模型为现有视频添加更多内容。
+   * 支持自定义提示词、负面提示词和CFG Scale参数，实现精确的视频延长控制。
+   * 
+   * @param {TaskModal.Task} task - 任务对象，包含小说批次任务的详细信息
+   * @returns {Promise<GeneralResponse.SuccessItem>} 返回成功消息或抛出错误
+   * 
+   * @throws {Error} 当API地址未配置时
+   * @throws {Error} 当API密钥未配置时
+   * @throws {Error} 当视频ID为空时
+   * @throws {Error} 当任务ID为空时
+   * @throws {Error} 当配置数据无效时
+   * 
+   * @description
+   * 视频延长处理流程：
+   * 1. 初始化基础句柄和API设置
+   * 2. 获取并验证可灵配置选项（包含视频ID、任务ID等）
+   * 3. 验证必需参数（video_id、task_id）的存在性
+   * 4. 构建API请求体，包含延长所需的参数
+   * 5. 调用可灵视频延长API接口
+   * 6. 更新任务状态和视频消息数据
+   * 7. 发送前端任务提交成功通知
+   * 8. 启动轮询机制跟踪任务执行状态
+   * 
+   * @note
+   * - 视频延长基于已存在的视频内容进行扩展
+   * - 需要提供原始视频的video_id和task_id
+   * - 支持自定义提示词控制延长内容的风格
+   * - 延长后的视频会通过轮询机制获取结果
+   * - 所有参数都会在前端界面进行配置和验证
+   * 
+   * @example
+   * ```typescript
+   * const klingService = new KlingVideoService();
+   * const result = await klingService.KlingVideoExtend(task);
+   * console.log('视频延长任务已提交');
+   * ```
+   */
+  async KlingVideoExtend(task: TaskModal.Task): Promise<GeneralResponse.SuccessItem> {
+    try {
+      // 初始化基础句柄和API设置
+      await this.InitBookBasicHandle();
+      await this.InitApiSetting();
+
+      let { klingOption, videoMessage, bookTaskDetail } = await this.GetKlingOptions(task.bookTaskDetailId as string)
+
+      let video_id = klingOption.video_id?.trim()
+      if (isEmpty(video_id)) {
+        throw new Error(t("当前分镜数据的可灵视频ID为空，请检查"))
+      }
+      let task_id = klingOption.task_id?.trim()
+      if (isEmpty(task_id)) {
+        throw new Error(t("当前分镜数据的可灵任务ID为空，请检查"))
+      }
+
+      let prompt = klingOption.prompt?.trim();
+      let negative_prompt = klingOption.negative_prompt?.trim();
+      let cfg_scale = klingOption.cfg_scale || 0.5;
+
+      let body: any = {
+        video_id: video_id as string,
+        task_id: task_id as string
+      }
+      if (!isEmpty(prompt)) {
+        body.prompt = prompt
+      }
+      if (!isEmpty(negative_prompt)) {
+        body.negative_prompt = negative_prompt
+      }
+      if (cfg_scale != null) {
+        body.cfg_scale = cfg_scale
+      }
+      // 开始做请求
+      let url = this.inferenceSetting.apiProviderItem.base_url + '/kling/v1/videos/video-extend';
+      let res = await axios.post(url, body, {
+        headers: {
+          Authorization: `Bearer ${this.inferenceSetting.apiToken}`,
+          'Content-Type': 'application/json'
+        }
+      })
+
+      console.log("Kling video extend res", res.data)
+
+      let resData = res.data
+
+      let taskId = resData.data.task_id
+
+      // 修改Task, 将数据写入
+      this.taskListService.UpdateBackTaskData(task.id as string, {
+        taskId: taskId as string,
+        taskMessage: JSON.stringify(resData)
+      })
+
+      // 修改videoMessage
+      videoMessage.taskId = taskId
+      videoMessage.status = VideoStatus.SUBMITTED
+      videoMessage.messageData = JSON.stringify(resData)
+      videoMessage.msg = ''
+      delete videoMessage.imageUrl // 不要修改原本的图片地址
+
+      this.bookTaskDetailService.UpdateBookTaskDetailVideoMessage(
+        task.bookTaskDetailId as string,
+        videoMessage
+      )
+
+      // 添加任务成功 返回前端任务事件
+      SendReturnMessage(
+        {
+          code: 1,
+          id: task.bookTaskDetailId as string,
+          message: t('已成功提交{type}图转视频任务，任务ID：{taskId}', { type: t("可灵"), taskId: taskId }),
+          type: ResponseMessageType.KLING_VIDEO_EXTEND,
+          data: JSON.stringify(videoMessage)
+        },
+        task.messageName as string
+      )
+      await this.FecthKlingImageToVideoResult(bookTaskDetail, task, taskId, false)
+      return successMessage(
+        t('可灵视频延长任务完成！'),
+        'MJVideoService_MJImageToVideo'
+      )
+    } catch (error) {
+      throw new Error(t('可灵视频延长任务失败，失败信息：{error}', { error: (error as Error).message }));
+    }
+  }
+
+  //#endregion
+
+
+  //#region FecthKlingImageToVideoResult
+  /**
+   * 获取可灵图转视频任务结果
+   * 
+   * 通过轮询机制持续检查可灵视频生成任务的执行状态，直到任务完成（成功或失败）。
+   * 根据不同的任务状态调用相应的处理方法，实现任务状态的实时跟踪和处理。
+   * 
+   * @param {Book.SelectBookTaskDetail} bookTaskDetail - 小说任务详情对象，包含分镜和视频配置信息
+   * @param {TaskModal.Task} task - 当前执行的任务对象，包含任务类型和消息通道信息
+   * @param {string} taskId - 可灵任务的唯一标识符，用于查询任务状态
+   * @param {boolean} useTransfer - 是否使用转存服务的标志位（当前未使用，保留参数）
+   * 
+   * @throws {Error} 当遇到未知任务状态时抛出错误
+   * @throws {Error} 当API调用失败时抛出错误
+   * 
+   * @description
+   * 轮询处理流程：
+   * 1. 构建查询URL并发送GET请求获取任务状态
+   * 2. 解析返回的任务状态信息
+   * 3. 根据状态值进行分发处理：
+   *    - "submitted" | "processing": 调用KlingTaskProcessing处理中间状态
+   *    - "succeed": 调用KlingTaskSuccessed处理成功状态并结束轮询
+   *    - "failed": 调用KlingTaskFailed处理失败状态并结束轮询
+   *    - 其他状态: 抛出未知状态错误
+   * 4. 对于中间状态，等待20秒后继续下一次轮询
+   * 5. 对于终态（成功/失败），退出轮询循环
+   * 
+   * @note
+   * - 这是一个无限循环的轮询方法，只有在任务完成时才会退出
+   * - 每次轮询间隔为20秒（在KlingTaskProcessing中实现）
+   * - 支持图转视频和视频延长两种任务类型的状态跟踪
+   * - 所有状态变更都会同步到数据库并通知前端
+   * 
+   * @example
+   * ```typescript
+   * await this.FecthKlingImageToVideoResult(
+   *   bookTaskDetail, 
+   *   task, 
+   *   'kling_task_123456', 
+   *   false
+   * );
+   * ```
+   */
+  async FecthKlingImageToVideoResult(
+    bookTaskDetail: Book.SelectBookTaskDetail,
+    task: TaskModal.Task,
+    taskId: string,
+    useTransfer: boolean = false) {
+    console.log(useTransfer)
+    while (true) {
+      let fetchUrl = this.inferenceSetting.apiProviderItem.base_url + '/kling/v1/videos/image2video/' + taskId;
+
+      let res = await axios.get(fetchUrl, {
+        headers: {
+          Authorization: `Bearer ${this.inferenceSetting.apiToken}`,
+          'Content-Type': 'application/json'
+        }
+      });
+
+      let resData = res.data.data;
+
+      let status = resData.task_status;
+      if (status === "submitted" || status === "processing") {
+        await this.KlingTaskProcessing(bookTaskDetail, task, taskId, resData)
+      } else if (status === "succeed") {
+        await this.KlingTaskSuccessed(bookTaskDetail, task, taskId, resData)
+        break
+      } else if (status === "failed") {
+        // 任务失败
+        await this.KlingTaskFailed(bookTaskDetail, task, taskId, resData)
+        break
+      } else {
+        // 未知状态
+        throw new Error(t("未知状态"));
+      }
+    }
+  }
+
+  //#endregion
+
+
+  //#region fetck video extend res
+
+  /**
+   * 获取可灵视频延长任务结果
+   * 
+   * 通过轮询机制持续检查可灵视频延长任务的执行状态，直到任务完成（成功或失败）。
+   * 专门用于视频延长任务的状态跟踪，与图转视频任务使用不同的API端点。
+   * 
+   * @param {Book.SelectBookTaskDetail} bookTaskDetail - 小说任务详情对象，包含分镜和视频配置信息
+   * @param {TaskModal.Task} task - 当前执行的任务对象，包含任务类型和消息通道信息
+   * @param {string} taskId - 可灵视频延长任务的唯一标识符，用于查询任务状态
+   * @param {boolean} useTransfer - 是否使用转存服务的标志位（当前未使用，保留参数）
+   * 
+   * @throws {Error} 当遇到未知任务状态时抛出错误
+   * @throws {Error} 当API调用失败时抛出错误
+   * 
+   * @description
+   * 视频延长任务轮询处理流程：
+   * 1. 构建视频延长任务查询URL（/kling/v1/videos/video-extend/{taskId}）
+   * 2. 发送GET请求获取任务状态信息
+   * 3. 解析返回的任务状态数据
+   * 4. 根据状态值进行分发处理：
+   *    - "submitted" | "processing": 调用KlingTaskProcessing处理中间状态
+   *    - "succeed": 调用KlingTaskSuccessed处理成功状态并结束轮询
+   *    - "failed": 调用KlingTaskFailed处理失败状态并结束轮询
+   *    - 其他状态: 抛出未知状态错误
+   * 5. 对于中间状态，等待20秒后继续下一次轮询
+   * 6. 对于终态（成功/失败），退出轮询循环
+   * 
+   * @note
+   * - 这是一个无限循环的轮询方法，只有在任务完成时才会退出
+   * - 每次轮询间隔为20秒（在KlingTaskProcessing中实现）
+   * - 专门用于视频延长任务，与图转视频任务使用不同的API路径
+   * - 所有状态变更都会同步到数据库并通知前端
+   * - 支持视频延长任务的完整生命周期管理
+   * 
+   * @example
+   * ```typescript
+   * await this.FecthKlingVideoExtendResult(
+   *   bookTaskDetail,
+   *   task,
+   *   'kling_extend_task_123456',
+   *   false
+   * );
+   * ```
+   * 
+   * @see KlingTaskProcessing - 处理中间状态
+   * @see KlingTaskSuccessed - 处理成功状态
+   * @see KlingTaskFailed - 处理失败状态
+   */
+  async FecthKlingVideoExtendResult(
+    bookTaskDetail: Book.SelectBookTaskDetail,
+    task: TaskModal.Task,
+    taskId: string,
+    useTransfer: boolean = false
+  ) {
+    console.log(useTransfer)
+    while (true) {
+      let fetchUrl = this.inferenceSetting.apiProviderItem.base_url + '/kling/v1/videos/video-extend/' + taskId;
+
+      let res = await axios.get(fetchUrl, {
+        headers: {
+          Authorization: `Bearer ${this.inferenceSetting.apiToken}`,
+          'Content-Type': 'application/json'
+        }
+      });
+
+      let resData = res.data.data;
+
+      let status = resData.task_status;
+      if (status === "submitted" || status === "processing") {
+        await this.KlingTaskProcessing(bookTaskDetail, task, taskId, resData)
+      } else if (status === "succeed") {
+        await this.KlingTaskSuccessed(bookTaskDetail, task, taskId, resData)
+        break
+      } else if (status === "failed") {
+        // 任务失败
+        await this.KlingTaskFailed(bookTaskDetail, task, taskId, resData)
+        break
+      } else {
+        // 未知状态
+        throw new Error(t("未知状态"));
+      }
+    }
+  }
+
+  //#endregion
+
+  //#region get kling option
+
+  /**
+   * 获取可灵视频配置选项
+   * 
+   * 从小说任务详情中提取和解析可灵视频生成相关的配置参数。
+   * 包括验证配置数据的完整性和有效性，确保后续视频生成过程能够正常进行。
+   * 
+   * @param {string} bookTaskDetailId - 小说任务详情的唯一标识符
+   * 
+   * @returns {Promise<{klingOption: BookTaskDetail.klingOptions, videoMessage: BookTaskDetail.VideoMessage}>}
+   * 返回包含可灵配置选项和视频消息的对象
+   * - klingOption: 解析后的可灵视频配置参数
+   * - videoMessage: 完整的视频消息配置对象
+   * 
+   * @throws {Error} 当小说任务详情不存在时
+   * @throws {Error} 当视频配置信息为空时
+   * @throws {Error} 当可灵参数JSON格式无效时
+   * 
+   * @description
+   * 配置获取流程：
+   * 1. 根据任务详情ID查询数据库获取完整数据
+   * 2. 验证视频消息配置是否存在
+   * 3. 验证可灵选项字符串是否为有效的JSON格式
+   * 4. 解析JSON字符串为可灵配置对象
+   * 5. 返回配置选项和视频消息的组合对象
+   * 
+   * @note
+   * - 这个方法主要用于配置验证和数据准备阶段
+   * - 确保了可灵视频生成所需的所有参数都已正确配置
+   * - 为后续的视频生成API调用提供完整的参数基础
+   * - 支持灵活的配置参数组合和验证
+   * 
+   * @example
+   * ```typescript
+   * const { klingOption, videoMessage } = await klingService.GetKlingOptions(
+   *   'task_detail_123456'
+   * );
+   * console.log('模型名称:', klingOption.model_name);
+   * console.log('视频状态:', videoMessage.status);
+   * ```
+   */
+  async GetKlingOptions(bookTaskDetailId: string): Promise<{ bookTaskDetail: Book.SelectBookTaskDetail, klingOption: BookTaskDetail.klingOptions, videoMessage: BookTaskDetail.VideoMessage }> {
+    // 开始处理小说数据
+    let bookTaskDetail = await this.bookTaskDetailService.GetBookTaskDetailDataById(bookTaskDetailId, true);
+
+
+    // 获取视频配置信息
+    let videoMessage = bookTaskDetail.videoMessage
+    if (videoMessage == null || videoMessage == undefined) {
+      throw new Error(t("小说批次任务的分镜数据的转视频配置为空，请检查"))
+    }
+
+    // 获取 MJ Video 的options
+    let klingOptionsString = bookTaskDetail.videoMessage?.klingOptions as string
+    if (!ValidateJson(klingOptionsString)) {
+      throw new Error(t("当前分镜数据的可灵图转视频参数为空或参数校验失败，请检查"))
+    }
+
+    let klingOptions = JSON.parse(klingOptionsString) as BookTaskDetail.klingOptions
+    return { bookTaskDetail: bookTaskDetail, klingOption: klingOptions, videoMessage: videoMessage }
+  }
+
+  //#endregion
+
+  //#region Kling Task Status Handle
+
+  /**
+   * 处理可灵任务失败状态
+   * 
+   * 当可灵视频生成任务失败时，更新相关数据状态并通知前端。
+   * 包括更新视频消息状态、任务状态，并发送失败通知消息。
+   * 
+   * @param {Book.SelectBookTaskDetail} bookTaskDetail - 小说任务详情对象
+   * @param {TaskModal.Task} task - 当前执行的任务对象
+   * @param {string} taskId - 可灵任务ID
+   * @param {any} resData - 从可灵API返回的响应数据，包含失败信息
+   * 
+   * @throws {Error} 抛出包含失败原因的错误信息
+   * 
+   * @description
+   * 处理流程：
+   * 1. 复制并更新视频消息状态为失败
+   * 2. 记录失败原因和任务数据
+   * 3. 更新数据库中的视频消息和任务状态
+   * 4. 根据任务类型发送相应的失败通知
+   * 5. 抛出包含具体失败信息的错误
+   */
+  async KlingTaskFailed(bookTaskDetail: Book.SelectBookTaskDetail,
+    task: TaskModal.Task,
+    taskId: string,
+    resData: any) {
+    // 修改小说分镜的 videoMessage
+    let videoMessage = cloneDeep(bookTaskDetail.videoMessage) ?? {}
+
+    videoMessage.status = VideoStatus.FAIL
+    videoMessage.msg = resData.task_status_msg
+    videoMessage.taskId = taskId
+    videoMessage.messageData = JSON.stringify(resData)
+    delete videoMessage.imageUrl
+
+    // 修改 videoMessage数据
+    this.bookTaskDetailService.UpdateBookTaskDetailVideoMessage(
+      bookTaskDetail.id as string,
+      videoMessage
+    )
+
+    // 修改TASK
+    this.taskListService.UpdateBackTaskData(task.id as string, {
+      taskId: taskId,
+      taskMessage: JSON.stringify(resData)
+    })
+
+    // 返回前端数据
+    SendReturnMessage(
+      {
+        code: 0,
+        id: bookTaskDetail.id as string,
+        message: task.type == BookBackTaskType.KLING_VIDEO_EXTEND ?
+          t("可灵视频延长任务失败，失败信息：{error}", {
+            error: resData.task_status_msg
+          }) :
+          t('可灵图转视频任务失败，失败信息：{error}', {
+            error: resData.task_status_msg
+          }),
+        type: task.type == BookBackTaskType.KLING_VIDEO_EXTEND ? ResponseMessageType.KLING_VIDEO_EXTEND : ResponseMessageType.KLING_VIDEO,
+        data: JSON.stringify(videoMessage)
+      },
+      task.messageName as string
+    )
+    throw new Error(resData.task_status_msg)
+  }
+
+  /**
+   * 处理可灵任务成功状态
+   * 
+   * 当可灵视频生成任务成功完成时，处理视频结果并下载到本地。
+   * 包括提取视频URL、更新状态、下载视频文件，并通知前端任务完成。
+   * 
+   * @param {Book.SelectBookTaskDetail} bookTaskDetail - 小说任务详情对象
+   * @param {TaskModal.Task} task - 当前执行的任务对象
+   * @param {string} taskId - 可灵任务ID
+   * @param {any} resData - 从可灵API返回的成功响应数据，包含视频URLs
+   * 
+   * @description
+   * 处理流程：
+   * 1. 复制并更新视频消息状态为成功
+   * 2. 从响应数据中提取视频URL列表
+   * 3. 更新数据库中的视频消息和任务状态
+   * 4. 修改小说分镜状态为图转视频成功
+   * 5. 调用下载方法将视频保存到本地
+   * 6. 根据任务类型发送相应的成功通知
+   * 
+   * @note
+   * - 支持多个视频文件的处理
+   * - 自动更新任务状态为完成
+   * - 使用任务ID作为下载文件的前缀标识
+   */
+  async KlingTaskSuccessed(bookTaskDetail: Book.SelectBookTaskDetail,
+    task: TaskModal.Task,
+    taskId: string,
+    resData: any) {
+    // 任务成功 修改 videoMessage
+    let videoMessage = cloneDeep(bookTaskDetail.videoMessage) ?? {}
+    videoMessage.status = VideoStatus.SUCCESS
+    videoMessage.taskId = taskId
+
+    let klingVideoIds: string[] = []
+
+    if (resData.task_result && resData.task_result.videos && resData.task_result.videos.length > 0) {
+      videoMessage.videoUrls = []
+      resData.task_result.videos.forEach((item: any) => {
+        videoMessage.videoUrls?.push(item.url)
+        klingVideoIds.push(item.id);
+      })
+    }
+    videoMessage.messageData = JSON.stringify(resData)
+    delete videoMessage.imageUrl
+
+    this.bookTaskDetailService.UpdateBookTaskDetailVideoMessage(
+      task.bookTaskDetailId as string,
+      videoMessage
+    )
+
+    // 修改小说分镜状态
+    this.bookTaskDetailService.ModifyBookTaskDetailById(task.bookTaskDetailId as string, {
+      status: BookTaskStatus.IMAGE_TO_VIDEO_SUCCESS
+    })
+
+    // 修改任务状态
+    this.taskListService.UpdateBackTaskData(task.id as string, {
+      status: BookBackTaskStatus.DONE,
+      taskId: taskId,
+      taskMessage: JSON.stringify(resData)
+    })
+
+    let klingId = resData.task_id ?? new Date().getTime().toString()
+
+    // 下载 视频
+    await this.DownloadVideoUrls(videoMessage.videoUrls || [], task, bookTaskDetail, klingId, klingVideoIds)
+
+    SendReturnMessage(
+      {
+        code: 1,
+        id: bookTaskDetail.id as string,
+        message: task.type == BookBackTaskType.KLING_VIDEO_EXTEND ?
+          t('可灵视频延长任务完成！') : t('Kling图转视频任务完成！'),
+        type: task.type == BookBackTaskType.KLING_VIDEO_EXTEND ? ResponseMessageType.KLING_VIDEO_EXTEND : ResponseMessageType.KLING_VIDEO,
+        data: JSON.stringify(videoMessage)
+      },
+      task.messageName as string
+    )
+  }
+
+  /**
+   * 处理可灵任务执行中状态
+   * 
+   * 当可灵视频生成任务正在处理或刚提交时，更新任务状态并等待继续检查。
+   * 用于轮询机制中的中间状态处理，保持任务状态同步并通知前端进度。
+   * 
+   * @param {Book.SelectBookTaskDetail} bookTaskDetail - 小说任务详情对象
+   * @param {TaskModal.Task} task - 当前执行的任务对象
+   * @param {string} taskId - 可灵任务ID
+   * @param {any} resData - 从可灵API返回的处理中状态数据
+   * 
+   * @description
+   * 处理流程：
+   * 1. 复制并更新视频消息状态为处理中
+   * 2. 更新任务数据和消息内容
+   * 3. 更新数据库中的视频消息状态
+   * 4. 根据任务类型发送相应的处理中通知
+   * 5. 等待20秒后返回，用于轮询间隔控制
+   * 
+   * @note
+   * - 这个方法会阻塞20秒作为轮询间隔
+   * - 支持图转视频和视频延长两种任务类型
+   * - 状态包括"submitted"(已提交)和"processing"(处理中)
+   */
+  async KlingTaskProcessing(
+    bookTaskDetail: Book.SelectBookTaskDetail,
+    task: TaskModal.Task,
+    taskId: string,
+    resData: any) {
+    // 任务执行中或者是提交成功
+    let videoMessage = cloneDeep(bookTaskDetail.videoMessage) ?? {}
+    videoMessage.status = VideoStatus.PROCESSING
+    videoMessage.taskId = taskId
+    videoMessage.messageData = JSON.stringify(resData)
+    delete videoMessage.imageUrl
+    this.bookTaskDetailService.UpdateBookTaskDetailVideoMessage(
+      task.bookTaskDetailId as string,
+      videoMessage
+    )
+
+    SendReturnMessage(
+      {
+        code: 1,
+        id: bookTaskDetail.id as string,
+        message: task.type == BookBackTaskType.KLING_VIDEO_EXTEND ?
+          t('可灵视频延长任务正在执行中...') : t('可灵图转视频任务执行中...'),
+        type: task.type == BookBackTaskType.KLING_VIDEO_EXTEND ? ResponseMessageType.KLING_VIDEO_EXTEND : ResponseMessageType.KLING_VIDEO,
+        data: JSON.stringify(videoMessage)
+      },
+      task.messageName as string
+    )
+
+    // 没有成功 等待二十秒后继续执行
+    await new Promise((resolve) => setTimeout(resolve, 20000))
+  }
+
+  //#endregion
+
+}

src/main/service/video/mjVideo.ts

@@ -152,7 +152,7 @@ export class MJVideoService extends MJApiService {
         {
           code: 1,
           id: task.bookTaskDetailId as string,
-          message: t('已成功提交Midjourney图转视频任务，任务ID：{taskId}', { taskId: id }),
+          message: t('已成功提交{type}图转视频任务，任务ID：{taskId}', { type: 'Midjourney', taskId: id }),
           type: ResponseMessageType.MJ_VIDEO,
           data: JSON.stringify(videoMessage)
         },
@@ -275,7 +275,7 @@ export class MJVideoService extends MJApiService {
         {
           code: 1,
           id: task.bookTaskDetailId as string,
-          message: t('已成功提交Midjourney图转视频任务，任务ID：{taskId}', { taskId: id }),
+          message: t('已成功提交{type}图转视频任务，任务ID：{taskId}', { type: 'Midjourney Extend', taskId: id }),
           type: ResponseMessageType.MJ_VIDEO,
           data: JSON.stringify(videoMessage)
         },

src/renderer/components.d.ts

@@ -21,6 +21,7 @@ declare module 'vue' {
     ComfyUIAddWorkflow: typeof import('./src/components/Setting/ComfyUIAddWorkflow.vue')['default']
     ComfyUISetting: typeof import('./src/components/Setting/ComfyUISetting.vue')['default']
     CommonDialog: typeof import('./src/components/common/CommonDialog.vue')['default']
+    ConfigOptionGroup: typeof import('./src/components/common/ConfigOptionGroup.vue')['default']
     ContactDeveloper: typeof import('./src/components/SoftHome/ContactDeveloper.vue')['default']
     CopyWritingCategoryMenu: typeof import('./src/components/CopyWriting/CopyWritingCategoryMenu.vue')['default']
     CopyWritingContent: typeof import('./src/components/CopyWriting/CopyWritingContent.vue')['default']
@@ -34,6 +35,7 @@ declare module 'vue' {
     DatatableGenerateImageAction: typeof import('./src/components/Original/BookTaskDetail/DatatableGenerateImageAction.vue')['default']
     DataTableGptPrompt: typeof import('./src/components/Original/BookTaskDetail/DataTableGptPrompt.vue')['default']
     DatatableHeaderCharacter: typeof import('./src/components/Original/BookTaskDetail/DatatableHeaderCharacter.vue')['default']
+    DatatableHeaderGptPrompt: typeof import('./src/components/Original/BookTaskDetail/DatatableHeaderGptPrompt.vue')['default']
     DatatableHeaderImage: typeof import('./src/components/Original/BookTaskDetail/DatatableHeaderImage.vue')['default']
     DisabledWrapper: typeof import('./src/components/common/DisabledWrapper.vue')['default']
     DocHelp: typeof import('./src/components/DocHelp.vue')['default']
@@ -50,6 +52,8 @@ declare module 'vue' {
     InputDialogContent: typeof import('./src/components/common/InputDialogContent.vue')['default']
     JianyingGenerateInformation: typeof import('./src/components/Original/BookTaskDetail/JianyingGenerateInformation.vue')['default']
     JianyingKeyFrameSetting: typeof import('./src/components/Setting/JianyingKeyFrameSetting.vue')['default']
+    KlingImageToVideoInfo: typeof import('./src/components/MediaToVideo/MediaToVideoInfo/MediaToVideoInfoKling/KlingImageToVideoInfo.vue')['default']
+    KlingVideoExtendInfo: typeof import('./src/components/MediaToVideo/MediaToVideoInfo/MediaToVideoInfoKling/KlingVideoExtendInfo.vue')['default']
     LanguageSwitcher: typeof import('./src/components/common/LanguageSwitcher.vue')['default']
     LoadingComponent: typeof import('./src/components/common/LoadingComponent.vue')['default']
     ManageAISetting: typeof import('./src/components/CopyWriting/ManageAISetting.vue')['default']
@@ -57,15 +61,16 @@ declare module 'vue' {
     MediaToVideoInfoConfig: typeof import('./src/components/MediaToVideo/MediaToVideoInfo/MediaToVideoInfoConfig.vue')['default']
     MediaToVideoInfoEmptyState: typeof import('./src/components/MediaToVideo/MediaToVideoInfo/MediaToVideoInfoEmptyState.vue')['default']
     MediaToVideoInfoHome: typeof import('./src/components/MediaToVideo/MediaToVideoInfoHome.vue')['default']
+    MediaToVideoInfoKlingVideoInfo: typeof import('./src/components/MediaToVideo/MediaToVideoInfo/MediaToVideoInfoKling/MediaToVideoInfoKlingVideoInfo.vue')['default']
     MediaToVideoInfoMJVideoExtend: typeof import('./src/components/MediaToVideo/MediaToVideoInfo/MediaToVideoInfoMJVideo/MediaToVideoInfoMJVideoExtend.vue')['default']
     MediaToVideoInfoMJVideoImageToVideo: typeof import('./src/components/MediaToVideo/MediaToVideoInfo/MediaToVideoInfoMJVideo/MediaToVideoInfoMJVideoImageToVideo.vue')['default']
     MediaToVideoInfoMJVideoInfo: typeof import('./src/components/MediaToVideo/MediaToVideoInfo/MediaToVideoInfoMJVideo/MediaToVideoInfoMJVideoInfo.vue')['default']
-    MediaToVideoInfoMJVideoSelectParentTask: typeof import('./src/components/MediaToVideo/MediaToVideoInfo/MediaToVideoInfoMJVideo/MediaToVideoInfoMJVideoSelectParentTask.vue')['default']
     MediaToVideoInfoTaskDetail: typeof import('./src/components/MediaToVideo/MediaToVideoInfo/MediaToVideoInfoTaskDetail.vue')['default']
     MediaToVideoInfoTaskList: typeof import('./src/components/MediaToVideo/MediaToVideoInfo/MediaToVideoInfoTaskList.vue')['default']
     MediaToVideoInfoTaskOptions: typeof import('./src/components/MediaToVideo/MediaToVideoInfo/MediaToVideoInfoTaskOptions.vue')['default']
     MediaToVideoInfoVideoConfig: typeof import('./src/components/MediaToVideo/MediaToVideoInfo/MediaToVideoInfoVideoConfig.vue')['default']
     MediaToVideoInfoVideoListInfo: typeof import('./src/components/MediaToVideo/MediaToVideoInfo/MediaToVideoInfoVideoListInfo.vue')['default']
+    MediaToVideoSelectParentTask: typeof import('./src/components/MediaToVideo/MediaToVideoInfo/MediaToVideoSelectParentTask.vue')['default']
     MenuOpenRound: typeof import('./src/components/common/Icon/MenuOpenRound.vue')['default']
     MessageAndProgress: typeof import('./src/components/Original/BookTaskDetail/MessageAndProgress.vue')['default']
     MJAccountDialog: typeof import('./src/components/Setting/MJSetting/MJAccountDialog.vue')['default']
@@ -116,6 +121,8 @@ declare module 'vue' {
     NSpace: typeof import('naive-ui')['NSpace']
     NSpin: typeof import('naive-ui')['NSpin']
     NSwitch: typeof import('naive-ui')['NSwitch']
+    NTabPane: typeof import('naive-ui')['NTabPane']
+    NTabs: typeof import('naive-ui')['NTabs']
     NTag: typeof import('naive-ui')['NTag']
     NText: typeof import('naive-ui')['NText']
     NTooltip: typeof import('naive-ui')['NTooltip']
@@ -132,6 +139,7 @@ declare module 'vue' {
     OriginalTaskList: typeof import('./src/components/Original/MainHome/OriginalTaskList.vue')['default']
     OriginalViewBookInfo: typeof import('./src/components/Original/MainHome/OriginalViewBookInfo.vue')['default']
     OriginalViewBookTaskInfo: typeof import('./src/components/Original/MainHome/OriginalViewBookTaskInfo.vue')['default']
+    PointRightIcon: typeof import('./src/components/common/Icon/PointRightIcon.vue')['default']
     PresetShowCard: typeof import('./src/components/Preset/PresetShowCard.vue')['default']
     RouterLink: typeof import('vue-router')['RouterLink']
     RouterView: typeof import('vue-router')['RouterView']

src/renderer/src/components/MediaToVideo/MediaToVideoInfo/MediaToVideoInfoConfig.vue

@@ -139,77 +139,7 @@
 
     <!-- Kling 类型 -->
     <div v-else-if="selectedVideoType === 'KLING'" class="info-content">
-      <div class="info-section">
+      <MediaToVideoInfoKlingVideoInfo :task="task" />
-        <div class="info-item">
-          <div class="info-label">
-            <n-icon size="16">
-              <svg viewBox="0 0 24 24">
-                <path
-                  fill="currentColor"
-                  d="M12,2A10,10 0 0,0 2,12A10,10 0 0,0 12,22A10,10 0 0,0 22,12A10,10 0 0,0 12,2M11,16.5L6.5,12L7.91,10.59L11,13.67L16.59,8.09L18,9.5L11,16.5Z"
-                />
-              </svg>
-            </n-icon>
-            <span>模型</span>
-          </div>
-          <div class="info-value">
-            <n-tag size="small" type="info">{{ klingOptions?.model || 'kling-v1' }}</n-tag>
-          </div>
-        </div>
-
-        <div class="info-item">
-          <div class="info-label">
-            <n-icon size="16">
-              <svg viewBox="0 0 24 24">
-                <path
-                  fill="currentColor"
-                  d="M12,2L13.09,8.26L22,9L13.09,9.74L12,16L10.91,9.74L2,9L10.91,8.26L12,2Z"
-                />
-              </svg>
-            </n-icon>
-            <span>模式</span>
-          </div>
-          <div class="info-value">
-            <n-tag size="small" :type="klingOptions?.mode === 'pro' ? 'success' : 'info'">
-              {{ klingOptions?.mode === 'pro' ? '高表现' : '高性能' }}
-            </n-tag>
-          </div>
-        </div>
-
-        <div class="info-item">
-          <div class="info-label">
-            <n-icon size="16">
-              <svg viewBox="0 0 24 24">
-                <path
-                  fill="currentColor"
-                  d="M12,2A10,10 0 0,0 2,12A10,10 0 0,0 12,22A10,10 0 0,0 22,12A10,10 0 0,0 12,2M12,17A5,5 0 0,1 7,12A5,5 0 0,1 12,7A5,5 0 0,1 17,12A5,5 0 0,1 12,17Z"
-                />
-              </svg>
-            </n-icon>
-            <span>时长</span>
-          </div>
-          <div class="info-value">
-            <n-text>{{ klingOptions?.duration || 5 }}秒</n-text>
-          </div>
-        </div>
-
-        <div class="info-item" v-if="klingOptions?.cfg_scale">
-          <div class="info-label">
-            <n-icon size="16">
-              <svg viewBox="0 0 24 24">
-                <path
-                  fill="currentColor"
-                  d="M19,3H5C3.89,3 3,3.89 3,5V19A2,2 0 0,0 5,21H19A2,2 0 0,0 21,19V5C21,3.89 20.1,3 19,3M19,5V19H5V5H19Z"
-                />
-              </svg>
-            </n-icon>
-            <span>提示词相关性</span>
-          </div>
-          <div class="info-value">
-            <n-text>{{ klingOptions.cfg_scale }}</n-text>
-          </div>
-        </div>
-      </div>
     </div>
 
     <!-- Midjourney 类型 -->

src/renderer/src/components/MediaToVideo/MediaToVideoInfo/MediaToVideoInfoKling/KlingImageToVideoInfo.vue

@@ -0,0 +1,184 @@
+<template>
+  <n-space vertical :size="20" style="width: 100%">
+    <ConfigOptionGroup
+      v-model:value="videoMessage.klingOptionsObject"
+      :options="klingOptions"
+      @change="handleConfigChange"
+    />
+
+    <div style="display: flex; gap: 12px; width: 100%">
+      <TooltipButton
+        :tooltip="t('将当前转视频的基础设置批量应用到所有的分镜中')"
+        type="default"
+        size="small"
+        @click="handleBatchSettings"
+        style="width: 100px"
+      >
+        <template #icon>
+          <n-icon>
+            <svg viewBox="0 0 24 24">
+              <path fill="currentColor" d="M3,6V8H21V6H3M3,11V13H21V11H3M3,16V18H21V16H3Z" />
+            </svg>
+          </n-icon>
+        </template>
+        {{ t('应用设置') }}
+      </TooltipButton>
+
+      <n-button type="primary" size="small" @click="handleImageToVideo" style="flex: 1">
+        <template #icon>
+          <n-icon>
+            <svg viewBox="0 0 24 24">
+              <path fill="currentColor" d="M8,5.14V19.14L19,12.14L8,5.14Z" />
+            </svg>
+          </n-icon>
+        </template>
+        {{ t('生成视频') }}
+      </n-button>
+    </div>
+  </n-space>
+</template>
+
+<script setup>
+import { computed } from 'vue'
+import ConfigOptionGroup from '@/renderer/src/components/common/ConfigOptionGroup.vue'
+import TooltipButton from '@/renderer/src/components/common/TooltipButton.vue'
+import {
+  GetKlingDurationOptions,
+  GetKlingModelNameOptions,
+  GetKlingModeOptions
+} from '@/define/enum/video'
+import { t } from '@/i18n'
+import { useFile } from '@/renderer/src/hooks/useFile'
+
+const { UploadImageToLaiTool } = useFile()
+
+const props = defineProps({
+  task: {
+    type: Object,
+    required: true
+  },
+  videoMessage: {
+    type: Object,
+    required: true
+  }
+})
+
+const emit = defineEmits(['update-kling-options', 'batch-settings', 'image-to-video'])
+
+// 处理配置变更
+const handleConfigChange = (key, value, newValue) => {
+  // 数据已经被直接修改了，这里只需要处理业务逻辑（如保存到后端）
+  emit('update-kling-options', key, value, newValue)
+  console.log('Kling options changed:', key, value, newValue)
+}
+
+// 批量设置基础设置
+async function handleBatchSettings() {
+  emit('batch-settings')
+}
+
+// 执行图转视频任务
+async function handleImageToVideo() {
+  emit('image-to-video')
+}
+
+// 图片上传的逻辑
+async function handleImageUpload(key, imagePath) {
+  const url = await UploadImageToLaiTool(imagePath, 'video')
+
+  if (url) {
+    const newValue = {
+      ...props.videoMessage.klingOptionsObject,
+      [key]: url
+    }
+    // 上传成功，更新数据
+    emit('update-kling-options', key, url, newValue)
+  }
+}
+
+const klingOptions = computed(() => [
+  {
+    key: 'model_name',
+    label: t('模型名称'),
+    type: 'select',
+    options: GetKlingModelNameOptions(),
+    placeholder: t('请选择 {data}', { data: t('模型名称') }),
+    width: '180px'
+  },
+  {
+    key: 'image',
+    label: t('参考图像'),
+    type: 'image',
+    placeholder: t('请输入 {data}', { data: t('图片链接') }),
+    fullWidth: true, // 占满整行，换行显示
+    onUpload: handleImageUpload,
+    required: true,
+    tooltip: t(
+      '<strong>必须</strong><br/><br/>• 支持格式：<strong>.jpg/.jpeg/.png</strong><br/>• 文件大小：<strong>不超过10MB</strong><br/>• 分辨率：<strong>不小于300*300px</strong><br/>• 宽高比：<strong>1:2.5 ~ 2.5:1</strong>之间'
+    )
+  },
+  {
+    key: 'image_tail',
+    label: t('参考图像 - 尾帧控制'),
+    type: 'image',
+    fullWidth: true, // 占满整行，换行显示
+    onUpload: handleImageUpload,
+    required: false,
+    placeholder: t('请输入 {data}', { data: t('图片链接') }),
+    tooltip: t(
+      '<strong>可选</strong><br/><br/>• 支持格式：<strong>.jpg/.jpeg/.png</strong><br/>• 文件大小：<strong>不超过10MB</strong><br/>• 分辨率：<strong>不小于300*300px</strong><br/>• 宽高比：<strong>1:2.5 ~ 2.5:1</strong>之间'
+    )
+  },
+  {
+    key: 'prompt',
+    label: t('正向提示词'),
+    type: 'input',
+    inputType: 'textarea',
+    autosize: { minRows: 3, maxRows: 3 },
+    fullWidth: true, // 占满整行，换行显示
+    placeholder: t('请输入 {data}', { data: t('正向提示词') }),
+    tooltip: t('正向文本提示，可选，不能超过2500个字符')
+  },
+  {
+    key: 'negative_prompt',
+    label: t('反向提示词'),
+    type: 'input',
+    inputType: 'textarea',
+    autosize: { minRows: 3, maxRows: 3 },
+    fullWidth: true, // 占满整行，换行显示
+    placeholder: t('请输入 {data}', { data: t('反向提示词') }),
+    tooltip: t('负向文本提示，可选，不能超过2500个字符')
+  },
+  {
+    key: 'cfg_scale',
+    label: t('自由度'),
+    type: 'number',
+    min: 0,
+    max: 1,
+    step: 0.1,
+    placeholder: t('0-1之间'),
+    width: '120px',
+    tooltip: t(
+      '生成视频的自由度<br/><br/><strong>值越大，模型自由度越小</strong><br/>与用户输入的提示词相关性越强<br/><br/>取值范围：<strong>[0, 1]</strong>'
+    )
+  },
+  {
+    key: 'mode',
+    label: t('生成模式'),
+    type: 'select',
+    options: GetKlingModeOptions(),
+    width: '180px',
+    tooltip: t(
+      '生成视频的模式<br/><br/>枚举值：std，pro<br/>其中std：标准模式（标准），基础模式，性价比高<br/>其中pro：专家模式（高品质），高表现模式，生成视频质量更佳'
+    )
+  },
+  {
+    key: 'duration',
+    label: t('视频时长'),
+    type: 'select',
+    options: GetKlingDurationOptions(),
+    width: '100px',
+    tooltip: t('生成视频时长，单位s（5秒或10秒）')
+  }
+])
+</script>

src/renderer/src/components/MediaToVideo/MediaToVideoInfo/MediaToVideoInfoKling/KlingVideoExtendInfo.vue

@@ -0,0 +1,118 @@
+<template>
+  <n-space vertical :size="20" style="width: 100%">
+    <ConfigOptionGroup
+      v-model:value="videoMessage.klingOptionsObject"
+      :options="klingOptions"
+      @change="handleConfigChange"
+    />
+    <div style="display: flex; gap: 12px; width: 100%">
+      <n-button type="primary" size="small" @click="handleVideoExtend" style="flex: 1">
+        <template #icon>
+          <n-icon>
+            <svg viewBox="0 0 24 24">
+              <path fill="currentColor" d="M8,5.14V19.14L19,12.14L8,5.14Z" />
+            </svg>
+          </n-icon>
+        </template>
+        {{ t('视频延长') }}
+      </n-button>
+    </div>
+  </n-space>
+</template>
+
+<script setup>
+import { computed } from 'vue'
+import ConfigOptionGroup from '@/renderer/src/components/common/ConfigOptionGroup.vue'
+
+import { t } from '@/i18n'
+import PointRightIcon from '../../../common/Icon/PointRightIcon.vue'
+
+const props = defineProps({
+  task: {
+    type: Object,
+    required: true
+  },
+  videoMessage: {
+    type: Object,
+    required: true
+  }
+})
+
+const emit = defineEmits([
+  'update-kling-options',
+  'batch-settings',
+  'video-extend',
+  'select-parent-task'
+])
+
+// 执行视频拓展
+async function handleVideoExtend() {
+  emit('video-extend')
+}
+
+// Kling 配置选项
+const klingOptions = computed(() => [
+  {
+    key: 'prompt',
+    label: t('正向提示词'),
+    type: 'input',
+    inputType: 'textarea',
+    autosize: { minRows: 2, maxRows: 4 },
+    placeholder: t('请输入 {data}', { data: t('正向提示词') }),
+    fullWidth: true // 占满整行，换行显示
+  },
+  {
+    key: 'negative_prompt',
+    label: t('反向提示词'),
+    type: 'input',
+    inputType: 'textarea',
+    autosize: { minRows: 2, maxRows: 3 },
+    placeholder: t('请输入 {data}', { data: t('反向提示词') }),
+    fullWidth: true, // 占满整行，换行显示
+    tooltip: t('负向文本提示，可选，不能超过2500个字符')
+  },
+  {
+    key: 'video_id',
+    label: t('视频ID'),
+    type: 'input',
+    suffixButton: {
+      icon: PointRightIcon,
+      tooltip: t('选择已有的视频任务作为延长的基础'),
+      text: t('选择Video'),
+      width: '120px',
+      onClick: () => {
+        emit('select-parent-task')
+      }
+    },
+    placeholder: t('请选择 {data}', { data: t('视频ID') }),
+    fullWidth: true, // 占满整行，换行显示
+    tooltip: t('支持通过文本、图片和视频延长生成的视频的ID（原视频不能超过3分钟）')
+  },
+  {
+    key: 'task_id',
+    label: t('任务ID'),
+    type: 'input',
+    placeholder: t('请选择 {data}', { data: t('任务ID') }),
+    fullWidth: true, // 占满整行，换行显示
+    tooltip: t('对应于视频ID的任务ID，通常在选择视频后自动填充')
+  },
+  {
+    key: 'cfg_scale',
+    label: t('自由度'),
+    type: 'number',
+    min: 0,
+    max: 1,
+    step: 0.1,
+    placeholder: t('0-1之间'),
+    width: '120px',
+    tooltip: t(
+      '生成视频的自由度<br/><br/><strong>值越大，模型自由度越小</strong><br/>与用户输入的提示词相关性越强<br/><br/>取值范围：<strong>[0, 1]</strong>'
+    )
+  }
+])
+
+// 处理配置变化
+function handleConfigChange(key, value, newValue) {
+  emit('update-kling-options', key, value, newValue)
+}
+</script>

src/renderer/src/components/MediaToVideo/MediaToVideoInfo/MediaToVideoInfoKling/MediaToVideoInfoKlingVideoInfo.vue

@@ -0,0 +1,288 @@
+<template>
+  <div class="mj-video-container">
+    <n-tabs v-model:value="activeTab" type="segment" size="small">
+      <!-- 图生视频 Tab -->
+      <n-tab-pane name="image-to-video" :tab="t('图生视频')">
+        <KlingImageToVideoInfo
+          :task="props.task"
+          :video-message="videoMessage"
+          @update-kling-options="handleKlingOptionsUpdate"
+          @batch-settings="handleBatchSettings"
+          @image-to-video="handleImageToVideo(BookBackTaskType.KLING_VIDEO)"
+        />
+      </n-tab-pane>
+
+      <!-- 视频拓展 Tab -->
+      <n-tab-pane name="video-extend" :tab="t('视频延长')">
+        <KlingVideoExtendInfo
+          :task="props.task"
+          :video-message="videoMessage"
+          @update-kling-options="handleKlingOptionsUpdate"
+          @batch-settings="handleBatchSettings"
+          @select-parent-task="handleSelectParentTask"
+          @video-extend="handleImageToVideo(BookBackTaskType.KLING_VIDEO_EXTEND)"
+        />
+      </n-tab-pane>
+    </n-tabs>
+
+    <!-- 选择父任务的 Modal 弹窗 -->
+    <n-modal
+      v-model:show="showParentTaskModal"
+      :mask-closable="false"
+      preset="card"
+      style="width: 90%; max-width: 1200px"
+      :title="t('选择父任务')"
+      size="huge"
+      :content-style="{ padding: '8px 16px' }"
+      :segmented="true"
+    >
+      <ImageToVideoSelectParentTask
+        :taskData="props.task"
+        :videoList="subVideoPathObject"
+        @save-selection="handleParentTaskSelection"
+      />
+    </n-modal>
+  </div>
+</template>
+
+<script setup>
+import { ref, computed, h } from 'vue'
+import { useMessage, useDialog } from 'naive-ui'
+import KlingImageToVideoInfo from './KlingImageToVideoInfo.vue'
+import KlingVideoExtendInfo from './KlingVideoExtendInfo.vue'
+import { t } from '@/i18n'
+import { ValidateJsonAndParse } from '@/define/Tools/validate'
+import { KlingDuration, KlingMode, KlingModelName } from '@/define/enum/video'
+import { useSoftwareStore, useBookStore } from '@/renderer/src/stores'
+import ImageToVideoSelectParentTask from '@/renderer/src/components/MediaToVideo/MediaToVideoInfo/MediaToVideoSelectParentTask.vue'
+import { ImageToVideoModels } from '@/define/enum/video'
+import { isEmpty } from 'lodash'
+import { BookBackTaskType, TaskExecuteType } from '@/define/enum/bookEnum'
+import { DEFINE_STRING } from '@/define/ipcDefineString'
+import { AddOneTask } from '@/renderer/src/common/task'
+
+const message = useMessage()
+const dialog = useDialog()
+
+const softwareStore = useSoftwareStore()
+const bookStore = useBookStore()
+
+const showParentTaskModal = ref(false)
+
+// 获取当前有效任务的视频列表
+const subVideoPathObject = computed(() => {
+  return props.task?.subVideoPathObject.filter(
+    (video) =>
+      !isEmpty(video.localPath) &&
+      (video.type == ImageToVideoModels.KLING || video.type == ImageToVideoModels.KLING_VIDEO_EXTEND)
+  )
+})
+
+const props = defineProps({
+  task: {
+    type: Object,
+    required: true
+  }
+})
+
+// 图生视频表单
+const videoMessage = computed(() => {
+  console.log('MediaToVideoInfoKlingVideoInfo props.task', props.task, props.task?.videoMessage)
+  let videoMessage = props.task?.videoMessage || {}
+  let klingVideoOptionsString = videoMessage.klingOptions || '{}'
+  let klingVideoOptions = ValidateJsonAndParse(klingVideoOptionsString)
+
+  // 确保 klingOptions 是一个干净的对象，避免保留上一个任务的数据
+  const cleanKlingVideoOptions = {
+    model_name: klingVideoOptions.model_name || KlingModelName.KLING_V2_1,
+    image: videoMessage.imageUrl || klingVideoOptions.image || '',
+    image_tail: klingVideoOptions.image_tail || '',
+    prompt: klingVideoOptions.prompt || '',
+    negative_prompt: klingVideoOptions.negative_prompt || '',
+    cfg_scale: klingVideoOptions.cfg_scale ?? 0.5,
+    mode: klingVideoOptions.mode || KlingMode.STD,
+    duration: klingVideoOptions.duration ?? KlingDuration.FIVE,
+    video_id: klingVideoOptions.video_id || '',
+    task_id: klingVideoOptions.task_id || ''
+  }
+
+  videoMessage.klingOptionsObject = cleanKlingVideoOptions
+
+  console.log(
+    'MediaToVideoInfoKlingVideoInfo videoMessage',
+    videoMessage,
+    videoMessage.klingOptionsObject
+  )
+  return videoMessage
+})
+
+// 处理 Kling 选项更新
+async function handleKlingOptionsUpdate(key, value, newOptions) {
+  // 直接修改数据到数据库
+  let updateData = {
+    klingOptions: JSON.stringify(newOptions),
+    imageUrl: newOptions.image // 同步更新 imageUrl 字段
+  }
+  let res = await window.book.video.UpdateBookTaskDetailVideoMessage(props.task.id, updateData)
+  if (res.code !== 1) {
+    message.error(
+      t('保存失败：{error}', {
+        error: res.message
+      }) + `, Key: ${key}`
+    )
+    return
+  }
+
+  // 修改成功后要同步更新本地数据，避免切换tab时数据丢失
+  if (!props.task.videoMessage) {
+    props.task.videoMessage = {}
+  }
+
+  Object.assign(props.task.videoMessage, updateData)
+
+  // 同步更新 klingOptionsObject
+  videoMessage.value.klingOptionsObject = {
+    ...videoMessage.value.klingOptionsObject,
+    ...newOptions
+  }
+}
+// 批量设置基础设置
+async function handleBatchSettings() {
+  // 直接触发父组件的批量设置事件
+  // 这里不做任何处理，交给父组件去处理
+  let da = dialog.warning({
+    title: t('操作确认'),
+    content: () =>
+      h(
+        'div',
+        {
+          style: {
+            whiteSpace: 'pre-line'
+          }
+        },
+        {
+          default: () =>
+            t(
+              '是否将当前分镜的设置批量应用到其余所有分镜？\n\n同步的设置：模型名称（Model Name），生成模式（Mode），视频时长（Duration），自由度（CFG Scale） \n\n批量应用后，其余分镜的上述基础设置会被替换为当前分镜的数据，是否继续？'
+            )
+        }
+      ),
+    positiveText: t('确认'),
+    negativeText: t('取消'),
+    closable: true,
+    onPositiveClick: async () => {
+      da.destroy()
+      try {
+        softwareStore.spin.spinning = true
+        softwareStore.spin.tip = t('正在批量应用当前设置...')
+
+        // 开始修改所有的分镜
+        for (let i = 0; i < bookStore.selectBookTaskDetail.length; i++) {
+          const element = bookStore.selectBookTaskDetail[i]
+
+          let updateObject = {}
+          // 开始修改所有分镜
+          let elementVideoMessage = element?.videoMessage || {}
+          let elementKlingOptionsString = elementVideoMessage.klingOptions || '{}'
+          let elementKlingOptions = ValidateJsonAndParse(elementKlingOptionsString)
+
+          // 更新 Kling 的核心设置参数
+          elementKlingOptions.model_name =
+            videoMessage.value.klingOptionsObject.model_name || KlingModelName.KLING_V2_1
+          elementKlingOptions.mode = videoMessage.value.klingOptionsObject.mode || KlingMode.STD
+          elementKlingOptions.duration =
+            videoMessage.value.klingOptionsObject.duration ?? KlingDuration.FIVE
+          elementKlingOptions.cfg_scale = videoMessage.value.klingOptionsObject.cfg_scale ?? 0.5
+
+          elementVideoMessage.klingOptions = JSON.stringify(elementKlingOptions)
+          updateObject.klingOptions = elementVideoMessage.klingOptions
+
+          // 开始修改数据库
+          let res = await window.book.video.UpdateBookTaskDetailVideoMessage(
+            element.id,
+            updateObject
+          )
+
+          if (res.code !== 1) {
+            message.error(
+              t('批量应用当前设置失败，{error}', {
+                error: res.message
+              })
+            )
+            return
+          }
+        }
+
+        message.success(t('批量应用当前设置成功！'))
+      } catch (error) {
+        message.error(
+          t('批量应用当前设置失败，{error}', {
+            error: error.message
+          })
+        )
+      } finally {
+        softwareStore.spin.spinning = false
+      }
+    },
+    onNegativeClick: () => {
+      da.destroy()
+      message.info(t('取消操作'))
+    }
+  })
+}
+
+// 图生视频任务
+async function handleImageToVideo(type) {
+  if (isEmpty(videoMessage.value.imageUrl)) {
+    message.error(t('请输入图片链接'))
+    return
+  }
+
+  let res = await AddOneTask({
+    bookId: props.task.bookId,
+    type: type,
+    executeType: TaskExecuteType.AUTO,
+    bookTaskId: props.task.bookTaskId,
+    bookTaskDetailId: props.task.id,
+    messageName: DEFINE_STRING.BOOK.KLING_IMAGE_TO_VIDEO_RETURN
+  })
+
+  if (res.code != 1) {
+    message.error(res.message)
+    return
+  }
+  message.success(res.message)
+}
+
+async function handleSelectParentTask() {
+  showParentTaskModal.value = true
+  message.info(t('请选择一个已有的视频任务作为延长的基础'))
+}
+
+// 处理父任务选择
+async function handleParentTaskSelection(selectedVideoInfo) {
+  try {
+    // 更新当前任务的 Kling 配置中的 video_id
+    const currentKlingOptions = videoMessage.value.klingOptionsObject
+    const updatedKlingOptions = {
+      ...currentKlingOptions,
+      video_id: selectedVideoInfo.videoId,
+      task_id: selectedVideoInfo.taskId
+    }
+
+    // 保存到数据库
+    await handleKlingOptionsUpdate('video_id', selectedVideoInfo.taskId, updatedKlingOptions)
+
+    // 关闭 modal
+    showParentTaskModal.value = false
+
+    message.success(
+      t('父任务选择成功，视频ID已更新为: {videoId}', { videoId: selectedVideoInfo.taskId })
+    )
+  } catch (error) {
+    message.error(t('保存失败：{error}', { error: error.message }))
+  }
+}
+
+const activeTab = ref('image-to-video')
+</script>

src/renderer/src/components/MediaToVideo/MediaToVideoInfo/MediaToVideoInfoMJVideo/MediaToVideoInfoMJVideoExtend.vue

@@ -443,7 +443,33 @@
 
     <!-- 执行按钮 -->
     <n-form-item>
-      <n-button type="primary" size="small" :loading="loading" @click="handleExtend" block>
+      <div style="display: flex; gap: 12px; width: 100%">
+        <TooltipButton
+          :tooltip="t('将当前转视频的基础设置批量应用到所有的分镜中')"
+          type="default"
+          size="small"
+          :loading="loading"
+          @click="handleBatchSettings"
+          style="width: 100px"
+        >
+          <template #icon>
+            <n-icon>
+              <svg viewBox="0 0 24 24">
+                <path fill="currentColor" d="M3,6V8H21V6H3M3,11V13H21V11H3M3,16V18H21V16H3Z" />
+              </svg>
+            </n-icon>
+          </template>
+          {{ t('应用设置') }}
+        </TooltipButton>
+
+        <n-button
+          type="primary"
+          size="small"
+          :loading="loading"
+          @click="handleExtend"
+          block
+          style="flex: 1"
+        >
           <template #icon>
             <n-icon>
               <svg viewBox="0 0 24 24">
@@ -453,6 +479,7 @@
           </template>
           {{ t('执行视频拓展') }}
         </n-button>
+      </div>
     </n-form-item>
   </n-space>
 </template>
@@ -469,8 +496,6 @@ import {
   NTooltip,
   NSwitch,
   NAlert,
-  NImage,
-  NText,
   useMessage
 } from 'naive-ui'
 
@@ -511,13 +536,24 @@ const props = defineProps({
 })
 
 // 定义 emits
-const emit = defineEmits(['video-message-change', 'extend', 'select-parent-task', 'image-upload'])
+const emit = defineEmits([
+  'video-message-change',
+  'extend',
+  'select-parent-task',
+  'image-upload',
+  'batch-settings'
+])
 
 // 修改 videoMessage 的通用函数
 function handleVideoMessageChange(key, value = undefined) {
   emit('video-message-change', key, value)
 }
 
+// 处理批量设置
+async function handleBatchSettings() {
+  emit('batch-settings', 'extend')
+}
+
 // 处理视频拓展
 async function handleExtend() {
   console.log('执行视频拓展', props.videoMessage, props.task)

src/renderer/src/components/MediaToVideo/MediaToVideoInfo/MediaToVideoInfoMJVideo/MediaToVideoInfoMJVideoImageToVideo.vue

@@ -8,7 +8,6 @@
           :placeholder="t('请输入图片链接')"
           @change="handleVideoMessageChange('imageUrl')"
           size="small"
-          :disabled="loading"
           class="image-input"
         >
           <template #suffix>
@@ -17,7 +16,7 @@
               :tooltip="t('上传图片到LaiTool图床，获取图片链接')"
               quaternary
               @click="handleUploadImage(videoMessage.imageUrl, 'video', 'imageUrl')"
-              :disabled="loading"
+
             >
               <template #icon>
                 <n-icon size="20">
@@ -68,7 +67,6 @@
             handleVideoMessageChange('endImageUrl', videoMessage.mjVideoOptionsObject.endImageUrl)
           "
           size="small"
-          :disabled="loading"
           class="image-input"
         >
           <template #suffix>
@@ -83,7 +81,6 @@
                   'endImageUrl'
                 )
               "
-              :disabled="loading"
             >
               <template #icon>
                 <n-icon size="20">
@@ -132,7 +129,6 @@
         :placeholder="t('请输入 {data}', { data: t('提示词（可选）') })"
         size="small"
         :autosize="{ minRows: 2, maxRows: 4 }"
-        :disabled="loading"
         @change="handleVideoMessageChange('prompt')"
       />
     </n-form-item>
@@ -196,7 +192,6 @@
           :placeholder="t('选择视频类型')"
           @update-value="(value) => handleVideoMessageChange('videoType', value)"
           size="small"
-          :disabled="loading"
           class="motion-select"
           :style="{ width: '140px' }"
         />
@@ -251,7 +246,6 @@
           :placeholder="t('选择运动变化程度')"
           @update-value="(value) => handleVideoMessageChange('motion', value)"
           size="small"
-          :disabled="loading"
           class="motion-select"
         />
       </div>
@@ -310,7 +304,6 @@
           :placeholder="t('选择批次数量')"
           @update-value="(value) => handleVideoMessageChange('batchSize', value)"
           size="small"
-          :disabled="loading"
           class="motion-select"
         />
       </div>
@@ -355,7 +348,6 @@
           v-model:value="videoMessage.mjVideoOptionsObject.raw"
           size="small"
           @update-value="handleVideoMessageChange('raw')"
-          :disabled="loading"
         >
           <template #checked>{{ t('是') }}</template>
           <template #unchecked>{{ t('否') }}</template>
@@ -397,7 +389,6 @@
           v-model:value="videoMessage.mjVideoOptionsObject.loop"
           size="small"
           @update-value="handleVideoMessageChange('loop')"
-          :disabled="loading"
         >
           <template #checked>{{ t('是') }}</template>
           <template #unchecked>{{ t('否') }}</template>
@@ -407,7 +398,30 @@
 
     <!-- 生成按钮 -->
     <n-form-item>
-      <n-button type="primary" size="small" :loading="loading" @click="handleImageToVideo" block>
+      <div style="display: flex; gap: 12px; width: 100%">
+        <TooltipButton
+          :tooltip="t('将当前转视频的基础设置批量应用到所有的分镜中')"
+          type="default"
+          size="small"
+          @click="handleBatchSettings"
+          style="width: 100px"
+        >
+          <template #icon>
+            <n-icon>
+              <svg viewBox="0 0 24 24">
+                <path fill="currentColor" d="M3,6V8H21V6H3M3,11V13H21V11H3M3,16V18H21V16H3Z" />
+              </svg>
+            </n-icon>
+          </template>
+          {{ t('应用设置') }}
+        </TooltipButton>
+
+        <n-button
+          type="primary"
+          size="small"
+          @click="handleImageToVideo"
+          style="flex: 1"
+        >
           <template #icon>
             <n-icon>
               <svg viewBox="0 0 24 24">
@@ -417,6 +431,7 @@
           </template>
           {{ t('生成视频') }}
         </n-button>
+      </div>
     </n-form-item>
   </n-space>
 </template>
@@ -453,15 +468,16 @@ const props = defineProps({
   videoMessage: {
     type: Object,
     required: true
-  },
-  loading: {
-    type: Boolean,
-    default: false
   }
 })
 
 // 定义 emits
-const emit = defineEmits(['video-message-change', 'image-to-video', 'image-upload'])
+const emit = defineEmits([
+  'video-message-change',
+  'image-to-video',
+  'image-upload',
+  'batch-settings'
+])
 
 // 处理图片加载错误
 function handleImageError(imageUrl) {
@@ -492,6 +508,11 @@ function handleImageToVideo() {
 
   emit('image-to-video')
 }
+
+// 批量应用当前设置
+async function handleBatchSettings() {
+  emit('batch-settings')
+}
 </script>
 
 <style scoped>

src/renderer/src/components/MediaToVideo/MediaToVideoInfo/MediaToVideoInfoMJVideo/MediaToVideoInfoMJVideoInfo.vue

@@ -5,10 +5,10 @@
       <n-tab-pane name="image-to-video" :tab="t('图生视频')">
         <ImageTextVideoInfoMJVideoImageToVideo
           :video-message="videoMessage"
-          :loading="loading"
           @video-message-change="handleVideoMessageChange"
           @image-to-video="handleImageToVideo"
           @image-upload="handleUploadImage"
+          @batch-settings="handleBatchSettings"
         />
       </n-tab-pane>
 
@@ -17,11 +17,11 @@
         <DisabledWrapper :un-use="false">
           <ImageTextVideoInfoMJVideoExtend
             :video-message="videoMessage"
-            :loading="loading"
             :task="props.task"
             @video-message-change="handleVideoMessageChange"
             @select-parent-task="handleSelectParentTask"
             @image-upload="handleUploadImage"
+            @batch-settings="handleBatchSettings"
           />
         </DisabledWrapper>
       </n-tab-pane>
@@ -38,35 +38,38 @@
       :content-style="{ padding: '8px 16px' }"
       :segmented="true"
     >
-      <ImageTextVideoInfoMJVideoSelectParentTask
+      <MediaToVideoSelectParentTask
         :taskData="props.task"
         :videoList="subVideoPathObject"
         @close="showParentTaskModal = false"
+        @save-selection="handleSaveSelection"
       />
     </n-modal>
   </div>
 </template>
 
 <script setup>
-import { ref, computed } from 'vue'
+import { ref, computed, h } from 'vue'
-import { NTabs, NTabPane, NModal, useMessage } from 'naive-ui'
+import { NTabs, NTabPane, NModal, useMessage, useDialog } from 'naive-ui'
 
-import { ImageToVideoModels, MJVideoMotion } from '@/define/enum/video'
+import { ImageToVideoModels, MJVideoMotion, MJVideoType } from '@/define/enum/video'
 import { ValidateJsonAndParse } from '@/define/Tools/validate'
 import { BookBackTaskType, TaskExecuteType } from '@/define/enum/bookEnum'
 import { DEFINE_STRING } from '@/define/ipcDefineString'
 import { isEmpty } from 'lodash'
-import ImageTextVideoInfoMJVideoSelectParentTask from './MediaToVideoInfoMJVideoSelectParentTask.vue'
 import ImageTextVideoInfoMJVideoImageToVideo from './MediaToVideoInfoMJVideoImageToVideo.vue'
 import ImageTextVideoInfoMJVideoExtend from './MediaToVideoInfoMJVideoExtend.vue'
+import DisabledWrapper from '@/renderer/src/components/common/DisabledWrapper.vue'
 import { AddOneTask } from '@/renderer/src/common/task'
 import { t } from '@/i18n'
-import { useSoftwareStore } from '@/renderer/src/stores'
+import { useSoftwareStore, useBookStore } from '@/renderer/src/stores'
 import { useFile } from '@/renderer/src/hooks/useFile'
+import MediaToVideoSelectParentTask from '../MediaToVideoSelectParentTask.vue'
 
 const message = useMessage()
 const dialog = useDialog()
 const softwareStore = useSoftwareStore()
+const bookStore = useBookStore()
 const { UploadImageToLaiTool } = useFile()
 
 // 定义 props
@@ -79,7 +82,6 @@ const props = defineProps({
 
 // 响应式状态
 const activeTab = ref('image-to-video')
-const loading = ref(false)
 const showParentTaskModal = ref(false)
 
 // 图生视频表单
@@ -107,7 +109,12 @@ const videoMessage = computed(() => {
 })
 
 const subVideoPathObject = computed(() => {
-  return props.task?.subVideoPathObject || []
+  return props.task?.subVideoPathObject?.filter(
+    (video) =>
+      !isEmpty(video.localPath) &&
+      (video.type == ImageToVideoModels.MJ_VIDEO ||
+        video.type == ImageToVideoModels.MJ_VIDEO_EXTEND)
+  )
 })
 
 // 处理图生视频
@@ -240,11 +247,42 @@ async function handleVideoMessageChange(key, value = undefined) {
     )
     return
   }
+
+  // 修改成功之后要同步更新本地数据，避免切换tab时数据丢失
+  // 更新 props.task.videoMessage
+  if (!props.task.videoMessage) {
+    props.task.videoMessage = {}
+  }
+
+  Object.assign(props.task.videoMessage, updateObject)
+
+  // 如果更新了 mjVideoOptions，也要同步更新 mjVideoOptionsObject
+  if (updateObject.mjVideoOptions) {
+    const updatedMjVideoOptions = ValidateJsonAndParse(updateObject.mjVideoOptions)
+    videoMessage.value.mjVideoOptionsObject = {
+      ...videoMessage.value.mjVideoOptionsObject,
+      ...updatedMjVideoOptions
+    }
+  }
 }
 
 // 处理上传图片
 async function handleUploadImage(filePath, type, property) {
-  debugger
+  const url = await UploadImageToLaiTool(filePath, type)
+
+  if (url) {
+    // 上传成功，更新数据
+    if (property == 'endImageUrl' || property == 'extendEndImageUrl') {
+      videoMessage.value.mjVideoOptionsObject[property] = url
+    } else {
+      videoMessage.value[property] = url
+    }
+    await handleVideoMessageChange(property, url)
+  }
+}
+
+// 批量应用当前设置到其余所有分镜
+async function handleBatchSettings(value) {
   let da = dialog.warning({
     title: t('操作确认'),
     content: () =>
@@ -256,7 +294,7 @@ async function handleUploadImage(filePath, type, property) {
         {
           default: () =>
             t(
-              '是否上传图片文件到LaiTool云端？\n\n上传后会返回一个全球可分享的网络链接地址，但是每日限制五十次上传。上传后的图片可用于MJ垫图，转视频等功能。\n\n注意：上传后的图片会再Laitool服务器留存，若介意请勿上传。'
+              '是否将当前分镜的设置批量应用到其余所有分镜？\n\n同步的设置：视频类型（SD/HD），运动变化（Motion），批次数据（Batch），视频原始（Raw），首尾循环（Loop） \n\n批量应用后，其余分镜的上述基础设置会被替换为当前分镜的数据，是否继续？'
             )
         }
       ),
@@ -266,15 +304,51 @@ async function handleUploadImage(filePath, type, property) {
       da?.destroy()
       try {
         softwareStore.spin.spinning = true
-        softwareStore.spin.tip = t('开始上传文件...')
+        softwareStore.spin.tip = t('正在批量应用当前设置...')
 
-        let url = await UploadImageToLaiTool(filePath, type)
+        for (let i = 0; i < bookStore.selectBookTaskDetail.length; i++) {
-        if (property == 'endImageUrl' || property == 'extendEndImageUrl')
+          const element = bookStore.selectBookTaskDetail[i]
-          videoMessage.value.mjVideoOptionsObject[property] = url
+
-        else videoMessage.value[property] = url
+          let updateObject = {}
-        await handleVideoMessageChange(property, url)
+
+          // 开始修改所有分镜
+          let elementVideoMessage = element?.videoMessage || {}
+          let elementMjVideoOptionsString = elementVideoMessage.mjVideoOptions || '{}'
+          let elementMjVideoOptions = ValidateJsonAndParse(elementMjVideoOptionsString)
+          elementMjVideoOptions.videoType =
+            videoMessage.value.mjVideoOptionsObject.videoType ?? MJVideoType.HD
+          elementMjVideoOptions.motion =
+            videoMessage.value.mjVideoOptionsObject.motion ?? MJVideoMotion.Low
+          elementMjVideoOptions.batchSize = videoMessage.value.mjVideoOptionsObject.batchSize || 1
+          elementMjVideoOptions.raw = videoMessage.value.mjVideoOptionsObject.raw ?? true
+          if (value != 'extend') {
+            elementMjVideoOptions.loop = videoMessage.value.mjVideoOptionsObject.loop ?? false
+          }
+          elementVideoMessage.mjVideoOptions = JSON.stringify(elementMjVideoOptions)
+          updateObject.mjVideoOptions = elementVideoMessage.mjVideoOptions
+
+          // 开始修改
+          let res = await window.book.video.UpdateBookTaskDetailVideoMessage(
+            element.id,
+            updateObject
+          )
+
+          if (res.code !== 1) {
+            message.error(
+              t('批量应用当前设置失败，{error}', {
+                error: res.message
+              })
+            )
+            return
+          }
+        }
+        message.success(t('批量应用当前设置成功！'))
       } catch (error) {
-        message.error(error.message)
+        message.error(
+          t('批量应用当前设置失败，{error}', {
+            error: error.message
+          })
+        )
       } finally {
         softwareStore.spin.spinning = false
       }
@@ -284,6 +358,38 @@ async function handleUploadImage(filePath, type, property) {
     }
   })
 }
+
+// 保存选中的视频任务信息
+async function handleSaveSelection(currentVideoInfo) {
+  let taskId = currentVideoInfo.taskId || ''
+  let videoIndex = currentVideoInfo.index
+  if (isEmpty(taskId) || videoIndex == null) {
+    message.error(t('当前选中的视频的 taskId 或 videoIndex 为空，请检查视频信息'))
+    return
+  }
+
+  // 开始修改实际的数据
+  let updateObject = {
+    mjVideoOptions: JSON.stringify({
+      ...videoMessage.value.mjVideoOptionsObject,
+      taskId: taskId,
+      index: videoIndex
+    })
+  }
+
+  let res = await window.book.video.UpdateBookTaskDetailVideoMessage(props.task.id, updateObject)
+
+  // 检查返回结果
+  if (res.code == 1) {
+    message.success(t('保存成功'))
+
+    videoMessage.value.mjVideoOptionsObject.taskId = taskId
+    videoMessage.value.mjVideoOptionsObject.index = videoIndex
+  } else {
+    message.error(t('保存失败：{error}', { error: res.message }))
+    return
+  }
+}
 </script>
 
 <style scoped>

src/renderer/src/components/MediaToVideo/MediaToVideoInfo/MediaToVideoInfoVideoConfig.vue

@@ -122,7 +122,7 @@ const progress = computed(() => {
   if (videoType == ImageToVideoModels.MJ_VIDEO) {
     p = messageObject.progress ?? '0%'
   } else {
-    p = '0%'
+    p = undefined
   }
   return p
 })

src/renderer/src/components/MediaToVideo/MediaToVideoInfo/MediaToVideoSelectParentTask.vue

@@ -374,18 +374,9 @@ const props = defineProps({
   }
 })
 
-const videoList = computed(() => {
+const emit = defineEmits(['save-selection'])
-  console.log('未过滤的当前视频列表', props.videoList)
-  // 过滤掉没有本地路径的视频
-  return props.videoList.filter(
-    (video) =>
-      !isEmpty(video.localPath) &&
-      (video.type == ImageToVideoModels.MJ_VIDEO ||
-        video.type == ImageToVideoModels.MJ_VIDEO_EXTEND)
-  )
-})
-
 const videoMessage = ref({})
+const videoList = computed(() => props.videoList || [])
 
 const message = useMessage()
 
@@ -445,41 +436,9 @@ async function handleSaveMJVideoTaskSelection() {
       message.error(t('请选择一个视频'))
       return
     }
-
+    emit('save-selection', {
-    let taskId = currentVideoInfo.value.taskId
+      ...toRaw(currentVideoInfo.value)
-    let videoIndex = currentVideoInfo.value.index
-
-    console.log('当前选中的视频信息', taskId, videoIndex, currentSelectedVideo.value)
-    if (isEmpty(taskId) || videoIndex == null) {
-      message.error(t('当前选中的视频的 taskId 或 videoIndex 为空，请检查视频信息'))
-      return
-    }
-
-    // 开始修改实际的数据
-    let updateObject = {
-      mjVideoOptions: JSON.stringify({
-        ...videoMessage.value.mjVideoOptionsObject,
-        taskId: taskId,
-        index: videoIndex
     })
-    }
-    console.log('更新的实际数据', updateObject)
-
-    let res = await window.book.video.UpdateBookTaskDetailVideoMessage(
-      props.taskData.id,
-      updateObject
-    )
-
-    // 检查返回结果
-    if (res.code == 1) {
-      message.success(t('保存成功'))
-
-      videoMessage.value.mjVideoOptionsObject.taskId = taskId
-      videoMessage.value.mjVideoOptionsObject.index = videoIndex
-    } else {
-      message.error(t('保存失败：{error}', { error: res.message }))
-      return
-    }
   } catch (error) {
     message.error(t('保存失败：{error}', { error: error.message }))
   }

src/renderer/src/components/MediaToVideo/MediaToVideoInfoHome.vue

@@ -134,36 +134,40 @@ onMounted(async () => {
 onUnmounted(() => {
   // 清理事件监听
   window.system.removeEventListen([DEFINE_STRING.BOOK.MJ_VIDEO_TO_VIDEO_RETURN])
+  window.system.removeEventListen(DEFINE_STRING.BOOK.KLING_IMAGE_TO_VIDEO_RETURN)
 })
 
-function handleIpcTaskListChange() {
+// 接收到消息修改的处理小说批次任务信息的逻辑
-  // 监听SD出图返回的数据
+function handleMessageChange(videoMessage, id) {
-  window.system.setEventListen([DEFINE_STRING.BOOK.MJ_VIDEO_TO_VIDEO_RETURN], (value) => {
+  let findIndex = bookStore.selectBookTaskDetail.findIndex((item) => item.id === id)
+  if (findIndex !== -1) {
+    bookStore.selectBookTaskDetail[findIndex].videoMessage.status = videoMessage.status
+    bookStore.selectBookTaskDetail[findIndex].videoMessage.taskId = videoMessage.taskId
+    bookStore.selectBookTaskDetail[findIndex].videoMessage.msg = videoMessage.msg
+    bookStore.selectBookTaskDetail[findIndex].videoMessage.messageData = videoMessage.messageData
+  }
+}
+
+function handleEventReceive(value) {
   try {
     if (value.type == ResponseMessageType.MJ_VIDEO) {
       // 正在执行中
       let videoMessage = JSON.parse(value.data)
       console.log('收到 mj video视频处理进度', videoMessage)
-        let findIndex = bookStore.selectBookTaskDetail.findIndex((item) => item.id === value.id)
+      handleMessageChange(videoMessage, value.id)
-        if (findIndex !== -1) {
-          bookStore.selectBookTaskDetail[findIndex].videoMessage.status = videoMessage.status
-          bookStore.selectBookTaskDetail[findIndex].videoMessage.taskId = videoMessage.taskId
-          bookStore.selectBookTaskDetail[findIndex].videoMessage.msg = videoMessage.msg
-          bookStore.selectBookTaskDetail[findIndex].videoMessage.messageData =
-            videoMessage.messageData
-        }
     } else if (value.type == ResponseMessageType.MJ_VIDEO_EXTEND) {
       // 正在执行中
       let videoMessage = JSON.parse(value.data)
       console.log('收到 mj video extend 视频处理进度', videoMessage)
-        let findIndex = bookStore.selectBookTaskDetail.findIndex((item) => item.id === value.id)
+      handleMessageChange(videoMessage, value.id)
-        if (findIndex !== -1) {
+    } else if (value.type == ResponseMessageType.KLING_VIDEO) {
-          bookStore.selectBookTaskDetail[findIndex].videoMessage.status = videoMessage.status
+      let videoMessage = JSON.parse(value.data)
-          bookStore.selectBookTaskDetail[findIndex].videoMessage.taskId = videoMessage.taskId
+      console.log('收到 Kling video extend 视频处理进度', videoMessage)
-          bookStore.selectBookTaskDetail[findIndex].videoMessage.msg = videoMessage.msg
+      handleMessageChange(videoMessage, value.id)
-          bookStore.selectBookTaskDetail[findIndex].videoMessage.messageData =
+    } else if (value.type == ResponseMessageType.KLING_VIDEO_EXTEND) {
-            videoMessage.messageData
+      let videoMessage = JSON.parse(value.data)
-        }
+      console.log('收到 Kling video extend 视频处理进度', videoMessage)
+      handleMessageChange(videoMessage, value.id)
     } else if (value.type == ResponseMessageType.VIDEO_SUCESS) {
       // 执行返回 返回全部的最新数据
       let bookTaskDetail = JSON.parse(value.data)
@@ -185,6 +189,16 @@ function handleIpcTaskListChange() {
   } catch (error) {
     message.error(t('处理数据时发生错误，{error}', { error: error.message }))
   }
+}
+
+function handleIpcTaskListChange() {
+  // 监听SD出图返回的数据
+  window.system.setEventListen([DEFINE_STRING.BOOK.MJ_VIDEO_TO_VIDEO_RETURN], (value) => {
+    handleEventReceive(value)
+  })
+
+  window.system.setEventListen(DEFINE_STRING.BOOK.KLING_IMAGE_TO_VIDEO_RETURN, (value) => {
+    handleEventReceive(value)
   })
 }
 

src/renderer/src/components/Original/BookTaskDetail/BookTaskDetailTable.vue

@@ -27,6 +27,7 @@ import DataTableAction from './DataTableAction.vue'
 import DatatableHeaderImage from './DatatableHeaderImage.vue'
 import DatatableHeaderCharacter from './DatatableHeaderCharacter.vue'
 import { t } from '@/i18n'
+import DatatableHeaderGptPrompt from './DatatableHeaderGptPrompt.vue'
 
 const bookStore = useBookStore()
 const softwareStore = useSoftwareStore()
@@ -94,7 +95,7 @@ const columns = computed(() => {
       // title(row) {
       //   return h(ODataTableHeaderGptPrompt)
       // },
-      title: t('提示词'),
+      title: () => h(DatatableHeaderGptPrompt, { bookTask: bookStore.selectBookTask }),
       key: 'gpt_prompt',
       className: 'empty-margin',
 
@@ -115,9 +116,6 @@ const columns = computed(() => {
       width: '300',
       minWidth: softwareStore.showCompletePrompt ? 300 : 0,
       className: 'empty-margin'
-      // render(row, index) {
-      //   return h(ODatatablePrompt, { initData: row, index: index })
-      // }
     },
     {
       // 参数

src/renderer/src/components/Original/BookTaskDetail/DatatableHeaderGptPrompt.vue

@@ -0,0 +1,115 @@
+<template>
+  <div style="display: flex">
+    <span style="margin-right: 5px">{{ t('提示词') }}</span>
+
+    <TooltipButton
+      size="tiny"
+      tertiary
+      type="primary"
+      :style="{ marginLeft: '10px' }"
+      @click="showModal = true"
+    >
+      {{ t('通用前/后缀') }}
+    </TooltipButton>
+
+    <n-modal
+      preset="dialog"
+      :mask-closable="false"
+      title="提示词前后缀设置"
+      v-model:show="showModal"
+      :show-icon="false"
+    >
+      <div style="padding: 16px 0">
+        <n-space vertical size="large">
+          <n-form v-model="data" label-width="80px">
+            <n-form-item :label="t('通用前缀')">
+              <n-input
+                v-model:value="data.prefix"
+                :placeholder="
+                  t('请输入 {data}', {
+                    data: t('通用前缀')
+                  })
+                "
+                clearable
+              />
+            </n-form-item>
+
+            <n-form-item :label="t('通用后缀')">
+              <n-input
+                v-model:value="data.suffix"
+                :placeholder="
+                  t('请输入 {data}', {
+                    data: t('通用后缀')
+                  })
+                "
+                clearable
+              />
+            </n-form-item>
+          </n-form>
+
+          <n-space justify="end">
+            <n-button @click="handleCancel">{{ t('取消') }}</n-button>
+            <n-button type="primary" @click="handleSave">{{ t('保存') }}</n-button>
+          </n-space>
+        </n-space>
+      </div>
+    </n-modal>
+  </div>
+</template>
+
+<script setup>
+import { TimeDelay } from '@/define/Tools/time'
+import { t } from '@/i18n'
+import { isEmpty } from 'lodash'
+
+const message = useMessage()
+
+const props = defineProps({
+  bookTask: {
+    type: Object,
+    required: true
+  }
+})
+
+const data = ref({
+  prefix: '',
+  suffix: ''
+})
+
+const showModal = ref(false)
+
+// 监听弹窗打开，初始化数据
+watch(showModal, (newVal) => {
+  if (newVal) {
+    data.value.prefix = props.bookTask?.prefixPrompt || ''
+    data.value.suffix = props.bookTask?.suffixPrompt || ''
+  }
+})
+
+const handleSave = async () => {
+  let updateObject = {}
+  if (!isEmpty(data.value.prefix)) {
+    updateObject['prefixPrompt'] = data.value.prefix
+  }
+  if (!isEmpty(data.value.suffix)) {
+    updateObject['suffixPrompt'] = data.value.suffix
+  }
+  // 开始实际更新
+  let res = await window.book.ModifyBookTaskDataById(props.bookTask.id, updateObject)
+
+  if (res.code != 1) {
+    message.error(t('保存失败：{error}', { error: res.message }))
+    return
+  }
+  message.success(t('保存成功'))
+  await TimeDelay(300)
+  // 保存成功后关闭弹窗
+  showModal.value = false
+}
+
+const handleCancel = () => {
+  // 关闭弹窗
+  showModal.value = false
+  message.info(t('取消操作'))
+}
+</script>

src/renderer/src/components/Original/BookTaskDetail/TopMenuButtons.vue

@@ -184,6 +184,14 @@ const promptOptions = ref([
   {
     label: '3. ' + t('重置所有提示词'),
     key: 'reset-all-prompt'
+  },
+  {
+    type: 'divider',
+    key: 'd5_2'
+  },
+  {
+    label: '4. ' + t('导入提示词'),
+    key: 'import-prompt'
   }
 ])
 
@@ -583,6 +591,78 @@ async function handleResetAllPrompt() {
   })
 }
 
+// 一键导入提示词
+async function handleImportPrompt() {
+  let da = dialog.warning({
+    title: t('操作确认'),
+    content: () =>
+      h(
+        'div',
+        { style: { whiteSpace: 'pre-line' } },
+        {
+          default: () =>
+            `该操作会选择 TXT 文件进行导入提示词，\n\n提示词文件格式要求：\n每行一个提示词，顺序和当前分镜顺序一致，\n如果某个分镜不需要导入提示词，可以留空该行，\n超出分镜的提示词会被删除，不足则只导入文本中有的提示词数据\n\n是否继续？`
+        }
+      ),
+    negativeText: t('取消'),
+    positiveText: t('继续'),
+    onPositiveClick: async () => {
+      da?.destroy()
+      await TimeDelay(200)
+      try {
+        // 选择文件
+        let fileRes = await window.system.SelectSingleFile(['txt'])
+        if (fileRes.code == 0) {
+          throw new Error(fileRes.message)
+        }
+        let filePath = fileRes.data
+
+        // 读取文件内容
+        let fileContentRes = await window.system.ReadTextFile(filePath)
+        if (fileContentRes.code == 0) {
+          throw new Error(fileContentRes.message)
+        }
+        let fileContent = fileContentRes.data.content
+        if (fileContent == null || fileContent == undefined || isEmpty(fileContent.trim())) {
+          throw new Error(t('导入的提示词文件内容为空'))
+        }
+
+        let lines = fileContent.split(/\r?\n/).map((line) => line.trim())
+
+
+        // 开始导入提示词
+        for (let i = 0; i < lines.length && i < bookStore.selectBookTaskDetail.length; i++) {
+          const element = lines[i]
+
+          // 开始导入和修改
+          let res = await window.book.ModifyBookTaskDetailById(
+            bookStore.selectBookTaskDetail[i].id,
+            {
+              gptPrompt: element
+            }
+          )
+          if (res.code != 1) {
+            throw new Error(
+              t('导入第 {line} 行提示词失败，{error}', { line: i + 1, error: res.message })
+            )
+          }
+          // 成功后更新本地数据
+          bookStore.selectBookTaskDetail[i].gptPrompt = element
+        }
+        message.success(t('导入提示词成功'))
+      } catch (error) {
+        softwareStore.spin.spinning = false
+        message.error(t('导入提示词失败，{error}', { error: error.message }))
+      }
+    },
+    onNegativeClick: () => {
+      message.info(t('取消操作'))
+    },
+    closable: true,
+    maskClosable: false
+  })
+}
+
 // 一键推理提示词的操作选择方法
 async function handlePromptSelect(key) {
   if (key === 'original-get-all-ai-prompt') {
@@ -597,6 +677,8 @@ async function handlePromptSelect(key) {
     )
   } else if (key == 'reset-all-prompt') {
     await handleResetAllPrompt()
+  } else if (key == 'import-prompt') {
+    await handleImportPrompt()
   } else {
     message.error(t('未知一键推理操作'))
   }

src/renderer/src/components/common/ConfigOptionGroup.vue

@@ -0,0 +1,480 @@
+<template>
+  <n-space vertical :size="12">
+    <!-- 验证错误提示 -->
+    <n-alert v-if="hasValidationErrors" type="error" closable>
+      <template #header>{{ t('配置验证失败') }}</template>
+      <div>
+        <div v-for="(error, index) in validationErrors" :key="index" style="margin-bottom: 4px">
+          • {{ error }}
+        </div>
+      </div>
+    </n-alert>
+
+    <!-- 循环渲染所有配置选项 -->
+    <template v-if="!hasValidationErrors">
+      <n-form-item
+        v-for="option in options"
+        :key="option.key"
+        :show-label="false"
+        :show-require-mark="false"
+        :show-feedback="false"
+      >
+        <div :class="['config-control', { 'full-width': option.fullWidth }]">
+          <div class="config-label">
+            <span>{{ option.label }}</span>
+
+            <!-- 帮助提示 -->
+            <n-tooltip
+              v-if="option.tooltip"
+              trigger="hover"
+              placement="top"
+              style="max-width: 300px"
+            >
+              <template #trigger>
+                <n-button size="small" quaternary circle>
+                  <template #icon>
+                    <n-icon>
+                      <HelpCircleOutline />
+                    </n-icon>
+                  </template>
+                </n-button>
+              </template>
+              <div style="line-height: 1.5" v-html="option.tooltip"></div>
+            </n-tooltip>
+          </div>
+
+          <!-- 根据类型渲染不同的控件 -->
+          <!-- 下拉选择器 -->
+          <n-select
+            v-if="option.type === 'select'"
+            :value="getOptionValue(option.key)"
+            :options="option.options"
+            :placeholder="
+              option.placeholder ||
+              t('请选择 {data}', {
+                data: option.label
+              })
+            "
+            @update-value="(value) => handleOptionChange(option.key, value)"
+            size="small"
+            :disabled="option.disabled || false"
+            :style="{ width: option.fullWidth ? '100%' : option.width || '140px' }"
+          />
+
+          <!-- 开关 -->
+          <n-switch
+            v-else-if="option.type === 'switch'"
+            :value="getOptionValue(option.key)"
+            size="small"
+            @update-value="(value) => handleOptionChange(option.key, value)"
+            :disabled="option.disabled || false"
+          >
+            <template #checked>{{ option.checkedText || t('是') }}</template>
+            <template #unchecked>{{ option.uncheckedText || t('否') }}</template>
+          </n-switch>
+
+          <!-- 数字输入 -->
+          <n-input-number
+            v-else-if="option.type === 'number'"
+            :value="getOptionValue(option.key)"
+            :show-button="false"
+            :step="option.step || 1"
+            :min="option.min"
+            :max="option.max"
+            :placeholder="option.placeholder"
+            @update-value="(value) => handleOptionChange(option.key, value)"
+            size="small"
+            :disabled="option.disabled || false"
+            :style="{ width: option.fullWidth ? '100%' : option.width || '100px' }"
+          />
+
+          <!-- 文本输入 -->
+          <div
+            v-else-if="option.type === 'input'"
+            class="form-item-with-suffix-button"
+            :style="{ width: option.fullWidth ? '100%' : 'auto' }"
+          >
+            <n-input
+              :value="getOptionValue(option.key)"
+              :type="option.inputType || 'text'"
+              :placeholder="option.placeholder"
+              :autosize="option.inputType === 'textarea' ? option.autosize : undefined"
+              @update-value="(value) => handleOptionChange(option.key, value)"
+              size="small"
+              :disabled="option.disabled || false"
+            />
+
+            <TooltipButton
+              v-if="option.suffixButton"
+              :type="option.suffixButton.type || 'primary'"
+              :size="option.suffixButton.size || 'small'"
+              :quaternary="option.suffixButton.quaternary ?? false"
+              :circle="option.suffixButton.circle ?? false"
+              :disabled="option.disabled || option.suffixButton.disabled || false"
+              ghost
+              :style="{ width: option.suffixButton.width || '80px' }"
+              :tooltip="option.suffixButton.tooltip"
+              @click="() => handleSuffixButtonClick(option)"
+            >
+              <template #icon v-if="option.suffixButton.icon">
+                <n-icon :size="option.suffixButton.iconSize || 16">
+                  <component :is="option.suffixButton.icon" />
+                </n-icon>
+              </template>
+              {{ option.suffixButton.text || '' }}
+            </TooltipButton>
+          </div>
+
+          <!-- 图片输入 -->
+          <div
+            v-else-if="option.type === 'image'"
+            class="input-with-preview"
+            :style="{ width: option.fullWidth ? '100%' : 'auto' }"
+          >
+            <n-input
+              :value="getOptionValue(option.key)"
+              :placeholder="option.placeholder || t('请输入图片链接')"
+              @update-value="(value) => handleOptionChange(option.key, value)"
+              size="small"
+              :disabled="option.disabled || false"
+              class="image-input"
+            >
+              <template #suffix>
+                <TooltipButton
+                  v-if="option.onUpload"
+                  size="tiny"
+                  quaternary
+                  @click="() => handleImageUpload(option)"
+                  :disabled="option.disabled || false"
+                  :tooltip="option.uploadTooltip || t('上传图片到LaiTool图床，获取图片链接')"
+                >
+                  <template #icon>
+                    <n-icon size="20">
+                      <svg
+                        xmlns="http://www.w3.org/2000/svg"
+                        xmlns:xlink="http://www.w3.org/1999/xlink"
+                        viewBox="0 0 24 24"
+                      >
+                        <g
+                          fill="none"
+                          stroke="currentColor"
+                          stroke-width="2"
+                          stroke-linecap="round"
+                          stroke-linejoin="round"
+                        >
+                          <path d="M4 17v2a2 2 0 0 0 2 2h12a2 2 0 0 0 2-2v-2"></path>
+                          <path d="M7 9l5-5l5 5"></path>
+                          <path d="M12 4v12"></path>
+                        </g>
+                      </svg>
+                    </n-icon>
+                  </template>
+                </TooltipButton>
+              </template>
+            </n-input>
+            <n-image
+              v-if="!isEmpty(getOptionValue(option.key))"
+              :src="getOptionValue(option.key)"
+              :height="option.previewHeight || 60"
+              :fallback-src="'data:image/svg+xml;base64,PHN2ZyB3aWR0aD0iMTAwIiBoZWlnaHQ9IjEwMCIgeG1sbnM9Imh0dHA6Ly93d3cudzMub3JnLzIwMDAvc3ZnIj4KICA8cmVjdCB3aWR0aD0iMTAwIiBoZWlnaHQ9IjEwMCIgZmlsbD0iI2Y1ZjVmNSIvPgogIDx0ZXh0IHg9IjUwIiB5PSI1MCIgZm9udC1mYW1pbHk9IkFyaWFsLCBzYW5zLXNlcmlmIiBmb250LXNpemU9IjEyIiBmaWxsPSIjOTk5IiB0ZXh0LWFuY2hvcj0ibWlkZGxlIiBkeT0iMC4zZW0iPuWbvueJh+WKoOi9veWksei0pTwvdGV4dD4KPC9zdmc+'"
+              object-fit="contain"
+              class="preview-image"
+              @error="() => handleImageError(option.key)"
+            />
+          </div>
+        </div>
+      </n-form-item>
+    </template>
+  </n-space>
+</template>
+
+<script setup>
+import {
+  NSpace,
+  NFormItem,
+  NSelect,
+  NSwitch,
+  NInputNumber,
+  NInput,
+  NButton,
+  NIcon,
+  NTooltip,
+  NAlert,
+  NImage} from 'naive-ui'
+import { HelpCircleOutline } from '@vicons/ionicons5'
+import { computed } from 'vue'
+import { t } from '@/i18n'
+import { isEmpty } from 'lodash'
+import TooltipButton from './TooltipButton.vue'
+
+// 定义 props
+const props = defineProps({
+  // 配置选项数组
+  options: {
+    type: Array,
+    required: true,
+    default: () => []
+    /*
+    选项格式示例：
+    [
+      {
+        key: 'videoType',           // 字段键名
+        label: '视频类型 (SD/HD)',   // 显示标签
+        type: 'select',             // 控件类型: select, switch, number, input, image
+        options: [...],             // select类型的选项数组
+        placeholder: '请选择',       // 占位符文本
+        tooltip: '帮助说明文本',     // 帮助提示内容，支持HTML
+        width: '140px',             // 控件宽度
+        // 以下为特定类型的配置
+        step: 0.1,                  // number类型的步长
+        min: 0,                     // number类型的最小值
+        max: 10,                    // number类型的最大值
+        inputType: 'textarea',      // input类型: text, textarea
+        autosize: { minRows: 2 },   // textarea的自动调整大小
+        checkedText: '开启',         // switch的选中文本
+        uncheckedText: '关闭',       // switch的未选中文本
+        // image类型的特定配置
+        onUpload: (currentValue, key) => {},  // 图片上传处理函数
+        uploadTooltip: '上传图片',   // 上传按钮的提示文字
+        previewHeight: 60,          // 图片预览高度
+        previewText: '图片预览',     // 预览占位符文字
+        fullWidth: false,           // 是否占满整行（换行显示）
+        disabled: false,            // 是否禁用该选项
+        suffixButton: {
+          text: string,          // 按钮文本
+          icon: Component,       // 图标组件
+          iconSize: number,      // 图标大小
+          type: string,          // 按钮类型 (primary, secondary等)
+          quaternary: boolean,   // 四级按钮样式
+          circle: boolean,       // 圆形按钮
+          disabled: boolean,     // 禁用状态
+          tooltip: string,       // 提示文本
+          width: string,         // 按钮宽度
+          onClick: Function      // 点击回调函数
+        }
+      }
+    ]
+    */
+  },
+
+  // 当前值对象
+  value: {
+    type: Object,
+    default: () => ({})
+  }
+})
+
+// 定义 emits
+const emit = defineEmits([
+  'update:value',
+  'change',
+  'image-upload',
+  'image-error',
+  'suffix-button-click'
+])
+
+// 验证选项配置完整性
+const validationErrors = computed(() => {
+  const errors = []
+
+  props.options.forEach((option, index) => {
+    if (!option.key) {
+      errors.push(`选项 ${index + 1}: 缺少必需的 key 属性`)
+    }
+
+    if (!option.label) {
+      errors.push(`选项 ${index + 1} (${option.key || '未知'}): 缺少必需的 label 属性`)
+    }
+
+    if (!option.type) {
+      errors.push(`选项 ${index + 1} (${option.key || '未知'}): 缺少必需的 type 属性`)
+    } else {
+      // 根据类型检查特定的必需属性
+      switch (option.type) {
+        case 'select':
+          if (!option.options || !Array.isArray(option.options) || option.options.length === 0) {
+            errors.push(`选项 ${index + 1} (${option.key}): select 类型需要 options 数组且不能为空`)
+          } else {
+            // 检查 options 数组中的项目格式
+            option.options.forEach((opt, optIndex) => {
+              if (
+                typeof opt !== 'object' ||
+                !opt.hasOwnProperty('value') ||
+                !opt.hasOwnProperty('label')
+              ) {
+                errors.push(
+                  `选项 ${index + 1} (${option.key}): options[${optIndex}] 必须包含 value 和 label 属性`
+                )
+              }
+            })
+          }
+          break
+
+        case 'number':
+          if (option.min !== undefined && option.max !== undefined && option.min > option.max) {
+            errors.push(`选项 ${index + 1} (${option.key}): min 值不能大于 max 值`)
+          }
+          if (option.step !== undefined && option.step <= 0) {
+            errors.push(`选项 ${index + 1} (${option.key}): step 值必须大于 0`)
+          }
+          break
+
+        case 'input':
+          if (option.inputType === 'textarea' && option.autosize) {
+            if (typeof option.autosize !== 'object') {
+              errors.push(`选项 ${index + 1} (${option.key}): textarea 的 autosize 必须是对象`)
+            } else if (
+              option.autosize.minRows !== undefined &&
+              option.autosize.maxRows !== undefined
+            ) {
+              if (option.autosize.minRows > option.autosize.maxRows) {
+                errors.push(`选项 ${index + 1} (${option.key}): autosize.minRows 不能大于 maxRows`)
+              }
+            }
+          }
+          break
+
+        case 'switch':
+          // switch 类型的检查（可选）
+          break
+
+        case 'image':
+          // image 类型的检查（可选）
+          if (option.onUpload && typeof option.onUpload !== 'function') {
+            errors.push(`选项 ${index + 1} (${option.key}): onUpload 必须是一个函数`)
+          }
+          if (
+            option.previewHeight !== undefined &&
+            (typeof option.previewHeight !== 'number' || option.previewHeight <= 0)
+          ) {
+            errors.push(`选项 ${index + 1} (${option.key}): previewHeight 必须是正数`)
+          }
+          break
+
+        default:
+          errors.push(`选项 ${index + 1} (${option.key}): 不支持的 type 类型 "${option.type}"`)
+      }
+    }
+  })
+
+  return errors
+})
+
+// 检查是否有验证错误
+const hasValidationErrors = computed(() => validationErrors.value.length > 0)
+
+// 获取选项值
+function getOptionValue(key) {
+  return props.value[key]
+}
+
+// 处理选项值变化
+function handleOptionChange(key, value) {
+  // 直接修改原对象，避免创建新对象导致的循环更新
+  if (props.value && typeof props.value === 'object') {
+    props.value[key] = value
+  }
+  // 可选：仍然触发事件用于业务逻辑处理
+  emit('change', key, value, props.value)
+}
+
+// 处理图片上传
+function handleImageUpload(option) {
+  const currentValue = getOptionValue(option.key)
+  if (option.onUpload && typeof option.onUpload === 'function') {
+    option.onUpload(option.key, currentValue)
+  } else {
+    // 如果没有自定义上传处理函数，触发事件
+    emit('image-upload', currentValue, option.key, option)
+  }
+}
+
+// 处理图片加载错误
+function handleImageError(key) {
+  emit('image-error', key, getOptionValue(key))
+}
+
+// 处理 suffix 按钮点击
+function handleSuffixButtonClick(option) {
+  const currentValue = getOptionValue(option.key)
+  if (option.suffixButton?.onClick && typeof option.suffixButton.onClick === 'function') {
+    option.suffixButton.onClick(option.key, currentValue, option)
+  } else {
+    // 如果没有自定义点击处理函数，触发事件
+    emit('suffix-button-click', option.key, currentValue, option)
+  }
+}
+</script>
+
+<style scoped>
+.config-control {
+  display: flex;
+  align-items: center;
+  justify-content: space-between;
+  width: 100%;
+}
+
+.config-control.full-width {
+  flex-direction: column;
+  align-items: flex-start;
+  gap: 8px;
+}
+
+.config-label {
+  display: flex;
+  align-items: center;
+  justify-self: center;
+  gap: 6px;
+  font-size: 14px;
+}
+
+/* 图片输入相关样式 */
+.input-with-preview {
+  display: flex;
+  align-items: center;
+  gap: 12px;
+  width: 100%;
+}
+
+.image-input {
+  flex: 1;
+}
+
+.preview-image {
+  width: auto;
+  height: 100%;
+  max-width: 100%;
+  object-fit: contain;
+}
+
+.preview-placeholder {
+  display: flex;
+  align-items: center;
+  justify-content: center;
+  width: 60px;
+  height: 60px;
+  border: 1px solid #e0e0e6;
+  background-color: #fafafa;
+  border-radius: 4px;
+}
+
+.placeholder-text {
+  font-size: 12px;
+}
+
+.form-item-with-suffix-button {
+  display: flex;
+  align-items: stretch;
+  gap: 8px;
+}
+
+.form-item-with-suffix-button .n-input {
+  flex: 1;
+}
+
+.form-item-with-suffix-button .n-button {
+  flex-shrink: 0;
+  min-width: 80px;
+  align-self: stretch;
+}
+</style>

src/renderer/src/components/common/Icon/PointRightIcon.vue

@@ -0,0 +1,12 @@
+<template>
+  <svg
+    xmlns="http://www.w3.org/2000/svg"
+    xmlns:xlink="http://www.w3.org/1999/xlink"
+    viewBox="0 0 512 512"
+  >
+    <path
+      d="M428.8 137.6h-86.177a115.52 115.52 0 0 0 2.176-22.4c0-47.914-35.072-83.2-92-83.2c-45.314 0-57.002 48.537-75.707 78.784c-7.735 12.413-16.994 23.317-25.851 33.253l-.131.146l-.129.148C135.662 161.807 127.764 168 120.8 168h-2.679c-5.747-4.952-13.536-8-22.12-8H32c-17.673 0-32 12.894-32 28.8v230.4C0 435.106 14.327 448 32 448h64c8.584 0 16.373-3.048 22.12-8h2.679c28.688 0 67.137 40 127.2 40h21.299c62.542 0 98.8-38.658 99.94-91.145c12.482-17.813 18.491-40.785 15.985-62.791A93.148 93.148 0 0 0 393.152 304H428.8c45.435 0 83.2-37.584 83.2-83.2c0-45.099-38.101-83.2-83.2-83.2zm0 118.4h-91.026c12.837 14.669 14.415 42.825-4.95 61.05c11.227 19.646 1.687 45.624-12.925 53.625c6.524 39.128-10.076 61.325-50.6 61.325H248c-45.491 0-77.21-35.913-120-39.676V215.571c25.239-2.964 42.966-21.222 59.075-39.596c11.275-12.65 21.725-25.3 30.799-39.875C232.355 112.712 244.006 80 252.8 80c23.375 0 44 8.8 44 35.2c0 35.2-26.4 53.075-26.4 70.4h158.4c18.425 0 35.2 16.5 35.2 35.2c0 18.975-16.225 35.2-35.2 35.2zM88 384c0 13.255-10.745 24-24 24s-24-10.745-24-24s10.745-24 24-24s24 10.745 24 24z"
+      fill="currentColor"
+    ></path>
+  </svg>
+</template>

src/renderer/src/hooks/useFile.ts

@@ -1,20 +1,73 @@
-import { useMessage } from 'naive-ui'
+import { t } from '@/i18n'
+import { useMessage, useDialog } from 'naive-ui'
+import { useSoftwareStore } from '@renderer/stores'
+import { h } from 'vue'
 
 export function useFile() {
 
   const message = useMessage()
+  const dialog = useDialog()
+  const softwareStore = useSoftwareStore()
 
-  async function UploadImageToLaiTool(imagePath: string, type: "video" | "image") {
+  /**
-
+   * 上传图片到 LaiTool 云端
-    // 开始上传
+   * @param imagePath 图片路径
-    let res = await window.system.UploadImageToLaiTool(imagePath, type)
+   * @param type 文件类型
-    if (res.code != 1) {
+   * @returns Promise<string | null> 返回上传成功的 URL，用户取消或失败返回 null
-      message.error(res.message)
+   */
-      return;
+  async function UploadImageToLaiTool(
+    imagePath: string, 
+    type: "video" | "image"
+  ): Promise<string | null> {
+    return new Promise((resolve) => {
+      let da = dialog.warning({
+        title: t('操作确认'),
+        content: () =>
+          h(
+            'div',
+            {
+              style: { whiteSpace: 'pre-line' }
+            },
+            {
+              default: () =>
+                t(
+                  '是否上传图片文件到LaiTool云端？\n\n上传后会返回一个全球可分享的网络链接地址，但是每日限制五十次上传。上传后的图片可用于MJ垫图，转视频等功能。\n\n注意：上传后的图片会再Laitool服务器留存，若介意请勿上传。'
+                )
             }
-    let url = res.data.url;
+          ),
-    return url;
+        positiveText: t('继续'),
+        negativeText: t('取消'),
+        onPositiveClick: async () => {
+          da?.destroy()
+          try {
+            softwareStore.spin.spinning = true
+            softwareStore.spin.tip = t('开始上传文件...')
 
+            let res = await window.system.UploadImageToLaiTool(imagePath, type)
+            
+            if (res.code !== 1) {
+              message.error(res.message || t('上传失败'))
+              resolve(null)
+              return
+            }
+            
+            const url = res.data.url
+            resolve(url)
+          } catch (error) {
+            const err = error as Error
+            message.error(err.message)
+            resolve(null)
+          } finally {
+            softwareStore.spin.spinning = false
+          }
+        },
+        onNegativeClick: () => {
+          da?.destroy()
+          message.info(t('取消操作'))
+          resolve(null) // 用户取消也返回 null
+        }
+      })
+    })
   }
 
   return {