diff --git a/.claude/skills/config.json b/.claude/skills/config.json index 96e2a27..7674927 100644 --- a/.claude/skills/config.json +++ b/.claude/skills/config.json @@ -1,6 +1,6 @@ { - "jianyingDraftPath": "/Users/lc/Movies/JianyingPro/User Data/Projects/com.lveditor.draft", - "capcutMateDir": "/Users/lc/capcut-mate", + "jianyingDraftPath": "C:/Users/45070/AppData/Local/JianyingPro/User Data/Projects/com.lveditor.draft", + "capcutMateDir": "C:/Users/45070/capcut-mate", "capcutMateApiBase": "http://capcut.muyetools.cn/openapi/capcut-mate/v1", "imgbbApiKey": "deprecated", "geminiApiBaseUrl": "https://yunwu.ai", diff --git a/.claude/skills/video-from-script/SKILL.md b/.claude/skills/video-from-script/SKILL.md index b104d55..c9001a9 100644 --- a/.claude/skills/video-from-script/SKILL.md +++ b/.claude/skills/video-from-script/SKILL.md @@ -35,14 +35,15 @@ B 模式又分两种：**单图模式**（1 图 → 1 段视频）/ **首尾帧 ### 核心约束 1. **不可跳步**： - - A（幻灯片）：分镜 → 图片提示词 → 生图 → TTS+成片。无视频阶段 - - B（AI视频）：分镜 → 图片提示词 → 生图 → 视频提示词 → 生视频 → TTS+成片 + - A（幻灯片）：分镜 → manifest init → 图片提示词 → 生图 → TTS+成片。无视频阶段 + - B（AI视频）：分镜 → manifest init → 图片提示词 → 生图 → 视频提示词 → 生视频 → TTS+成片 - 阶段之间必须审查 -2. **manifest.json 是唯一状态源**：任何操作完成后立即回写 +2. **manifest.json 是唯一状态源**：`pipeline.js init` 在分镜确认后立即执行，创建 `output/{name}/` 目录和初始 manifest。后续所有子 Agent 输出回写此 manifest，不再传裸 JSON 3. **禁止 curl 调 API**：生图/生视频必须通过 `pipeline.js` 或对应 generator 脚本 4. **并行优先**：独立子任务用子 Agent 并行 5. **分镜表是脊骨契约**：用户确认分镜表后，下游子 Agent 只能加字段，禁止改 shot 数量/顺序/字段值。主 Agent 每次接收子 Agent 输出，第一件事数数量是否对得上 6. **prompts/*.md 只被子 Agent 读**：主 Agent 读 account.json，不读子 Agent 提示词模板 +7. **中间产物落 output**：所有中间文件（items JSON、urls 缓存、子 Agent 输出）必须写入 `output/{name}/` 目录，禁止散落在项目根目录 ### Step -1: 意图确认（逐项确认，缺一不可） @@ -79,26 +80,27 @@ B 模式又分两种：**单图模式**（1 图 → 1 段视频）/ **首尾帧 → 展示给用户确认。确认后**分镜表锁定为脊骨契约**，下游禁止增减 shot。 +### Step 2-0: Manifest 初始化 + +```bash +node scripts/pipeline.js init --account --mode \ + --items '[{"id":1,"shotDesc":"...","script":"...","duration":5,"directorRef":"tarantino","keyword":"权力"}]' +``` + +- 分镜确认后立即执行，创建 `output/{name}/` 目录和初始 `manifest.json` +- 脚本从 account.json 继承：imageModel、videoModel、format、references +- `imagePrompt` 暂为空，Step 2-A 补充；`videoPrompt` 暂为空，Step 3-A 补充 +- 输出路径打印到控制台，后续所有操作以此为工作目录 + ### Step 2-A: 图片提示词（子 Agent 执行） -- 主 Agent 传**完整分镜表 JSON**（不传原始文案）+ 图片提示词模板路径给子 Agent -- 子 Agent 为每个 shot 追加 `imagePrompt` 字段： - - 入参（来自分镜表）：shotDesc + script + directorRef + keyword - - 出参：分镜表 JSON + imagePrompt +- 主 Agent 传**manifest 路径 + 图片提示词模板路径**给子 Agent +- 子 Agent 读 manifest.items，为每个 shot 追加 `imagePrompt` 字段后回写 manifest - **硬约束：输出 shot 数量 == 输入 shot 数量** **主 Agent 审查**：① 数量对得上？② shotDesc 内容完整保留？③ 光影策略对应 directorRef？ -### Step 2-B: 生图 + Manifest 初始化 - -```bash -node scripts/pipeline.js init --account --mode \ - --items '[{"shotDesc":"...","script":"...","duration":5,"imagePrompt":"...","directorRef":"tarantino","keyword":"权力"}]' -``` - -- items 不含 videoPrompt，后续 Step 3-A 补充 -- 脚本从 account.json 继承：imageModel、videoModel、format、references -- 首尾帧模式：每个 item 必须有 `lastFramePrompt` +### Step 2-B: 生图 ```bash node scripts/pipeline.js run --manifest --phase images @@ -111,12 +113,9 @@ node scripts/pipeline.js run --manifest --phase images ### Step 3-A: 视频提示词（B 模式专属，子 Agent 执行） -- 主 Agent 传分镜表 JSON（含已确认分镜图路径）+ 视频提示词模板路径给子 Agent -- 子 Agent 为每个 shot 生成 `videoPrompt`： - - 入参：shotDesc + directorRef + 已确认分镜图 + 目标模型 - - 出参：videoPrompt（描述镜头运动，非画面内容） +- 主 Agent 传**manifest 路径 + 视频提示词模板路径**给子 Agent +- 子 Agent 读 manifest.items（含已确认分镜图路径），为每个 shot 生成 `videoPrompt` 后回写 manifest - **硬约束：输出数量 == 分镜表 shot 数量** -- Agent 按 id 对齐回写 manifest.json **主 Agent 审查**：① 数量对得上？② 描述运动而非内容？③ 字数 ≤ 50？ diff --git a/.claude/skills/video-from-script/references/manifest-schema.md b/.claude/skills/video-from-script/references/manifest-schema.md index b03d9a8..f8ad840 100644 --- a/.claude/skills/video-from-script/references/manifest-schema.md +++ b/.claude/skills/video-from-script/references/manifest-schema.md @@ -9,9 +9,9 @@ ## 创建方式 ```bash -# Step 2-A 生成 imagePrompt 后，通过脚本初始化（不含 videoPrompt） +# Step 2-0：分镜确认后立即初始化（imagePrompt/videoPrompt 后续补充） node scripts/pipeline.js init --account 军事账号 --mode single \ - --items '[{"shotDesc":"英文画面描述","script":"中文口播文案","duration":5,"imagePrompt":"English prompt","directorRef":"tarantino","keyword":"权力"}]' + --items '[{"shotDesc":"英文画面描述","script":"中文口播文案","duration":5,"directorRef":"tarantino","keyword":"权力"}]' # 或从文件读取 node scripts/pipeline.js init --account 军事账号 --mode single --items-file ./items.json @@ -193,7 +193,7 @@ node scripts/pipeline.js run --manifest --retry-failed ## 目录结构 ``` -output/{account}_{YYYYMMDD}_{NNN}/ +output/{name}_{YYYYMMDD}_{NNN}/ ├── manifest.json # 主清单 ├── images/ # scene_{NN}_{slug}.jpeg（首尾帧加 _last，MJ 候选加 _cand{1-4}） ├── videos/ # scene_{NN}_{slug}.mp4 @@ -206,7 +206,7 @@ slug 从 `shotDesc` 派生（slugify: 保留中文和字母数字，最多 20 ## segments[] 字段（TTS 分句） -TTS 阶段自动生成。仅当 `script` 被切分为 2 句及以上时才写入。单句时不写 segments。 +TTS 阶段统一生成，单句时数组仅 1 个元素，多句时 N 个元素。assemble 阶段直接使用各 segment 的实际音频时长对齐字幕。 | 字段 | 说明 | |------|------| @@ -214,4 +214,26 @@ TTS 阶段自动生成。仅当 `script` 被切分为 2 句及以上时才写入 | `audio` | 该句音频路径（相对 manifest） | | `duration` | 该句音频时长（秒） | -`item.audio` 指向所有分段合并后的完整音频，`item.audioDuration` 为各段累计时长。assemble 阶段优先用 `segments` 的精确时长对齐字幕，无 segments 时回退到字数权重估算。 +`item.audio` 指向 `segments[0].audio`，`item.audioDuration` 为各段累计时长。assemble 阶段遍历 segments 逐一添加音频和字幕，使用实际文件时长（非比例分配），确保音频与字幕精确同步，消除留白。 + +--- + +## 成片时间线规则 + +### 图片模式（images） + +图片没有独立时长。TTS 音频时长 = 画面时长。无 TTS 音频的 item 时长为 0（跳过，不显示）。 + +### 视频模式（videos） + +TTS 音频为主轴，视频通过以下策略适配音频时长： + +| ratio = videoDur/audioDur | 策略 | 说明 | +|---------------------------|------|------| +| 0.9 ~ 1.1 | none | 接近匹配，无需调整 | +| > 1.1, ≤ 2 | speed_up | 加速（setpts 压缩时间） | +| > 2 | trim | 裁剪（截断到音频时长） | +| < 0.9, ≥ 0.5 | slow_down | 放缓（setpts 拉长时间） | +| < 0.5 | freeze | 画面停顿（视频原速 + 最后一帧冻结补时长） | + +所有策略失败后兜底：截断到目标时长。 diff --git a/.claude/skills/video-from-script/scripts/capcut_assemble.js b/.claude/skills/video-from-script/scripts/capcut_assemble.js index 2fd21e0..8bfb691 100644 --- a/.claude/skills/video-from-script/scripts/capcut_assemble.js +++ b/.claude/skills/video-from-script/scripts/capcut_assemble.js @@ -215,28 +215,89 @@ function getAudioDurationSec(filePath) { // 主流程 // ============================================================================ -function buildTimeline(items, defaultDurationUs) { - // 音频为主轴，视频调速适配（≤2x 加速，>2x 截断） +function buildTimeline(items) { + // 核心规则： + // 图片模式：图片没有独立时长，TTS 音频时长 = 画面时长。无音频 = 0 时长（跳过） + // 视频模式：TTS 为主轴，视频通过 裁剪/加速/放缓/停顿 适配 + // 视频比音频长（ratio > 1.1）: + // ≤ 2x → 加速（setpts 压缩时间） + // > 2x → 裁剪（截断到音频时长） + // 视频比音频短（ratio < 0.9）: + // ≥ 0.5x → 放缓（setpts 拉长时间，≤2x慢速） + // < 0.5x → 画面停顿（视频正常播放+最后一帧冻结补时长） let offset = 0 return items.map(item => { - const audioDur = (item.audioDuration != null) ? item.audioDuration * US : 0 + // 有 segments 时用各段实际时长之和（精确对齐音频文件） + let audioDur + if (item.segments && item.segments.length > 0) { + audioDur = item.segments.reduce((sum, s) => sum + (s.duration || 0), 0) * US + } else { + audioDur = (item.audioDuration != null) ? item.audioDuration * US : 0 + } const videoDur = (item.videoDuration != null) ? item.videoDuration * US : 0 - // 无 TTS：用视频时长或固定时长 + const hasVideo = !!(item.video || item.videoUrl || item.url) + + // 无 TTS 音频 if (audioDur <= 0) { - const dur = videoDur || defaultDurationUs - const entry = { start: offset, end: offset + dur, duration: dur, speed: 1 } + if (hasVideo && videoDur > 0) { + // 视频模式无音频：用视频原始时长 + const entry = { start: offset, end: offset + videoDur, duration: videoDur, speed: 1, strategy: 'none' } + offset += videoDur + return entry + } + // 图片模式无音频：0 时长，标记跳过 + const entry = { start: offset, end: offset, duration: 0, speed: 1, strategy: 'none', skip: true } + return entry + } + + // 有 TTS：音频时长为主轴 + const dur = audioDur + + if (!hasVideo || videoDur <= 0) { + // 图片模式：直接用音频时长 + const entry = { start: offset, end: offset + dur, duration: dur, speed: 1, strategy: 'none' } + offset += dur + return entry + } + + // 视频模式：视频 vs 音频时长匹配 + const ratio = videoDur / audioDur + + if (ratio > 1.1) { + // 视频比音频长 + if (ratio <= 2) { + // 加速策略 + const entry = { start: offset, end: offset + dur, duration: dur, speed: ratio, strategy: 'speed_up' } + offset += dur + return entry + } else { + // 裁剪策略 + const entry = { start: offset, end: offset + dur, duration: dur, speed: 1, strategy: 'trim' } + offset += dur + return entry + } + } else if (ratio < 0.9) { + // 视频比音频短 + if (ratio >= 0.5) { + // 放缓策略（慢放 ≤2x） + const entry = { start: offset, end: offset + dur, duration: dur, speed: ratio, strategy: 'slow_down' } + offset += dur + return entry + } else { + // 画面停顿策略（视频原速播放 + 最后一帧冻结补时长） + const entry = { + start: offset, end: offset + dur, duration: dur, speed: 1, + strategy: 'freeze', freezeExtra: dur - videoDur, + } + offset += dur + return entry + } + } else { + // 接近匹配（0.9 ~ 1.1），无需调整 + const entry = { start: offset, end: offset + dur, duration: dur, speed: 1, strategy: 'none' } offset += dur return entry } - // 有 TTS：音频时长为主轴 - const dur = audioDur - const ratio = videoDur > 0 ? videoDur / audioDur : 1 - // ≤2x: 加速到音频时长；>2x: 截断（视频只取前 audioDur 部分） - const speed = ratio <= 2 ? ratio : 1 - const needAdjust = videoDur > audioDur + 100000 // 视频比音频长 0.1s 以上才需要调整 - const entry = { start: offset, end: offset + dur, duration: dur, speed, needAdjust } - offset += dur - return entry }) } @@ -253,7 +314,6 @@ async function assemble(args) { filter: filterStr, format = '9:16', apiKey = '', - duration = '4', animation = '轻微放大', } = args @@ -284,22 +344,44 @@ async function assemble(args) { } const { width, height } = getResolution(format) - const defaultDurationUs = parseFloat(duration) * US // 过滤出实际存在的文件 + const missingFileItems = [] const items = manifest.items.filter(item => { if (item.url) return true // 视频模式可能用 URL + if (item.video) return true // 视频模式本地文件 + if (!item.file) { + missingFileItems.push(item.id || '?') + return false + } const filePath = path.join(inputDir, item.file) return fs.existsSync(filePath) }) + if (items.length === 0) { + if (missingFileItems.length > 0) { + throw new Error(`没有可用的素材文件 — ${missingFileItems.length} 个 item 缺少 file 字段（id: ${missingFileItems.join(', ')}），请先运行 images 阶段`) + } + throw new Error('没有可用的素材文件') + } + if (items.length === 0) throw new Error('没有可用的素材文件') // 用 ffprobe 测量实际音频/视频时长，替代 manifest 中的估计值 let audioMeasured = 0, videoMeasured = 0 for (const item of items) { - // 测量 TTS 音频实际时长（有 segments 时跳过，audioDuration 已是精确累计值） - if (item.audio && !item.audio.startsWith('http') && !item.segments) { + // 测量各 segment 音频文件实际时长 + if (item.segments && item.segments.length > 0) { + for (const seg of item.segments) { + if (!seg.audio || seg.audio.startsWith('http')) continue + const audioPath = path.isAbsolute(seg.audio) + ? seg.audio + : path.resolve(inputDir, seg.audio) + if (!fs.existsSync(audioPath)) continue + const actualDur = await getAudioDurationSec(audioPath) + if (actualDur != null) { seg.duration = actualDur; audioMeasured++ } + } + } else if (item.audio && !item.audio.startsWith('http')) { const audioPath = path.isAbsolute(item.audio) ? item.audio : path.resolve(inputDir, item.audio) @@ -323,16 +405,32 @@ async function assemble(args) { console.log(` 实际时长测量: 音频 ${audioMeasured} 个, 视频 ${videoMeasured} 个`) } - const timeline = buildTimeline(items, defaultDurationUs) + const timeline = buildTimeline(items) const totalDurationUs = timeline.length > 0 ? timeline[timeline.length - 1].end : 0 const hasTTS = items.some(item => item.audio && item.audioDuration != null) + // 时间轴诊断 + for (let i = 0; i < items.length; i++) { + const item = items[i] + const tl = timeline[i] + if (tl.skip) { console.log(` [${i + 1}] 跳过（无音频）`); continue } + const audioDur = item.segments + ? item.segments.reduce((s, seg) => s + (seg.duration || 0), 0) + : (item.audioDuration || 0) + const slotDur = tl.duration / US + const diff = slotDur - audioDur + const videoDur = (item.videoDuration || 0) + const stratInfo = tl.strategy && tl.strategy !== 'none' ? ` 策略=${tl.strategy}` : '' + const marker = Math.abs(diff) > 0.05 ? ' ⚠️ 不对齐' : '' + console.log(` [${i + 1}] 画面=${slotDur.toFixed(2)}s 音频=${audioDur.toFixed(2)}s 视频=${videoDur.toFixed(2)}s${stratInfo}${marker}`) + } + // -- 读取转场策略（在 addImages/addVideos 之前） -- const transitionConfig = loadTransitions(manifest) console.log(`\nCapCut 成片组装`) console.log(` 模式: ${mode} 画幅: ${format} (${width}x${height})`) - console.log(` 时间线: ${hasTTS ? 'TTS音频驱动' : `固定${duration}s/段`} 总时长: ${(totalDurationUs / US).toFixed(1)}s`) + console.log(` 时间线: ${hasTTS ? 'TTS音频驱动' : '视频原始时长'} 总时长: ${(totalDurationUs / US).toFixed(1)}s`) console.log(` 字幕: ${subtitles} 配音: ${voiceover} 动画: ${animation}`) if (finalEffects) console.log(` 特效: ${finalEffects}`) if (finalFilter) console.log(` 滤镜: ${finalFilter}`) @@ -386,10 +484,10 @@ async function assemble(args) { for (let i = 0; i < items.length; i++) { const item = items[i] const tl = timeline[i] - if (tl.needAdjust && item.video) { + if (tl.strategy && tl.strategy !== 'none' && item.video) { const videoPath = path.resolve(inputDir, item.video) const audioDur = tl.duration / US - const adjustedPath = await adjustVideoSpeed(videoPath, audioDur) + const adjustedPath = await adjustVideoSpeed(videoPath, audioDur, tl.strategy, tl.speed, tl.freezeExtra || 0) if (adjustedPath !== videoPath) { item.video = path.relative(inputDir, adjustedPath) item.videoDuration = audioDur @@ -398,7 +496,7 @@ async function assemble(args) { } } if (adjustedCount > 0) { - console.log(` 视频调速: ${adjustedCount}/${items.length} 个`) + console.log(` 视频调整: ${adjustedCount}/${items.length} 个`) } // Step 2: 上传（已调速的）视频到 OSS @@ -547,7 +645,7 @@ async function assemble(args) { console.log(` 草稿ID: ${draftId}`) console.log(` 总时长: ${(totalDurationUs / US).toFixed(1)}s`) console.log(` 素材数: ${items.length}`) - console.log(` 时间线: ${hasTTS ? 'TTS音频驱动' : '固定时长'}`) + console.log(` 时间线: ${hasTTS ? 'TTS音频驱动' : '视频原始时长'}`) if (mode === 'videos' && subtitles === 'false') { console.log(`\n >> 视频模式未加字幕，请在剪映中打开草稿 → 识别字幕 → 语音识别生成\n`) } @@ -713,54 +811,142 @@ async function addKenBurns(draftUrl, segmentIds, items, timeline, manifest) { // ============================================================================ /** - * ffmpeg 调速：将视频调整为指定时长 - * ratio <= 2x: 加速；ratio > 2x: 截断 - * 返回调整后的文件路径（调整失败则返回原路径） + * ffmpeg 视频调整：根据策略适配音频时长 + * + * 策略（按 ratio = videoDur / audioDur 选择）: + * speed_up (ratio > 1.1, ≤2x) → setpts 压缩时间（加速） + * trim (ratio > 2x) → 截断到目标时长 + * slow_down (ratio < 0.9, ≥0.5x) → setpts 拉长时间（慢放） + * freeze (ratio < 0.5x) → 视频原速 + 最后一帧冻结补时长 + * none (0.9~1.1) → 无需调整 + * + * 所有策略失败后兜底：截断到目标时长 + * + * 返回调整后的文件路径（失败则返回原路径） */ -async function adjustVideoSpeed(videoPath, targetDurationSec) { +async function adjustVideoSpeed(videoPath, targetDurationSec, strategy = 'none', speed = 1, freezeExtraUs = 0) { if (!fs.existsSync(videoPath)) return videoPath + if (strategy === 'none') return videoPath + + // 兜底截断：所有策略失败后的最终回退 + function fallbackTrim(cb) { + execFile('ffmpeg', [ + '-y', '-i', videoPath, + '-t', String(targetDurationSec), + '-c', 'copy', + videoPath.replace(/(\.\w+)$/, '_adj$1') + ], { timeout: 30000 }, (err) => { + if (err) { cb(videoPath); return } + cb(videoPath.replace(/(\.\w+)$/, '_adj$1')) + }) + } return new Promise((resolve) => { - // 先获取视频时长 execFile('ffprobe', [ '-v', 'quiet', '-show_entries', 'format=duration', '-of', 'csv=p=0', videoPath ], (err, stdout) => { - if (err) { resolve(videoPath); return } + if (err) { fallbackTrim(resolve); return } const videoDur = parseFloat(stdout.trim()) - if (!videoDur || videoDur <= 0 || videoDur <= targetDurationSec + 0.1) { - resolve(videoPath); return - } + if (!videoDur || videoDur <= 0) { fallbackTrim(resolve); return } - const ratio = videoDur / targetDurationSec const outPath = videoPath.replace(/(\.\w+)$/, '_adj$1') - if (ratio <= 2) { - // 加速：setpts=PTS/speed, atempo=speed (音频变速) - const speed = ratio.toFixed(3) - const atempo = Math.min(speed, 2.0) // atempo 单次上限 2.0 - execFile('ffmpeg', [ - '-y', '-i', videoPath, - '-filter_complex', `setpts=PTS/${speed}`, - '-an', - outPath - ], { timeout: 30000 }, (err) => { - if (err) { console.log(` 调速失败，使用原始视频: ${err.message}`); resolve(videoPath); return } - console.log(` 调速: ${videoDur.toFixed(1)}s → ${targetDurationSec.toFixed(1)}s (${speed}x)`) - resolve(outPath) - }) - } else { - // 截断：取前 targetDuration 秒 + if (strategy === 'trim') { execFile('ffmpeg', [ '-y', '-i', videoPath, '-t', String(targetDurationSec), '-c', 'copy', outPath ], { timeout: 30000 }, (err) => { - if (err) { console.log(` 截断失败，使用原始视频: ${err.message}`); resolve(videoPath); return } + if (err) { console.log(` 截断失败: ${err.message}`); resolve(videoPath); return } console.log(` 截断: ${videoDur.toFixed(1)}s → ${targetDurationSec.toFixed(1)}s`) resolve(outPath) }) + } else if (strategy === 'speed_up') { + const speedVal = speed.toFixed(3) + execFile('ffmpeg', [ + '-y', '-i', videoPath, + '-filter_complex', `setpts=PTS/${speedVal}`, + '-an', + outPath + ], { timeout: 30000 }, (err) => { + if (err) { + console.log(` 加速失败，兜底截断: ${err.message}`) + fallbackTrim(resolve) + return + } + console.log(` 加速: ${videoDur.toFixed(1)}s → ${targetDurationSec.toFixed(1)}s (${speedVal}x)`) + resolve(outPath) + }) + } else if (strategy === 'slow_down') { + const factor = (1 / speed).toFixed(3) + execFile('ffmpeg', [ + '-y', '-i', videoPath, + '-filter_complex', `setpts=PTS*${factor}`, + '-an', + outPath + ], { timeout: 30000 }, (err) => { + if (err) { + console.log(` 放缓失败，兜底截断: ${err.message}`) + fallbackTrim(resolve) + return + } + console.log(` 放缓: ${videoDur.toFixed(1)}s → ${targetDurationSec.toFixed(1)}s (${speed.toFixed(2)}x speed)`) + resolve(outPath) + }) + } else if (strategy === 'freeze') { + // 画面停顿：原速播放 + 最后一帧冻结补时长 + const freezeSec = freezeExtraUs / US + execFile('ffmpeg', [ + '-y', '-i', videoPath, + '-filter_complex', `tpad=stop=-1:stop_duration=${freezeSec.toFixed(3)}`, + '-an', + outPath + ], { timeout: 30000 }, (err) => { + if (err) { + // 回退方案：截取最后一帧 → 生成冻结帧视频 → concat 拼接 + console.log(` tpad freeze 失败，尝试 concat 方案: ${err.message}`) + const lastFrame = videoPath.replace(/(\.\w+)$/, '_lastframe.png') + const frozenVideo = videoPath.replace(/(\.\w+)$/, '_frozen.mp4') + execFile('ffmpeg', [ + '-y', '-sseof', '-0.1', '-i', videoPath, + '-frames:v', '1', lastFrame + ], { timeout: 10000 }, (err2) => { + if (err2) { console.log(` concat 方案也失败，兜底截断`); fallbackTrim(resolve); return } + execFile('ffmpeg', [ + '-y', '-loop', '1', '-i', lastFrame, + '-t', String(freezeSec.toFixed(3)), + '-pix_fmt', 'yuv420p', + '-vf', 'scale=trunc(iw/2)*2:trunc(ih/2)*2', + frozenVideo + ], { timeout: 15000 }, (err3) => { + if (err3) { + try { fs.unlinkSync(lastFrame) } catch (_) {} + console.log(` 冻结帧视频生成失败，兜底截断`) + fallbackTrim(resolve) + return + } + const concatList = path.join(path.dirname(videoPath), '_freeze_concat.txt') + fs.writeFileSync(concatList, `file '${videoPath}'\nfile '${frozenVideo}'\n`) + execFile('ffmpeg', [ + '-y', '-f', 'concat', '-safe', '0', '-i', concatList, + '-c', 'copy', outPath + ], { timeout: 30000 }, (err4) => { + try { fs.unlinkSync(lastFrame); fs.unlinkSync(frozenVideo); fs.unlinkSync(concatList) } catch (_) {} + if (err4) { console.log(` 拼接失败，兜底截断`); fallbackTrim(resolve); return } + console.log(` 画面停顿: ${videoDur.toFixed(1)}s + 冻结 ${freezeSec.toFixed(1)}s = ${targetDurationSec.toFixed(1)}s`) + resolve(outPath) + }) + }) + }) + return + } + console.log(` 画面停顿: ${videoDur.toFixed(1)}s + 冻结 ${freezeSec.toFixed(1)}s = ${targetDurationSec.toFixed(1)}s`) + resolve(outPath) + }) + } else { + resolve(videoPath) } }) }) @@ -829,8 +1015,8 @@ async function addVideos(draftUrl, inputDir, items, timeline, width, height, tra async function batchUploadAudio(inputDir, items) { const urls = {} for (const item of items) { - // 上传 segments 中的每段音频 - if (item.segments && item.segments.length > 1) { + // 上传所有 segment 音频文件 + if (item.segments && item.segments.length > 0) { for (const seg of item.segments) { if (!seg.audio || seg.audio.startsWith('http') || urls[seg.audio]) continue const filePath = path.isAbsolute(seg.audio) @@ -848,7 +1034,7 @@ async function batchUploadAudio(inputDir, items) { } } } - // 上传 item.audio（单段或 segments 的第一段） + // 上传 item.audio（向后兼容，segments[0].audio 通常等于此值） if (!item.audio || item.audio.startsWith('http')) { if (item.audio) urls[item.audio] = item.audio continue @@ -893,24 +1079,29 @@ async function addVoiceover(draftUrl, inputDir, items, timeline, audioUrls = {}) for (let i = 0; i < items.length; i++) { const item = items[i] const tl = timeline[i] - const segments = item.segments && item.segments.length > 1 ? item.segments : null - if (segments) { - // 多段音频：按 segment 逐段添加，使用精确时长 - const slots = distributeSegments(tl, segments) - - for (const slot of slots) { - const audioUrl = resolveAudio(slot.audio) + if (item.segments && item.segments.length > 0) { + // 逐段添加，每段使用实际音频文件时长（不做比例分配，消除留白） + let currentTime = tl.start + for (let si = 0; si < item.segments.length; si++) { + const seg = item.segments[si] + const audioUrl = resolveAudio(seg.audio) + const segDurUs = (seg.duration || 0) * US + if (segDurUs <= 0) continue + // 最后一段对齐 timeline 末尾，吃掉浮点误差 + const isLast = si === item.segments.length - 1 + const endTime = isLast ? tl.end : currentTime + segDurUs audioInfos.push({ audio_url: audioUrl, - start: slot.start, - end: slot.end, - duration: slot.duration, + start: currentTime, + end: endTime, + duration: endTime - currentTime, volume: 1.0, }) + currentTime = endTime } } else if (item.audio) { - // 单段音频：用实际音频时长，不超过 timeline 时长 + // 无 segments：用实际音频时长 const audioUrl = resolveAudio(item.audio) const audioDurUs = item.audioDuration ? item.audioDuration * US : tl.duration @@ -981,23 +1172,6 @@ function applyAnimationProps(cap, style = {}) { if (style.outAnimDuration) cap.out_animation_duration = style.outAnimDuration } -// segments 按比例分配到时间线（DRY helper） -function distributeSegments(tl, segments) { - const totalSegDur = segments.reduce((sum, s) => sum + (s.duration || 0) * US, 0) - if (totalSegDur <= 0) return [] - const tlDuration = tl.end - tl.start - let currentTime = tl.start - return segments.map((seg, idx) => { - const segDurUs = Math.round((seg.duration || 0) * US) - let duration = Math.round(tlDuration * (segDurUs / totalSegDur)) - if (idx === segments.length - 1) duration = tl.end - currentTime - duration = Math.max(duration, 100000) - const entry = { start: currentTime, end: currentTime + duration, duration, text: seg.text, audio: seg.audio } - currentTime += duration - return entry - }) -} - function loadAccountConfig(manifest) { const account = manifest.account if (!account) return {} @@ -1093,17 +1267,19 @@ async function addSubtitles(draftUrl, items, timeline, style = {}, split = false const tl = timeline[i] if (split) { - // 分句模式：优先用 segments（TTS 逐句生成的精确时长），回退到字数估算 - const segments = item.segments && item.segments.length > 1 ? item.segments : null - - if (segments) { - // 精确模式：用 segments 的实际音频时长 - const slots = distributeSegments(tl, segments) - - for (const slot of slots) { - const cap = { start: slot.start, end: slot.end, text: slot.text } + // 分句模式：优先用 segments 精确时长（与 addVoiceover 同步），回退到字数估算 + if (item.segments && item.segments.length > 0) { + let currentTime = tl.start + for (let si = 0; si < item.segments.length; si++) { + const seg = item.segments[si] + const segDurUs = (seg.duration || 0) * US + if (segDurUs <= 0) continue + const isLast = si === item.segments.length - 1 + const endTime = isLast ? tl.end : currentTime + segDurUs + const cap = { start: currentTime, end: endTime, text: seg.text } applyAnimationProps(cap, animStyle) captions.push(cap) + currentTime = endTime } } else { // 回退：字数权重估算 @@ -1246,7 +1422,6 @@ async function main() { console.log('选项:') console.log(' --mode images|videos 素材类型（默认 images）') console.log(' --format 9:16 画幅比例') - console.log(' --duration 4 默认每段时长/秒（无TTS时的fallback，默认 4）') console.log(' --voiceover true|false 是否添加TTS配音轨道（默认 true）') console.log(' --subtitles true|false 是否添加字幕（默认 true）') console.log(' --split-captions true|false 分句字幕模式（默认 true，按标点切分）') @@ -1256,12 +1431,12 @@ async function main() { console.log(' --apiKey 云渲染 API Key（可选）') console.log(' --manifest manifest.json 路径') console.log('') - console.log('时间线模式:') - console.log(' manifest.json 中每段包含 audio + duration → TTS音频驱动时间线') - console.log(' 无 audio/duration → 按 --duration 固定时长') - console.log('') - console.log('manifest.json 示例（TTS驱动）:') - console.log(' {"items":[{"file":"1.png","text":"文案","audio":"seg_1.mp3","duration":3.5}]}') + console.log('时间线规则:') + console.log(' 图片模式: TTS 音频时长 = 画面时长，无音频则跳过') + console.log(' 视频模式: TTS 为主轴，视频通过以下策略适配:') + console.log(' 视频比音频长 → 加速(≤2x) 或 裁剪(>2x)') + console.log(' 视频比音频短 → 放缓(≥0.5x) 或 画面停顿(<0.5x)') + console.log(' 所有策略失败 → 兜底截断') console.log('') console.log('配置:') console.log(' 请运行 node setup.js 生成配置') diff --git a/.claude/skills/video-from-script/scripts/lib/cmd-confirm.js b/.claude/skills/video-from-script/scripts/lib/cmd-confirm.js index add3142..33b2e33 100644 --- a/.claude/skills/video-from-script/scripts/lib/cmd-confirm.js +++ b/.claude/skills/video-from-script/scripts/lib/cmd-confirm.js @@ -5,21 +5,26 @@ const { loadManifest, saveManifest } = require('./pipeline-utils') function confirmManifest(options) { - const { manifest: manifestPath, all } = options + const { manifest: manifestPath, all, items: itemsStr } = options if (!manifestPath) { console.error('用法: pipeline.js confirm --manifest --all') + console.error(' pipeline.js confirm --manifest --items 1,3,5') process.exit(1) } - if (!all) { - console.error('错误: 必须指定 --all') + if (!all && !itemsStr) { + console.error('错误: 必须指定 --all 或 --items ') process.exit(1) } const manifest = loadManifest(manifestPath) + const targetIds = itemsStr + ? new Set(itemsStr.split(',').map(s => parseInt(s.trim(), 10)).filter(n => !isNaN(n))) + : null let count = 0 for (const item of manifest.items) { + if (targetIds && !targetIds.has(item.id)) continue if (item.file && item.status === 'done' && !item.confirmed) { item.confirmed = true count++ @@ -30,7 +35,8 @@ function confirmManifest(options) { const total = manifest.items.length const confirmed = manifest.items.filter(it => it.confirmed).length - console.log(`已确认: ${count} items（共 ${confirmed}/${total} 已确认）`) + const scope = targetIds ? `${Array.from(targetIds).join(',')}` : '全部' + console.log(`已确认: ${count} items（范围: ${scope}，共 ${confirmed}/${total} 已确认）`) } module.exports = { confirmManifest } diff --git a/.claude/skills/video-from-script/scripts/lib/cmd-init.js b/.claude/skills/video-from-script/scripts/lib/cmd-init.js index 8c87810..85849f0 100644 --- a/.claude/skills/video-from-script/scripts/lib/cmd-init.js +++ b/.claude/skills/video-from-script/scripts/lib/cmd-init.js @@ -6,7 +6,7 @@ const fs = require('fs') const path = require('path') -const { loadAccountConfig, saveManifest, ensureDir, ACCOUNTS_DIR, SKILLS_DIR } = require('./pipeline-utils') +const { loadAccountConfig, saveManifest, ensureDir, slugify, ACCOUNTS_DIR, SKILLS_DIR } = require('./pipeline-utils') function initManifest(options) { const { account: accountId, mode, items: itemsJson, itemsFile } = options @@ -40,7 +40,8 @@ function initManifest(options) { } // 校验必填字段 - const requiredFields = ['shotDesc', 'script', 'imagePrompt'] + const requiredFields = ['shotDesc', 'script'] + const optionalFields = ['imagePrompt', 'videoPrompt', 'lastFramePrompt'] const resolvedMode = mode || 'single' for (let i = 0; i < rawItems.length; i++) { @@ -52,8 +53,7 @@ function initManifest(options) { } } if (resolvedMode === 'framePair' && !item.lastFramePrompt) { - console.error(`错误: 首尾帧模式 items[${i}] 缺少 "lastFramePrompt"（imagePrompt 作为第一帧）`) - process.exit(1) + delete item.lastFramePrompt // 首尾帧模式 Step 2-A 补充 } } @@ -68,9 +68,11 @@ function initManifest(options) { // 构建 items const items = rawItems.map((raw, i) => { + const slug = slugify(raw.shotDesc || raw.script || `scene_${i + 1}`) const item = { id: i + 1, status: 'pending', + file: `images/scene_${String(i + 1).padStart(2, '0')}_${slug}.jpeg`, shotDesc: raw.shotDesc || '', script: raw.script || '', duration: raw.duration || 5, @@ -129,7 +131,13 @@ function initManifest(options) { console.log(` 画幅: ${manifest.format}, 模式: ${manifest.mode}`) console.log(` Items: ${items.length}`) console.log(` 参考图: ${references.length}`) - if (items.some(it => !it.videoPrompt)) { + if (items.some(it => !it.imagePrompt)) { + console.log(` ⚠ ${items.filter(it => !it.imagePrompt).length} 个 item 缺少 imagePrompt，请运行 Step 2-A（图片提示词）补充`) + } + if (resolvedMode === 'framePair' && items.some(it => !it.lastFramePrompt)) { + console.log(` ⚠ ${items.filter(it => !it.lastFramePrompt).length} 个 item 缺少 lastFramePrompt，请运行 Step 2-A 补充`) + } + if (items.some(it => !it.videoPrompt && resolvedMode !== 'framePair')) { console.log(` ⚠ ${items.filter(it => !it.videoPrompt).length} 个 item 缺少 videoPrompt，生视频阶段将跳过`) } console.log() diff --git a/.claude/skills/video-from-script/scripts/lib/cmd-validate.js b/.claude/skills/video-from-script/scripts/lib/cmd-validate.js index 64a69a0..a57f69d 100644 --- a/.claude/skills/video-from-script/scripts/lib/cmd-validate.js +++ b/.claude/skills/video-from-script/scripts/lib/cmd-validate.js @@ -41,6 +41,9 @@ function validateManifest(manifestPath) { if (item.status && !['pending', 'generating', 'done', 'failed'].includes(item.status)) { issues.push(`${prefix} status 无效: ${item.status}`) } + if (item.status === 'done' && !item.file && !item.video && !item.url) { + issues.push(`${prefix} status=done 但缺少 file/video/url（素材路径）`) + } }) } diff --git a/.claude/skills/video-from-script/scripts/lib/phase-assemble.js b/.claude/skills/video-from-script/scripts/lib/phase-assemble.js index 0488b8e..d0b3f9c 100644 --- a/.claude/skills/video-from-script/scripts/lib/phase-assemble.js +++ b/.claude/skills/video-from-script/scripts/lib/phase-assemble.js @@ -15,6 +15,14 @@ async function phaseAssemble(manifest, manifestPath, options) { const hasVideos = videoItems.length > 0 const mode = hasVideos ? 'videos' : 'images' + // 前置校验：图片模式下检查 file 字段 + if (mode === 'images') { + const missingFile = manifest.items.filter(it => !it.file) + if (missingFile.length > 0) { + throw new Error(`${missingFile.length} 个 item 缺少 file 字段（id: ${missingFile.map(it => it.id).join(', ')}），请先运行 images 阶段生成图片`) + } + } + const assembleArgs = { input: dir, manifest: manifestPath, @@ -22,7 +30,6 @@ async function phaseAssemble(manifest, manifestPath, options) { format: manifest.format || accountConfig.defaultFormat || '9:16', subtitles: mode === 'images' ? 'true' : 'false', voiceover: manifest.items.some(it => it.audio) ? 'true' : 'false', - duration: '4', animation: capcutConfig.animation || '渐显+放大', } diff --git a/.claude/skills/video-from-script/scripts/lib/phase-images.js b/.claude/skills/video-from-script/scripts/lib/phase-images.js index b4ff824..eda0621 100644 --- a/.claude/skills/video-from-script/scripts/lib/phase-images.js +++ b/.claude/skills/video-from-script/scripts/lib/phase-images.js @@ -17,7 +17,8 @@ async function phaseImages(manifest, manifestPath, options) { ensureDir(imagesDir) const items = manifest.items.filter(it => - (!it.status || it.status === 'pending' || it.status === 'generating') && it.imagePrompt + ((!it.status || it.status === 'pending' || it.status === 'generating') && it.imagePrompt) || + (it.status === 'done' && manifest.mode === 'framePair' && it.file && it.lastFramePrompt && !it.lastFrame) ) if (items.length === 0) { log('images', '无待处理 item，跳过'); return } @@ -45,6 +46,14 @@ async function phaseImages(manifest, manifestPath, options) { item.status = 'generating' saveManifest(manifestPath, manifest) + // 仅补 lastFrame：首帧已存在，跳过首帧生成 + if (item.file && manifest.mode === 'framePair' && item.lastFramePrompt && !item.lastFrame) { + log('images', `[${idx}] 补生成 lastFrame（首帧已有: ${item.file}）`) + await generateLastFrame(item, idx, manifest, dir, imagesDir, model, ratio, manifestPath) + saveManifest(manifestPath, manifest) + return { ok: true } + } + let result if (model === 'gemini') { result = await generateGemini(item, idx, dir, imagesDir, ratio, refs) diff --git a/.claude/skills/video-from-script/scripts/lib/phase-tts.js b/.claude/skills/video-from-script/scripts/lib/phase-tts.js index 16b9c85..0c34d80 100644 --- a/.claude/skills/video-from-script/scripts/lib/phase-tts.js +++ b/.claude/skills/video-from-script/scripts/lib/phase-tts.js @@ -2,7 +2,8 @@ * Phase: tts — 语音合成（逐句分句生成） * * 将每个 item 的 script 按标点切分为短句，每句单独生成 TTS 音频。 - * 结果写入 item.segments[]，实现字幕与语音精确对齐。 + * 统一写入 item.segments[]，单句时数组仅 1 个元素。 + * item.audio 指向第一段，item.audioDuration 为累计时长。 */ const path = require('path') @@ -29,47 +30,32 @@ async function phaseTts(manifest, manifestPath, options = {}) { try { const sentences = splitTextIntoSentences(fullText) + const segments = [] + let totalDuration = 0 - if (sentences.length <= 1) { - // 单句：不需要 segments，走原逻辑 - const { filePath, duration } = await synthesize(fullText, { + for (let j = 0; j < sentences.length; j++) { + const sentence = sentences[j] + const segId = `${item.id || idx}_${j + 1}` + const { filePath, duration } = await synthesize(sentence, { outputDir: audioDir, - id: item.id || idx, + id: segId, voice: manifest.ttsVoice || undefined, instruction: manifest.ttsInstruction || undefined, rate: manifest.ttsRate || undefined, }) - item.audio = path.relative(dir, filePath).replace(/\\/g, '/') - item.audioDuration = Math.round(duration * 1000) / 1000 - log('tts', `[${idx}/${items.length}] ${duration.toFixed(1)}s: ${fullText.substring(0, 30)}...`) - } else { - // 多句：逐句生成，写入 segments - const segments = [] - let totalDuration = 0 - - for (let j = 0; j < sentences.length; j++) { - const sentence = sentences[j] - const segId = `${item.id || idx}_${j + 1}` - const { filePath, duration } = await synthesize(sentence, { - outputDir: audioDir, - id: segId, - voice: manifest.ttsVoice || undefined, - instruction: manifest.ttsInstruction || undefined, - rate: manifest.ttsRate || undefined, - }) - segments.push({ - text: sentence, - audio: path.relative(dir, filePath).replace(/\\/g, '/'), - duration: Math.round(duration * 1000) / 1000, - }) - totalDuration += duration - } - - item.segments = segments - item.audio = segments[0].audio - item.audioDuration = Math.round(totalDuration * 1000) / 1000 - log('tts', `[${idx}/${items.length}] ${totalDuration.toFixed(1)}s (${segments.length}句): ${fullText.substring(0, 30)}...`) + segments.push({ + text: sentence, + audio: path.relative(dir, filePath).replace(/\\/g, '/'), + duration: Math.round(duration * 1000) / 1000, + }) + totalDuration += duration } + + // 统一使用 segments 数组（单句 = 1 元素，多句 = N 元素） + item.segments = segments + item.audio = segments[0].audio + item.audioDuration = Math.round(totalDuration * 1000) / 1000 + log('tts', `[${idx}/${items.length}] ${totalDuration.toFixed(1)}s (${segments.length}句): ${fullText.substring(0, 30)}...`) } catch (err) { item.status = 'failed' item.error = `TTS失败: ${err.message}` diff --git a/.claude/skills/video-from-script/scripts/lib/phase-upload.js b/.claude/skills/video-from-script/scripts/lib/phase-upload.js index 6fcb1d3..7b2b50b 100644 --- a/.claude/skills/video-from-script/scripts/lib/phase-upload.js +++ b/.claude/skills/video-from-script/scripts/lib/phase-upload.js @@ -1,7 +1,7 @@ /** * Phase: upload — OSS 上传 * - * 将生成的图片（含首尾帧）上传到 OSS，回写 url + * 将图片（含首尾帧）和视频上传到 OSS，回写 url / videoUrl */ const path = require('path') @@ -11,35 +11,64 @@ async function phaseUpload(manifest, manifestPath) { const dir = getManifestDir(manifestPath) const { uploadFile } = require('../oss-upload') - const items = manifest.items.filter(it => + // 图片（含首尾帧 first frame） + const imageItems = manifest.items.filter(it => it.status === 'done' && it.file && !it.url ) - if (items.length === 0) { log('upload', '无待上传 item，跳过'); return } + // 视频 + const videoItems = manifest.items.filter(it => + it.status === 'done' && it.video && !it.videoUrl + ) - log('upload', `共 ${items.length} 个文件`) + if (imageItems.length === 0 && videoItems.length === 0) { + log('upload', '无待上传文件，跳过') + return + } - for (let i = 0; i < items.length; i++) { - const item = items[i] - const filePath = path.resolve(dir, item.file) - try { - const { url } = await uploadFile(filePath) - item.url = url - log('upload', `[${i + 1}/${items.length}] ${item.file} → ${url.substring(0, 60)}...`) - } catch (err) { - item.error = `上传失败: ${err.message}` - log('upload', `[${i + 1}/${items.length}] 失败: ${err.message}`) - } - if (item.url && item.lastFrame && !item.lastFrameUrl) { - const lastPath = path.resolve(dir, item.lastFrame) + // 上传图片 + if (imageItems.length > 0) { + log('upload', `图片: ${imageItems.length} 个`) + for (let i = 0; i < imageItems.length; i++) { + const item = imageItems[i] + const filePath = path.resolve(dir, item.file) try { - const { url } = await uploadFile(lastPath) - item.lastFrameUrl = url - log('upload', `[${i + 1}/${items.length}] lastFrame → OK`) + const { url } = await uploadFile(filePath) + item.url = url + log('upload', ` [${i + 1}/${imageItems.length}] ${item.file} → OK`) } catch (err) { - log('upload', `[${i + 1}/${items.length}] lastFrame 上传失败: ${err.message}`) + item.error = `上传失败: ${err.message}` + log('upload', ` [${i + 1}/${imageItems.length}] 失败: ${err.message}`) } + // 首尾帧模式：上传 lastFrame + if (item.url && item.lastFrame && !item.lastFrameUrl) { + const lastPath = path.resolve(dir, item.lastFrame) + try { + const { url } = await uploadFile(lastPath) + item.lastFrameUrl = url + log('upload', ` [${i + 1}/${imageItems.length}] lastFrame → OK`) + } catch (err) { + log('upload', ` [${i + 1}/${imageItems.length}] lastFrame 上传失败: ${err.message}`) + } + } + saveManifest(manifestPath, manifest) + } + } + + // 上传视频 + if (videoItems.length > 0) { + log('upload', `视频: ${videoItems.length} 个`) + for (let i = 0; i < videoItems.length; i++) { + const item = videoItems[i] + const videoPath = path.resolve(dir, item.video) + try { + const { url } = await uploadFile(videoPath) + item.videoUrl = url + log('upload', ` [${i + 1}/${videoItems.length}] ${item.video} → OK`) + } catch (err) { + log('upload', ` [${i + 1}/${videoItems.length}] 失败: ${err.message}`) + } + saveManifest(manifestPath, manifest) } - saveManifest(manifestPath, manifest) } } diff --git a/.claude/skills/video-from-script/scripts/pipeline.js b/.claude/skills/video-from-script/scripts/pipeline.js index b290672..e87a965 100644 --- a/.claude/skills/video-from-script/scripts/pipeline.js +++ b/.claude/skills/video-from-script/scripts/pipeline.js @@ -112,13 +112,23 @@ function applyRetryFailed(manifest, phases) { for (const item of manifest.items) { if (item.status === 'failed' || item.status === 'partial') { if (item.url && item.videoPrompt && !item.video) { + // 图片已上传但视频未生成 → 直接重试视频阶段 item.status = 'done' item.error = '' resetCount++ } else if (!item.url && item.imagePrompt) { - item.status = 'pending' - item.error = '' - resetCount++ + // 图片未上传 → 重试图片阶段 + // 如果首帧已存在但 lastFrame 失败，只重置 lastFrame 相关 + if (item.file && manifest.mode === 'framePair' && !item.lastFrame) { + item.status = 'done' // 保留首帧，只补 lastFrame + item.error = '' + resetCount++ + } else { + item.status = 'pending' + item.error = '' + delete item.file // 清除旧文件引用，避免重复 + resetCount++ + } } } } @@ -128,7 +138,7 @@ function applyRetryFailed(manifest, phases) { } } if (phases.includes('images')) { - if (manifest.items.some(it => !it.status || it.status === 'pending')) { + if (manifest.items.some(it => (!it.status || it.status === 'pending') || (it.status === 'done' && manifest.mode === 'framePair' && !it.lastFrame))) { manifest.pipeline.phases.images = 'pending' } } @@ -159,7 +169,6 @@ function parseArgs(argv) { else if (argv[i] === '--image-model' && argv[i + 1]) args.imageModel = argv[++i] else if (argv[i] === '--video-model' && argv[i + 1]) args.videoModel = argv[++i] else if (argv[i] === '--references' && argv[i + 1]) args.references = argv[++i] - else if (argv[i] === '--style' && argv[i + 1]) args.style = argv[++i] else if (argv[i] === '--all') args.all = true else if (!args.command) args.command = argv[i] } @@ -219,6 +228,7 @@ async function main() { console.log(' pipeline.js init --account --mode --items [--items-file ] [--image-model gemini|mj] [--video-model veo3-fast|grok|kling] [--format 9:16]') console.log(' pipeline.js validate --manifest ') console.log(' pipeline.js confirm --manifest --all') + console.log(' pipeline.js confirm --manifest --items 1,3,5') console.log(' pipeline.js run --manifest [--account id] [--phase p1,p2] [--resume] [--retry-failed]') console.log(' pipeline.js status --manifest ') console.log('') diff --git a/.gitignore b/.gitignore index 2fbaee5..4710656 100644 --- a/.gitignore +++ b/.gitignore @@ -2,7 +2,7 @@ node_modules/ - +config.json # Local settings .claude/settings.local.json diff --git a/accounts/_template/prompts/通用图片.md b/accounts/_template/prompts/通用图片.md index 83930b5..041ce7f 100644 --- a/accounts/_template/prompts/通用图片.md +++ b/accounts/_template/prompts/通用图片.md @@ -2,9 +2,7 @@ ## 一、角色定义 -你是一位专精图片生成模型的提示词工程师，具备深厚的视觉叙事和光影设计能力。 - -你的唯一任务是：将输入的分镜描述（shotDesc）作为核心内容依据，结合旁白语义、文案上下文，以及上游指定的导演风格，生成一条可直接送给图片生成模型的完整 imagePrompt。 +你是一位拥有 15 年经验的电影摄影指导（DP），擅长将文字分镜转化为高表现力的视觉起始帧。你不仅关注“画了什么”，更关注“空间叙述”与“光影秩序”。 > **重要前提：** 你生成的图片是下游视频片段的起始帧。构图和姿态必须是「即将发生」的瞬间，而非「已完成」的状态。