video-create/.claude/skills/video-from-script/scripts/lib/phase-images.js

/**
 * Phase: images — 图片生成
 *
 * 支持 Gemini / MJ / Kling 三种模型，含首尾帧模式
 * 并发生成，支持 task ID 恢复（MJ）
 */

const fs = require('fs')
const path = require('path')
const { saveManifest, getReferences, ensureDir, renameGeneratedFile, log, getManifestDir } = require('./pipeline-utils')

const IMAGE_CONCURRENCY = 3

async function phaseImages(manifest, manifestPath, options) {
  const dir = getManifestDir(manifestPath)
  const imagesDir = path.join(dir, 'images')
  ensureDir(imagesDir)

  const items = manifest.items.filter(it =>
    (!it.status || it.status === 'pending' || it.status === 'generating') && it.imagePrompt
  )
  if (items.length === 0) { log('images', '无待处理 item，跳过'); return }

  const accountConfig = options.accountConfig || {}
  let model = options.imageModel || manifest.imageModel || accountConfig.imageModel || 'gemini'
  const ratio = manifest.format || accountConfig.defaultFormat || '9:16'

  // 首尾帧模式：MJ 降级为 Gemini
  if (model === 'mj' && manifest.mode === 'framePair') {
    log('images', '首尾帧模式不支持 MJ，自动降级为 Gemini')
    model = 'gemini'
  }
  const refs = getReferences(manifest, accountConfig)

  log('images', `共 ${items.length} 张, 模型: ${model}, 画幅: ${ratio}, 参考图: ${refs.localPaths.length}本地/${refs.urls.length}URL, 并发: ${IMAGE_CONCURRENCY}`)

  // 分批并发处理
  for (let batchStart = 0; batchStart < items.length; batchStart += IMAGE_CONCURRENCY) {
    const batch = items.slice(batchStart, batchStart + IMAGE_CONCURRENCY)

    const results = await Promise.allSettled(
      batch.map(async (item) => {
        const idx = item.id
        try {
          item.status = 'generating'
          saveManifest(manifestPath, manifest)

          let result
          if (model === 'gemini') {
            result = await generateGemini(item, idx, dir, imagesDir, ratio, refs)
          } else if (model === 'mj') {
            result = await generateMJ(item, idx, dir, imagesDir, ratio, refs, manifestPath)
          } else if (model === 'kling') {
            result = await generateKling(item, idx, dir, imagesDir, ratio, refs)
          } else {
            throw new Error(`不支持的模型: ${model}（支持: gemini, mj, kling）`)
          }

          if (result.file) {
            item.file = result.file
            if (result.candidates) item.candidates = result.candidates
            item.status = 'done'
            log('images', `[${idx}] 完成: ${item.file}`)
          } else {
            item.status = 'failed'
            item.error = '生成器未返回文件'
            log('images', `[${idx}] 失败: 生成器未返回文件`)
          }
          // 每个 item 完成后立即写盘，防止崩溃丢失已完成的结果
          saveManifest(manifestPath, manifest)

          // 首尾帧模式：生成第二张图
          if (item.status === 'done' && manifest.mode === 'framePair' && item.lastFramePrompt && !item.lastFrame) {
            await generateLastFrame(item, idx, manifest, dir, imagesDir, model, ratio, manifestPath)
          }

          return { ok: true }
        } catch (err) {
          item.status = 'failed'
          item.error = err.message
          log('images', `[${idx}] 失败: ${err.message}`)
          saveManifest(manifestPath, manifest)
          return { ok: false, error: err.message }
        }
      })
    )
  }
}

// ============================================================================
// 各模型生成逻辑
// ============================================================================

async function generateGemini(item, idx, dir, imagesDir, ratio, refs) {
  const { generate: geminiGen, edit: geminiEdit } = require('../gemini-image-generator')
  let result
  if (refs.localPaths.length > 0) {
    log('images', `[${idx}] Gemini 图生图: ${item.imagePrompt.substring(0, 60)}...`)
    result = await geminiEdit(item.imagePrompt, refs.localPaths, {
      outputDir: imagesDir,
      aspectRatio: ratio,
    })
  } else {
    log('images', `[${idx}] Gemini 文生图: ${item.imagePrompt.substring(0, 60)}...`)
    result = await geminiGen(item.imagePrompt, {
      outputDir: imagesDir,
      aspectRatio: ratio,
    })
  }
  const file = (result.savedFiles && result.savedFiles.length > 0)
    ? renameGeneratedFile(
        path.relative(dir, result.savedFiles[0]).replace(/\\/g, '/'),
        dir, idx, item.narration || item.shotDesc, ''
      )
    : null
  return { file }
}

async function generateMJ(item, idx, dir, imagesDir, ratio, refs, manifestPath) {
  const { MJApi, ImageUtils } = require('../mj-image-generator')
  const referenceImages = refs.urls.length > 0 ? refs.urls : []
  const styleWeight = 200

  let result

  // 尝试恢复中断的 MJ 任务
  if (item.taskId && item.status === 'generating') {
    try {
      log('images', `[${idx}] 恢复 MJ 任务: ${item.taskId}`)
      const pollResult = await MJApi.poll(item.taskId)
      const timestamp = new Date().toISOString().replace(/[:.]/g, '-')
      const gridFile = path.join(imagesDir, `${timestamp}_grid.png`)
      await ImageUtils.download(pollResult.imageUrl, gridFile)
      const splitFiles = await ImageUtils.split4(gridFile, imagesDir, timestamp)
      fs.unlinkSync(gridFile)
      result = { files: splitFiles }
      log('images', `[${idx}] MJ 任务恢复成功`)
    } catch (err) {
      log('images', `[${idx}] MJ 任务恢复失败: ${err.message}，重新提交`)
      delete item.taskId
    }
  }

  // 新提交
  if (!result) {
    log('images', `[${idx}] MJ 生图: ${item.imagePrompt.substring(0, 60)}...`)
    const taskId = await MJApi.submit(item.imagePrompt, { referenceImages, aspectRatio: ratio, styleWeight })
    item.taskId = taskId
    saveManifest(manifestPath, manifest)

    const pollResult = await MJApi.poll(taskId)
    const timestamp = new Date().toISOString().replace(/[:.]/g, '-')
    const gridFile = path.join(imagesDir, `${timestamp}_grid.png`)
    await ImageUtils.download(pollResult.imageUrl, gridFile)
    const splitFiles = await ImageUtils.split4(gridFile, imagesDir, timestamp)
    fs.unlinkSync(gridFile)
    result = { files: splitFiles }
  }

  const file = (result.files && result.files.length > 0) ? result.files[0] : null
  const candidates = (result.files && result.files.length > 0)
    ? result.files.map((f, ci) =>
        renameGeneratedFile(
          path.relative(dir, f).replace(/\\/g, '/'),
          dir, idx, item.narration || item.shotDesc, `cand${ci + 1}`
        )
      )
    : null

  delete item.taskId
  if (candidates && candidates.length > 0) {
    log('images', `[${idx}] ${candidates.length} 张候选，默认选第1张`)
    return { file: candidates[0], candidates }
  }
  return { file }
}

async function generateKling(item, idx, dir, imagesDir, ratio, refs) {
  const { generate: klingGen } = require('../kling-image-generator')
  const klingOpts = { outputDir: imagesDir, aspectRatio: ratio }
  if (refs.urls.length > 0) klingOpts.styleImageUrl = refs.urls[0]
  log('images', `[${idx}] 可灵生图: ${item.imagePrompt.substring(0, 60)}...`)
  const result = await klingGen(item.imagePrompt, klingOpts)
  const file = (result.savedFiles && result.savedFiles.length > 0)
    ? renameGeneratedFile(
        path.relative(dir, result.savedFiles[0]).replace(/\\/g, '/'),
        dir, idx, item.narration || item.shotDesc, ''
      )
    : null
  return { file }
}

async function generateLastFrame(item, idx, manifest, dir, imagesDir, model, ratio, manifestPath) {
  try {
    item.status = 'generating'
    saveManifest(manifestPath, manifest)

    const firstFramePath = path.resolve(dir, item.file)
    let lastResult
    if (model === 'gemini') {
      const { edit: geminiEdit } = require('../gemini-image-generator')
      lastResult = await geminiEdit(item.lastFramePrompt, [firstFramePath], {
        outputDir: imagesDir,
        aspectRatio: ratio,
      })
    } else if (model === 'kling') {
      const { generate: klingGen } = require('../kling-image-generator')
      lastResult = await klingGen(item.lastFramePrompt, {
        outputDir: imagesDir,
        styleImageUrl: item.url || '',
        aspectRatio: ratio,
      })
    }

    if (lastResult) {
      const files = lastResult.savedFiles || lastResult.files || []
      if (files.length > 0) {
        item.lastFrame = renameGeneratedFile(
          path.relative(dir, files[0]).replace(/\\/g, '/'),
          dir, idx, item.narration || item.shotDesc, 'last'
        )
        item.status = 'done'
        log('images', `[${idx}] lastFrame 完成: ${item.lastFrame}`)
      } else {
        item.status = 'failed'
        item.error = 'lastFrame 生成器未返回文件'
        log('images', `[${idx}] lastFrame 失败: 未返回文件`)
      }
    }
  } catch (err) {
    item.status = 'failed'
    item.error = `lastFrame 失败: ${err.message}`
    log('images', `[${idx}] lastFrame 失败: ${err.message}`)
  }
}

module.exports = { phaseImages }