sion123
35488beef2
- 新增 gpt-image-generator.js 脚本，支持文生图、图生图/重绘、批量生成 - 更新 pipeline 和 phase-images 支持 GPT Image 模型 - 更新技能文档，添加 GPT Image 使用说明和 API 特点 - 新增配置文件中的 GPT Image API 参数
342 lines
13 KiB
JavaScript
342 lines
13 KiB
JavaScript
/**
|
||
* Phase: images — 图片生成
|
||
*
|
||
* 支持 Gemini / GPT Image / MJ / Kling 四种模型，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')
|
||
|
||
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) ||
|
||
(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 }
|
||
|
||
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 = await 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: 全并行`)
|
||
|
||
if (model === 'mj') {
|
||
// MJ 两阶段策略：先全部提交拿 taskId，再滑动窗口收割
|
||
await phaseImagesMJ(items, manifest, manifestPath, dir, imagesDir, model, ratio, refs)
|
||
} else {
|
||
// Gemini/Kling：滑动窗口并发
|
||
await phaseImagesSlidingWindow(items, manifest, manifestPath, dir, imagesDir, model, ratio, refs)
|
||
}
|
||
}
|
||
|
||
// ============================================================================
|
||
// 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: ${item.imagePrompt.substring(0, 60)}...`)
|
||
result = await geminiGen(item.imagePrompt, {
|
||
outputDir: imagesDir,
|
||
aspectRatio: ratio,
|
||
})
|
||
}
|
||
const file = (result.savedFiles && result.savedFiles.length > 0)
|
||
? renameGeneratedFile(
|
||
path.relative(dir, result.savedFiles[0]).replace(/\\/g, '/'),
|
||
dir, idx, item.script || item.shotDesc, ''
|
||
)
|
||
: null
|
||
return { file }
|
||
}
|
||
|
||
/**
|
||
* MJ 提交阶段：仅提交任务，返回 taskId（不轮询）
|
||
* 用于与滑动窗口配合，先批量提交再并行轮询
|
||
*/
|
||
async function submitMJ(item, idx, dir, imagesDir, ratio, refs, manifestPath, manifest) {
|
||
const { MJApi } = require('../mj-image-generator')
|
||
const referenceImages = refs.urls.length > 0 ? refs.urls : []
|
||
const styleWeight = 100
|
||
|
||
// 已有 taskId 的跳过提交（恢复场景）
|
||
if (item.taskId && item.status === 'generating') {
|
||
log('images', `[${idx}] MJ 跳过提交，已有 taskId: ${item.taskId}`)
|
||
return item.taskId
|
||
}
|
||
|
||
log('images', `[${idx}] MJ 提交: ${item.imagePrompt.substring(0, 60)}...`)
|
||
const taskId = await MJApi.submit(item.imagePrompt, { referenceImages, aspectRatio: ratio, styleWeight })
|
||
item.taskId = taskId
|
||
saveManifest(manifestPath, manifest)
|
||
return taskId
|
||
}
|
||
|
||
/**
|
||
* MJ 收割阶段：轮询 + 下载 + 拆分 + 重命名
|
||
*/
|
||
async function harvestMJ(item, idx, dir, imagesDir, ratio, refs, manifestPath, manifest) {
|
||
const { MJApi, ImageUtils } = require('../mj-image-generator')
|
||
|
||
const pollResult = await MJApi.poll(item.taskId)
|
||
const timestamp = new Date().toISOString().replace(/[:.]/g, '-')
|
||
const gridFile = path.join(imagesDir, `${timestamp}_grid.png`)
|
||
await ImageUtils.download(pollResult.imageUrl, gridFile)
|
||
const splitFiles = await ImageUtils.split4(gridFile, imagesDir, timestamp)
|
||
fs.unlinkSync(gridFile)
|
||
const 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.script || item.shotDesc, `cand${ci + 1}`
|
||
)
|
||
)
|
||
: null
|
||
|
||
delete item.taskId
|
||
if (candidates && candidates.length > 0) {
|
||
log('images', `[${idx}] ${candidates.length} 张候选，默认选第1张`)
|
||
return { file: candidates[0], candidates }
|
||
}
|
||
return { file }
|
||
}
|
||
|
||
async function generateMJ(item, idx, dir, imagesDir, ratio, refs, manifestPath, manifest) {
|
||
await submitMJ(item, idx, dir, imagesDir, ratio, refs, manifestPath, manifest)
|
||
return harvestMJ(item, idx, dir, imagesDir, ratio, refs, manifestPath, manifest)
|
||
}
|
||
|
||
async function generateGptImage(item, idx, dir, imagesDir, ratio, refs) {
|
||
const { generate: gptGen, edit: gptEdit, ratioToSize } = require('../gpt-image-generator')
|
||
const size = ratioToSize(ratio)
|
||
let result
|
||
if (refs.localPaths.length > 0) {
|
||
log('images', `[${idx}] GPT Image 图生图: ${item.imagePrompt.substring(0, 60)}...`)
|
||
result = await gptEdit(item.imagePrompt, refs.localPaths, {
|
||
outputDir: imagesDir,
|
||
size,
|
||
})
|
||
} else {
|
||
log('images', `[${idx}] GPT Image 文生图: ${item.imagePrompt.substring(0, 60)}...`)
|
||
result = await gptGen(item.imagePrompt, {
|
||
outputDir: imagesDir, size,
|
||
quality: 'auto',
|
||
})
|
||
}
|
||
const file = (result.savedFiles && result.savedFiles.length > 0)
|
||
? renameGeneratedFile(
|
||
path.relative(dir, result.savedFiles[0]).replace(/\\/g, '/'),
|
||
dir, idx, item.script || item.shotDesc, ''
|
||
)
|
||
: null
|
||
return { file }
|
||
}
|
||
|
||
async function generateKling(item, idx, dir, imagesDir, ratio, refs) {
|
||
const { generate: klingGen } = require('../kling-image-generator')
|
||
const klingOpts = { outputDir: imagesDir, aspectRatio: ratio }
|
||
if (refs.urls.length > 0) klingOpts.styleImageUrl = refs.urls[0]
|
||
log('images', `[${idx}] 可灵生图: ${item.imagePrompt.substring(0, 60)}...`)
|
||
const result = await klingGen(item.imagePrompt, klingOpts)
|
||
const file = (result.savedFiles && result.savedFiles.length > 0)
|
||
? renameGeneratedFile(
|
||
path.relative(dir, result.savedFiles[0]).replace(/\\/g, '/'),
|
||
dir, idx, item.script || item.shotDesc, ''
|
||
)
|
||
: null
|
||
return { file }
|
||
}
|
||
|
||
async function generateLastFrame(item, idx, manifest, dir, imagesDir, model, ratio, manifestPath) {
|
||
try {
|
||
item.status = 'generating'
|
||
saveManifest(manifestPath, manifest)
|
||
|
||
const firstFramePath = path.resolve(dir, item.file)
|
||
let lastResult
|
||
if (model === 'gemini') {
|
||
const { edit: geminiEdit } = require('../gemini-image-generator')
|
||
lastResult = await geminiEdit(item.lastFramePrompt, [firstFramePath], {
|
||
outputDir: imagesDir,
|
||
aspectRatio: ratio,
|
||
})
|
||
} else if (model === 'gpt-image') {
|
||
const { edit: gptEdit, ratioToSize } = require('../gpt-image-generator')
|
||
lastResult = await gptEdit(item.lastFramePrompt, [firstFramePath], {
|
||
outputDir: imagesDir,
|
||
size: ratioToSize(ratio),
|
||
})
|
||
} else if (model === 'kling') {
|
||
const { generate: klingGen } = require('../kling-image-generator')
|
||
lastResult = await klingGen(item.lastFramePrompt, {
|
||
outputDir: imagesDir,
|
||
styleImageUrl: item.url || '',
|
||
aspectRatio: ratio,
|
||
})
|
||
}
|
||
|
||
if (lastResult) {
|
||
const files = lastResult.savedFiles || lastResult.files || []
|
||
if (files.length > 0) {
|
||
item.lastFrame = renameGeneratedFile(
|
||
path.relative(dir, files[0]).replace(/\\/g, '/'),
|
||
dir, idx, item.script || item.shotDesc, 'last'
|
||
)
|
||
item.status = 'done'
|
||
log('images', `[${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}`)
|
||
}
|
||
}
|
||
|
||
// ============================================================================
|
||
// 调度策略
|
||
// ============================================================================
|
||
|
||
/**
|
||
* Gemini/Kling：全部并行
|
||
*/
|
||
async function phaseImagesSlidingWindow(items, manifest, manifestPath, dir, imagesDir, model, ratio, refs) {
|
||
await Promise.allSettled(items.map(item =>
|
||
processItem(item, manifest, manifestPath, dir, imagesDir, model, ratio, refs)
|
||
))
|
||
}
|
||
|
||
/**
|
||
* MJ 两阶段策略：
|
||
* 1. 先串行提交所有任务拿 taskId（MJ API 限制同时只能提交一个，但提交很快）
|
||
* 2. 滑动窗口收割：轮询+下载+拆分，完成一个立即补一个
|
||
*/
|
||
async function phaseImagesMJ(items, manifest, manifestPath, dir, imagesDir, model, ratio, refs) {
|
||
// 阶段1：全部提交
|
||
log('images', `=== MJ 阶段1: 提交 ${items.length} 个任务 ===`)
|
||
for (const item of items) {
|
||
const idx = item.id
|
||
try {
|
||
item.status = 'generating'
|
||
saveManifest(manifestPath, manifest)
|
||
await submitMJ(item, idx, dir, imagesDir, ratio, refs, manifestPath, manifest)
|
||
} catch (err) {
|
||
item.status = 'failed'
|
||
item.error = err.message
|
||
log('images', `[${idx}] MJ 提交失败: ${err.message}`)
|
||
saveManifest(manifestPath, manifest)
|
||
}
|
||
}
|
||
// 阶段2：全部并行收割（MJ 轮询是轻量 HTTP，不受本地并发限制）
|
||
const harvestItems = items.filter(it => it.taskId && it.status === 'generating')
|
||
log('images', `=== MJ 阶段2: 并行收割 ${harvestItems.length} 个任务 ===`)
|
||
|
||
await Promise.allSettled(harvestItems.map(async (item) => {
|
||
const idx = item.id
|
||
try {
|
||
const result = await harvestMJ(item, idx, dir, imagesDir, ratio, refs, manifestPath, manifest)
|
||
if (result.file) {
|
||
item.file = result.file
|
||
if (result.candidates) item.candidates = result.candidates
|
||
item.status = 'done'
|
||
log('images', `[${idx}] 完成: ${item.file}`)
|
||
} else {
|
||
item.status = 'failed'
|
||
item.error = '生成器未返回文件'
|
||
}
|
||
saveManifest(manifestPath, manifest)
|
||
|
||
if (item.status === 'done' && manifest.mode === 'framePair' && item.lastFramePrompt && !item.lastFrame) {
|
||
await generateLastFrame(item, idx, manifest, dir, imagesDir, model, ratio, manifestPath)
|
||
}
|
||
} catch (err) {
|
||
item.status = 'failed'
|
||
item.error = err.message
|
||
log('images', `[${idx}] 收割失败: ${err.message}`)
|
||
saveManifest(manifestPath, manifest)
|
||
}
|
||
}))
|
||
}
|
||
|
||
/**
|
||
* 通用 item 处理（Gemini/Kling 用）
|
||
*/
|
||
async function processItem(item, manifest, manifestPath, dir, imagesDir, model, ratio, refs) {
|
||
const idx = item.id
|
||
try {
|
||
item.status = 'generating'
|
||
saveManifest(manifestPath, manifest)
|
||
|
||
if (item.file && manifest.mode === 'framePair' && item.lastFramePrompt && !item.lastFrame) {
|
||
log('images', `[${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)
|
||
} else if (model === 'gpt-image') {
|
||
result = await generateGptImage(item, idx, dir, imagesDir, ratio, refs)
|
||
} else if (model === 'kling') {
|
||
result = await generateKling(item, idx, dir, imagesDir, ratio, refs)
|
||
} else {
|
||
throw new Error(`不支持的模型: ${model}（支持: gemini, gpt-image, mj, kling）`)
|
||
}
|
||
|
||
if (result.file) {
|
||
item.file = result.file
|
||
if (result.candidates) item.candidates = result.candidates
|
||
item.status = 'done'
|
||
log('images', `[${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`)
|
||
}
|
||
saveManifest(manifestPath, manifest)
|
||
|
||
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 }
|
||
}
|
||
}
|
||
|
||
module.exports = { phaseImages }
|