OpenMontage 中 HeyGen 視頻狀態(tài)輪詢實(shí)戰(zhàn)從 poll 模式到斷點(diǎn)續(xù)查的完整實(shí)現(xiàn)【免費(fèi)下載鏈接】OpenMontageWorlds first open-source, agentic video production system. 12 production pipelines, 100 tools, 700 agent skill and production-knowledge files. Turn your AI coding assistant into a full video production studio.項(xiàng)目地址: https://gitcode.com/GitHub_Trending/op/OpenMontage本文圍繞 OpenMontage 倉(cāng)庫(kù)中 HeyGencreate-video技能的核心參考文檔 video-status.md 展開系統(tǒng)講解 HeyGen 異步視頻生成的狀態(tài)輪詢機(jī)制狀態(tài)類型語義、生成耗時(shí)預(yù)估、completed/failed兩種響應(yīng)結(jié)構(gòu)、帶進(jìn)度回調(diào)的輪詢實(shí)現(xiàn)、帶指數(shù)退避的下載重試以及適合長(zhǎng)任務(wù)的斷點(diǎn)續(xù)查模式。讀完本篇你可以為任何接入 HeyGen API或其他異步媒體生成服務(wù)的流程編寫生產(chǎn)級(jí)輪詢邏輯并理解 OpenMontage 工具層heygen_video是如何在源碼中落地同一套輪詢策略的。1. 背景為什么狀態(tài)輪詢是異步視頻生成的必經(jīng)環(huán)節(jié)HeyGen 的視頻生成是完全異步的提交請(qǐng)求后服務(wù)端只返回一個(gè)video_id真正的渲染在后臺(tái)排隊(duì)執(zhí)行?？蛻舳吮仨毞磸?fù)查詢狀態(tài)接口直到拿到video_url或確認(rèn)失敗。這正是 SKILL.md 中Default Workflow的第 3 步——Callmcp__heygen__get_videowith the returned video_id to poll status and get the download URL。文檔給出了兩條查詢路徑MCP 工具首選若 HeyGen MCP 服務(wù)器已連接直接使用mcp__heygen__get_video并傳入videoId參數(shù)。它一次性返回 status、video_url、thumbnail_url、duration、title、gif_url、captioned_video_url等全部元數(shù)據(jù)直接調(diào)用 REST APIGET /v2/videos/{video_id}需要自行處理狀態(tài)機(jī)與重試。SKILL.md的Tool Selection表格進(jìn)一步明確了這一優(yōu)先級(jí)有mcp__heygen__*工具時(shí)優(yōu)先用它自動(dòng)處理鑒權(quán)與請(qǐng)求格式?jīng)]有時(shí)才回退到裸 HTTP 調(diào)用。1.1 查詢接口的最小實(shí)現(xiàn)文檔給出三種語言的直接調(diào)用示例。curl 版本如下注意鑒權(quán)走X-Api-Key請(qǐng)求頭key 來自環(huán)境變量HEYGEN_API_KEYcurl -X GET https://api.heygen.com/v2/videos/YOUR_VIDEO_ID \ -H X-Api-Key: $HEYGEN_API_KEYTypeScript 版本定義了完整的響應(yīng)結(jié)構(gòu)VideoStatusResponse其中data字段包含id、status四態(tài)之一、video_url、thumbnail_url、duration、title、created_at、completed_at、gif_url、captioned_video_url、subtitle_url、folder_id、output_language以及失敗專用的failure_code與failure_message。錯(cuò)誤處理約定是頂層error字段非空即代表調(diào)用失敗如 404、鑒權(quán)失敗應(yīng)直接拋錯(cuò)業(yè)務(wù)狀態(tài)含失敗態(tài)則放在data.status中表達(dá)。async function getVideoStatus(videoId: string): PromiseVideoStatusResponse[data] { const response await fetch( https://api.heygen.com/v2/videos/${videoId}, { headers: { X-Api-Key: process.env.HEYGEN_API_KEY! } } ); const json: VideoStatusResponse await response.json(); if (json.error) { throw new Error(json.error); } return json.data; }Python 版本邏輯等價(jià)import requests import os def get_video_status(video_id: str) - dict: response requests.get( fhttps://api.heygen.com/v2/videos/{video_id}, headers{X-Api-Key: os.environ[HEYGEN_API_KEY]} ) data response.json() if data.get(error): raise Exception(data[error]) return data[data]2. 狀態(tài)類型與耗時(shí)預(yù)估2.1 四種狀態(tài)及其語義Status含義客戶端行為pending視頻已入隊(duì)等待處理繼續(xù)輪詢processing視頻正在生成繼續(xù)輪詢completed視頻可下載讀取video_url下載failed生成失敗讀取failure_message定位原因并終止輪詢邏輯的本質(zhì)就是一個(gè)針對(duì)這四個(gè)狀態(tài)的狀態(tài)機(jī)completed返回 URL、failed拋錯(cuò)、其余狀態(tài) sleep 后重試。2.2 生成耗時(shí)與影響因素文檔給出的經(jīng)驗(yàn)值是視頻生成通常需要5–15 分鐘高峰負(fù)載或長(zhǎng)腳本場(chǎng)景可能超過 20 分鐘。影響耗時(shí)的主要因素因素影響腳本長(zhǎng)度腳本越長(zhǎng)處理時(shí)間顯著增加分辨率1080p 比 720p 慢Avatar 復(fù)雜度部分 avatar 渲染更快隊(duì)列負(fù)載高峰時(shí)段可能等待 15–20 分鐘以上多場(chǎng)景每個(gè)場(chǎng)景都增加處理時(shí)間基于此文檔給出的工程建議是超時(shí)設(shè)置為 15–20 分鐘900,000–1,200,000 ms語音腳本超過 2 分鐘時(shí)應(yīng)預(yù)期 15 分鐘以上的等待長(zhǎng)視頻建議改用異步模式保存video_id稍后再查見第 5 節(jié)。這一經(jīng)驗(yàn)值與 OpenMontage 源碼中的實(shí)際實(shí)現(xiàn)一致heygen_video工具的輪詢默認(rèn)超時(shí)為 600 秒見 poll_heygen 的timeout: int 600參數(shù)——它對(duì)應(yīng)約 10 分鐘的基礎(chǔ)預(yù)算而文檔建議對(duì)長(zhǎng)內(nèi)容上調(diào)到 15–20 分鐘兩者并不矛盾前者是工具鏈的保守默認(rèn)后者是面向長(zhǎng)腳本的上限建議。3. 響應(yīng)格式詳解理解響應(yīng) JSON 的兩類形態(tài)是編寫正確狀態(tài)處理代碼的前提。3.1 completed 響應(yīng)成功時(shí)data中攜帶全部交付元數(shù)據(jù)。文檔示例{ error: null, data: { id: abc123, status: completed, video_url: https://files.heygen.ai/video/abc123.mp4, thumbnail_url: https://files.heygen.ai/thumbnail/abc123.jpg, duration: 45.2, title: My Video, created_at: 2024-01-15T10:30:00Z, completed_at: 2024-01-15T10:38:00Z, gif_url: https://files.heygen.ai/gif/abc123.gif, captioned_video_url: null, subtitle_url: null, folder_id: null, output_language: en } }注意兩個(gè)易踩的坑其一captioned_video_url、subtitle_url等字段可能為null取用前必須判空其二從示例中的created_at/completed_at時(shí)間差8 分鐘可以看到實(shí)際渲染時(shí)長(zhǎng)可用這兩個(gè)字段做生成耗時(shí)統(tǒng)計(jì)。3.2 failed 響應(yīng)失敗時(shí)響應(yīng)結(jié)構(gòu)不變但只有failure_code和failure_message提供診斷信息{ error: null, data: { id: abc123, status: failed, failure_code: script_too_long, failure_message: Script too long for selected avatar } }這里的failure_code如script_too_long是機(jī)器可讀的錯(cuò)誤分類failure_message是可直接展示給用戶的文本。輪詢代碼在failed分支應(yīng)優(yōu)先把兩者都記錄下來——OpenMontage 源碼中的poll_heygen同樣遵循失敗即拋異常并攜帶錯(cuò)誤詳情的原則raise RuntimeError(fHeyGen generation failed: {data.get(error, Unknown)})見 tools/video/_shared.py。4. 輪詢實(shí)現(xiàn)從基礎(chǔ)循環(huán)到進(jìn)度回調(diào)4.1 基礎(chǔ)輪詢核心是一個(gè)截止時(shí)刻 固定間隔循環(huán)記錄startTime每輪查一次狀態(tài)completed返回video_urlfailed拋錯(cuò)pending/processing則 sleep 后繼續(xù)超出maxWaitMs后拋超時(shí)錯(cuò)誤。async function waitForVideo( videoId: string, maxWaitMs 600000, // 10 minutes pollIntervalMs 5000 // 5 seconds ): Promisestring { const startTime Date.now(); while (Date.now() - startTime maxWaitMs) { const status await getVideoStatus(videoId); switch (status.status) { case completed: return status.video_url!; case failed: throw new Error(status.failure_message || Video generation failed); case pending: case processing: await new Promise((resolve) setTimeout(resolve, pollIntervalMs)); break; } } throw new Error(Video generation timed out); }默認(rèn)參數(shù)為 10 分鐘超時(shí)、5 秒輪詢間隔——注意這里的maxWaitMs默認(rèn)值偏保守對(duì)長(zhǎng)視頻應(yīng)按第 2 節(jié)的建議顯式傳入更大的值。4.2 帶進(jìn)度回調(diào)的輪詢?cè)?Agent 或 CLI 場(chǎng)景中用戶需要看到還在跑已等待 X 秒這類反饋。做法是引入ProgressCallback (status, elapsed) void在每次輪詢后把當(dāng)前狀態(tài)與已耗時(shí)傳給回調(diào)type ProgressCallback (status: string, elapsed: number) void; async function waitForVideoWithProgress( videoId: string, onProgress?: ProgressCallback, maxWaitMs 600000, pollIntervalMs 5000 ): Promisestring { const startTime Date.now(); while (Date.now() - startTime maxWaitMs) { const elapsed Date.now() - startTime; const status await getVideoStatus(videoId); onProgress?.(status.status, elapsed); switch (status.status) { case completed: return status.video_url!; case failed: throw new Error(status.failure_message || Video generation failed); default: await new Promise((resolve) setTimeout(resolve, pollIntervalMs)); } } throw new Error(Video generation timed out); } // Usage const videoUrl await waitForVideoWithProgress( videoId, (status, elapsed) { console.log(Status: ${status}, Elapsed: ${Math.round(elapsed / 1000)}s); } );Python 版本提供同樣能力on_progress是可選的Callable[[str, int], None]參數(shù)為當(dāng)前狀態(tài)與已等待秒數(shù)import time from typing import Optional, Callable def wait_for_video( video_id: str, max_wait_seconds: int 600, poll_interval: int 5, on_progress: Optional[Callable[[str, int], None]] None ) - str: start_time time.time() while time.time() - start_time max_wait_seconds: elapsed int(time.time() - start_time) status_data get_video_status(video_id) status status_data[status] if on_progress: on_progress(status, elapsed) if status completed: return status_data[video_url] elif status failed: raise Exception(status_data.get(failure_message, Video generation failed)) time.sleep(poll_interval) raise Exception(Video generation timed out) # Usage def progress_callback(status: str, elapsed: int): print(fStatus: {status}, Elapsed: {elapsed}s) video_url wait_for_video(video_id, on_progressprogress_callback)4.3 OpenMontage 源碼中的真實(shí)輪詢實(shí)現(xiàn)上述示例之外倉(cāng)庫(kù)的工具層給出了一個(gè)可直接借鑒的生產(chǎn)實(shí)現(xiàn)。tools/video/_shared.py 中的poll_heygen有兩個(gè)值得注意的設(shè)計(jì)漸進(jìn)式退避。間隔不是固定的 5 秒而是從 5.0 秒開始每輪乘以 1.2上限 30 秒interval min(interval * 1.2, 30.0)。這正好實(shí)踐了文檔Best Practices第 1 條——對(duì)長(zhǎng)任務(wù)增大輪詢間隔——避免在 15 分鐘級(jí)的任務(wù)里做無謂的高頻請(qǐng)求。def poll_heygen(execution_id: str, api_key: str, timeout: int 600) - str: ... interval 5.0 while time.time() deadline: response requests.get(url, headersheaders, timeout30) response.raise_for_status() data response.json().get(data, {}) status data.get(status, ) if status completed: video_url ( data.get(output, {}).get(video, {}).get(video_url) or data.get(output, {}).get(video_url) ) ... if status in {failed, error}: raise RuntimeError(fHeyGen generation failed: {data.get(error, Unknown)}) time.sleep(min(interval, max(0.0, deadline - time.time()))) interval min(interval * 1.2, 30.0) raise TimeoutError(fHeyGen execution {execution_id} timed out after {timeout}s)響應(yīng)結(jié)構(gòu)兼容。completed分支同時(shí)嘗試output.video.video_url與output.video_url兩條路徑取值并在都取不到時(shí)拋出帶完整響應(yīng)體的錯(cuò)誤Completed but no video_url in output——這是一種防御性寫法應(yīng)對(duì)服務(wù)端響應(yīng)結(jié)構(gòu)在不同端點(diǎn)版本間的差異。從源碼結(jié)構(gòu)看poll_heygen服務(wù)于 Workflow 端點(diǎn)/v1/workflows/executions/{id}而文檔示例針對(duì)的是標(biāo)準(zhǔn)video_id狀態(tài)端點(diǎn)/v2/videos/{id}兩者狀態(tài)機(jī)語義completed / failed / 輪詢 / 超時(shí)完全一致可視為同一套模式在不同端點(diǎn)上的落地。5. 下載階段completed 不等于立即可下載文檔特別強(qiáng)調(diào)了一個(gè)容易被忽略的事實(shí)狀態(tài)顯示completed之后video_url可能仍短暫不可用文件還在向 CDN 分發(fā)因此下載必須帶重試與指數(shù)退避。5.1 帶重試的下載TypeScriptasync function downloadVideoWithRetry( videoUrl: string, outputPath ./output/video.mp4, maxRetries 5, initialDelayMs 2000 ): Promisevoid { let lastError: Error | null null; for (let attempt 0; attempt maxRetries; attempt) { try { const response await fetch(videoUrl); if (!response.ok) { throw new Error(HTTP ${response.status}: ${response.statusText}); } const arrayBuffer await response.arrayBuffer(); fs.writeFileSync(path.resolve(outputPath), Buffer.from(arrayBuffer)); console.log(Video downloaded to ${outputPath}); return; } catch (error) { lastError error as Error; const delay initialDelayMs * Math.pow(2, attempt); // Exponential backoff console.log(Download attempt ${attempt 1} failed, retrying in ${delay}ms...); await new Promise((resolve) setTimeout(resolve, delay)); } } throw new Error(Failed to download after ${maxRetries} attempts: ${lastError?.message}); }退避序列為 2s → 4s → 8s → 16s → 32sinitialDelayMs * 2^attempt最多 5 次。5.2 帶重試的下載PythonPython 版本使用streamTrue分塊寫入chunk_size8192避免大文件一次性占用內(nèi)存重試邏輯與 TypeScript 版一一對(duì)應(yīng)def download_video_with_retry( video_url: str, output_path: str, max_retries: int 5, initial_delay: float 2.0 ) - None: last_error None for attempt in range(max_retries): try: response requests.get(video_url, streamTrue, timeout60) response.raise_for_status() with open(output_path, wb) as f: for chunk in response.iter_content(chunk_size8192): f.write(chunk) print(fVideo downloaded to {output_path}) return except Exception as e: last_error e delay initial_delay * (2 ** attempt) # Exponential backoff print(fDownload attempt {attempt 1} failed, retrying in {delay}s...) time.sleep(delay) raise Exception(fFailed to download after {max_retries} attempts: {last_error})若只是快速腳本、失敗后可手動(dòng)重跑文檔也提供了無重試的簡(jiǎn)版downloadVideo單次 fetch 寫入!response.ok時(shí)拋錯(cuò)。對(duì)比倉(cāng)庫(kù)實(shí)現(xiàn)generate_heygen_video在 tools/video/_shared.py 中拿到video_url后直接requests.get(video_url, timeout120)一次性下載未做應(yīng)用層重試——但這并不沖突因?yàn)?tools/video/heygen_video.py 聲明了retry_policy RetryPolicy(max_retries2, backoff_seconds10.0, retryable_errors[rate_limit, timeout, server_error])由工具框架層對(duì)execute整體重試兜底。這說明同一份文檔知識(shí)在 OpenMontage 中有兩種落地方式輪詢工具自行實(shí)現(xiàn)退避poll_heygen下載重試則委托給工具框架的 RetryPolicy。6. 完整工作流生成 → 輪詢 → 下載把前述環(huán)節(jié)串起來就是一個(gè)端到端的一次性流程。以下示例以 Video Agent 生成端點(diǎn)為起點(diǎn)該端點(diǎn)返回data.video_id與 video-agent.md 中的響應(yīng)示例一致再進(jìn)入輪詢與下載async function generateAndDownloadVideo(config: VideoConfig): Promisestring { // 1. Generate video const generateResponse await fetch( https://api.heygen.com/v2/video/generate, { method: POST, headers: { X-Api-Key: process.env.HEYGEN_API_KEY!, Content-Type: application/json, }, body: JSON.stringify(config), } ); const { data: generateData } await generateResponse.json(); const videoId generateData.video_id; console.log(Video ID: ${videoId}); // 2. Poll for completion const videoUrl await waitForVideoWithProgress( videoId, (status, elapsed) { console.log([${Math.round(elapsed / 1000)}s] Status: ${status}); } ); // 3. Download const outputPath ./output/${videoId}.mp4; await downloadVideo(videoUrl, outputPath); return outputPath; }OpenMontage 的generate_heygen_video演示了同樣的三步骨架只是第 1 步換成了 Workflow 端點(diǎn)POST /v1/workflows/executionsworkflow_type: GenerateVideoNode返回execution_id第 2 步調(diào)用內(nèi)部poll_heygen(execution_id, api_key, timeout600)第 3 步把結(jié)果寫入output_path并以ToolResult返回execution_id、provider_variant、aspect_ratio等元數(shù)據(jù)見 tools/video/_shared.py。另外image_to_video場(chǎng)景下本地參考圖會(huì)先經(jīng)upload_image_heygen上傳換取公開 URL 再注入請(qǐng)求體——這條上傳路徑同樣復(fù)用了v2 presigned 端點(diǎn)優(yōu)先、失敗回退的容錯(cuò)思路。7. 斷點(diǎn)續(xù)查長(zhǎng)任務(wù)的 Resumable 模式對(duì) 5–20 分鐘的生成任務(wù)讓一個(gè)進(jìn)程阻塞等待并不劃算進(jìn)程可能重啟、Agent 會(huì)話可能中斷。文檔給出的替代方案是生成后立刻持久化video_id進(jìn)程退出之后隨時(shí)再查一次狀態(tài)。7.1 保存待處理狀態(tài)interface PendingVideo { videoId: string; createdAt: string; script: string; avatarId: string; voiceId: string; } async function startVideoGeneration(config: VideoGenerateRequest): PromisePendingVideo { const videoId await generateVideo(config); const pending: PendingVideo { videoId, createdAt: new Date().toISOString(), script: config.video_inputs[0].voice.input_text!, avatarId: config.video_inputs[0].character.avatar_id!, voiceId: config.video_inputs[0].voice.voice_id!, }; // Save to file for later retrieval fs.writeFileSync(pending-video.json, JSON.stringify(pending, null, 2)); console.log(Video generation started. ID: ${videoId}); console.log(Check status later with: checkVideoStatus()); return pending; }PendingVideo除了videoId還冗余保存了script、avatarId、voiceId目的是讓后續(xù)查詢進(jìn)程無需重新構(gòu)造請(qǐng)求也能描述這個(gè)視頻是什么。7.2 稍后查詢并結(jié)算async function checkVideoStatus(): Promisevoid { if (!fs.existsSync(pending-video.json)) { console.log(No pending video found); return; } const pending: PendingVideo JSON.parse( fs.readFileSync(pending-video.json, utf-8) ); const elapsed Date.now() - new Date(pending.createdAt).getTime(); console.log(Checking video ${pending.videoId} (started ${Math.round(elapsed / 60000)} min ago)...); const status await getVideoStatus(pending.videoId); switch (status.status) { case completed: console.log(Video ready: ${status.video_url}); console.log(Duration: ${status.duration}s); // Clean up pending file fs.unlinkSync(pending-video.json); // Save result fs.writeFileSync(video-result.json, JSON.stringify({ ...pending, videoUrl: status.video_url, thumbnailUrl: status.thumbnail_url, duration: status.duration, title: status.title, createdAt: status.created_at, completedAt: status.completed_at, }, null, 2)); break; case failed: console.error(Video failed: ${status.failure_message}); fs.unlinkSync(pending-video.json); break; default: console.log(Status: ${status.status} - check again in a few minutes); } }注意其結(jié)算語義completed/failed兩個(gè)終態(tài)都會(huì)清理pending-video.jsoncompleted時(shí)額外把交付信息落盤到video-result.json非終態(tài)只做再等幾分鐘的提示不做阻塞。7.3 CLI 友好形態(tài)文檔最后把該模式拆成兩個(gè)獨(dú)立命令形成典型的兩段式 CLI 體驗(yàn)// generate-video.ts - Start generation and exit async function main() { const pending await startVideoGeneration(config); console.log(\nVideo ID saved. Run npx tsx check-status.ts to check progress.); process.exit(0); // Exit immediately, dont wait } // check-status.ts - Check and optionally wait async function main() { const args process.argv.slice(2); const shouldWait args.includes(--wait); if (shouldWait) { // Poll until complete (with 20 min timeout) const result await waitForVideo(pending.videoId, apiKey, onProgress, 1200000); console.log(Done: ${result.video_url}); } else { // Just check once and report await checkVideoStatus(); } }--wait參數(shù)提供了第三種行為查詢腳本可以只做看一眼也可以就地切換到 20 分鐘1200000ms超時(shí)的阻塞輪詢——這正好對(duì)應(yīng)第 2 節(jié)15–20 分鐘超時(shí)的建議值。8. 替代方案與最佳實(shí)踐清單8.1 Webhook 替代輪詢對(duì)于不想維護(hù)輪詢連接的生產(chǎn)系統(tǒng)HeyGen 支持 webhook 推送視頻完成、失敗、翻譯完成、Avatar 訓(xùn)練完成等事件會(huì) POST 到你的端點(diǎn)。完整的事件類型列表、簽名與端點(diǎn)實(shí)現(xiàn)含 Express 與 Flask 示例在同目錄的 webhooks.md 中有專門說明Video Agent 端點(diǎn)的callback_idcallback_url參數(shù)對(duì)見 video-agent.md 請(qǐng)求字段表即是為該通道預(yù)留的入口。8.2 文檔總結(jié)的五條 Best Practices使用指數(shù)退避——對(duì)長(zhǎng)任務(wù)逐步增大輪詢間隔poll_heygen的 5s→30s 漸進(jìn)間隔即為此實(shí)踐設(shè)置合理超時(shí)——大多數(shù)視頻 10 分鐘內(nèi)完成長(zhǎng)內(nèi)容上調(diào)至 15–20 分鐘優(yōu)雅處理失敗——利用failure_code/failure_message給出可操作的反饋生產(chǎn)系統(tǒng)優(yōu)先考慮 webhook——比輪詢更省資源緩存視頻 URL——下載用的 URL 有時(shí)效性拿到后應(yīng)盡快落盤不要長(zhǎng)期持有 URL 反復(fù)引用。9. 小結(jié)這篇參考文檔在 OpenMontage 中的位置video-status.md 是create-video技能Foundation類參考件之一與webhooks.md、assets.md、dimensions.md、quota.md并列見 SKILL.md 的 Reference Files 章節(jié)承擔(dān)拿到 video_id 之后怎么辦這一環(huán)節(jié)的全部知識(shí)狀態(tài)機(jī)語義、耗時(shí)預(yù)算、輪詢/下載/斷點(diǎn)續(xù)查三套代碼模式。而 tools/video/heygen_video.py 與 tools/video/_shared.py 則證明這些模式不是紙面規(guī)范漸進(jìn)退避輪詢、終態(tài)錯(cuò)誤上報(bào)、框架層重試策略都已在heygen_video工具的調(diào)用鏈中真實(shí)運(yùn)行。對(duì)需要接入 HeyGen 或任何異步媒體生成 API 的開發(fā)者本文覆蓋的生成 → 輪詢含進(jìn)度→ 退避下載 → 斷點(diǎn)續(xù)查閉環(huán)可以直接作為實(shí)現(xiàn)模板復(fù)用?！久赓M(fèi)下載鏈接】OpenMontageWorlds first open-source, agentic video production system. 12 production pipelines, 100 tools, 700 agent skill and production-knowledge files. Turn your AI coding assistant into a full video production studio.項(xiàng)目地址: https://gitcode.com/GitHub_Trending/op/OpenMontage創(chuàng)作聲明：本文部分內(nèi)容由AI輔助生成（AIGC），僅供參考