Seedance 2.0 是字節跳動的一款多模態 AI 視頻模型，優化以快速且逼真的視頻生成。它支持高品質虛擬人視頻創作，具有強大的多鏡頭一致性，使各場景的輸出更加生動且具有電影感。
憑藉高效的生成速度，Seedance 2.0 通常每次生成約平均需 ~5 分鐘，而 Seedance 2.0 Fast 平均約需 ~4 分鐘，使其成為可擴展內容生產的可靠選擇。
最低價格起 $0.06/s
480p: 12 學分/秒 - 視頻到視頻 - （輸入+輸出）×12
480p: 19 學分/秒 - 文字/圖像轉視頻 - 輸出秒數 × 19
720p: 25 學分/秒 - 視頻到視頻 - （輸入+輸出）×25
720p: 41 學分/秒 - 文字/圖像轉視頻 - 輸出秒數 × 41
1080p: 62 學分/秒 - 視頻到視頻 - （輸入+輸出）×62
1080p: 102 學分/秒 - 文字/圖像轉視頻 - 輸出秒數 × 102
美元估算使用每個積分 $0.005 的最佳年計劃。
核心請求欄位
Keep the payload predictable while still allowing rich multimodal control.
{
"model": "bytedance/seedance-2",
"input": {
"prompt": "A serene beach at sunset with waves gently crashing on the shore, palm trees swaying in the breeze, and seagulls flying across the orange sky",
"first_frame_url": "https://templateb.aiquickdraw.com/custom-page/akr/section-images/example2.png",
"last_frame_url": "https://templateb.aiquickdraw.com/custom-page/akr/section-images/example3.png",
"reference_image_urls": [
"https://templateb.aiquickdraw.com/custom-page/akr/section-images/example1.png"
],
"reference_video_urls": [
"https://templateb.aiquickdraw.com/custom-page/akr/section-images/example1.mp4"
],
"reference_audio_urls": [
"https://templateb.aiquickdraw.com/custom-page/akr/section-images/example1.mp3"
],
"return_last_frame": false,
"generate_audio": false,
"resolution": "720p",
"aspect_ratio": "16:9",
"duration": 15,
"web_search": false
}
}使用 Seedance 2.0 進行生成
此頁面上的遊樂場、樣本請求、請求欄位及價格皆依所選模型類型而定。
查看詳細的 API 文件Open the full API documentation for endpoints, authentication, task polling, and payload details. /models/seedance-2.0.md
promptstringThe text prompt used to generate the video. Required field. (Min length: 3, Max length: 20000 characters)first_frame_urlstringFirst frame image url or asset://{assetId}last_frame_urlstringEnd frame image url or asset://{assetId}reference_image_urlsarrayEnter a list of image URLs or asset://{assetId} (for example: asset://asset-20260404242101-76djj).reference_video_urlsarrayEnter a list of video URLs or asset://{assetId} (for example: asset://asset-20260404242101-76djj) .reference_audio_urlsarrayEnter a list of audio URLs or asset://{assetId} (for example: asset://asset-20260404242101-76djj) .return_last_framebooleanWhether to return the last frame of the video as an image.generate_audiobooleanWhether to generate audio for the video.resolutionenumVideo resolution - 480p for faster generation, 720p for balance, 1080p for High-quality video, 4K Ultra-High Definition, delivering perfect visual details. (480p, 720p, 1080p, 4k)aspect_ratioenumVideo aspect ratio configuration. Required field. (1:1, 4:3, 3:4, 16:9, 9:16, 21:9, adaptive)durationnumberVideo duration in 4-15 seconds.web_searchbooleanUse online searchnsfw_checkerbooleanDefaults to false. You can set it to false based on your needs. If set to false, our content filtering will be disabled, and all results will be returned directly by the model itself.Seedance 2.0 API 為您的影片工作流程新增的功能
此頁面遵循與參考相同的 API 優先結構：測試模型、了解欄位，然後進行整合。
多模態參考
將提示與圖像、影片和音訊結合，使模型能夠遵循主體的身份、動作、節奏和視覺風格。
多次拍攝一致性
創建短小的電影序列，具有更穩定的角色、攝影機邏輯以及跨剪輯的場景連貫性。
參考驅動運動
使用原始片段來引導鏡頭移動、動作時機、轉場和高衝擊視覺節奏。
音訊感知創作
上傳音頻參考或啟用生成的音頻，以用於節拍匹配的片段、音樂視頻和同步敘事。
從遊樂場測試到生產請求
為希望在將 API 連接到應用程式之前驗證輸出質量的團隊提供的緊湊整合路徑。
1. 準備請求
選擇 Seedance 2.0 或 Seedance 2.0 Fast，然後添加提示文字和您的工作流程所需的任何參考媒體。
2. 提交生成
使用您的帳戶密鑰、模型 ID、持續時間、解析度、長寬比和媒體網址呼叫 API。
3. 投票並呈現
追蹤任務直到成功，然後檢索為您的應用程式、活動或流程生成的影片 URL。
使用 Seedance 2.0 API 可以創建的內容
當您的產品需要可重複的 AI 視頻輸出，而不僅僅是一個一次性的遊樂場結果時，請使用 API。
來自社群的成功 Seedance 2.0 世代
瀏覽已成功完成的公開 Seedance 2.0 輸出，然後打開任何案例以檢查提示、設定和結果。
Hilarious viral dachshund comedy. bright colorful home interior, exaggerated close-up of dachshund making dramatic facial expressions, sausage dog in silly situations, vibrant warm colors, chaotic playful energy. The scene opens with an attention-grabbing
Hilarious viral dachshund comedy. bright colorful home interior, exaggerated close-up of dachshund making dramatic facial expressions, sausage dog in silly situations, vibrant warm colors, chaotic playful energy. The scene opens with an attention-grabbing moment: Can dachshunds really talk back to their owners?. The camera smoothly transitions to show know they've got a lot to say. From their signature howl to their sassy little barks, it's like they're trying to tell us something. But have you ever caught your dachshund in a case of the zoomies? You know, that chaotic energy where they just can't stop running around in circles? It's hilarious a. The scene concludes with Follow for more!. Pure photorealistic cinematography, no text, no watermarks, no overlays, no captions. Ambient sounds of the environment fill the scene naturally.
Wilderness preparedness and self-reliance documentary. wilderness setting with outdoor skills, rugged outdoor environment with camping and hiking gear, dramatic natural lighting, forest and mountain landscapes. The scene opens with an attention-grabbing m
Wilderness preparedness and self-reliance documentary. wilderness setting with outdoor skills, rugged outdoor environment with camping and hiking gear, dramatic natural lighting, forest and mountain landscapes. The scene opens with an attention-grabbing moment: Can you start a fire without matches or a lighter?. The camera smoothly transitions to show I'm putting my skills to the test using innovative techniques like flint and steel, bow drills, and solar fire starting. These methods require some practice, but they're essential for any outdoor adventurer. From camping to emergency preparedness, knowing how to start a fire can be a lifesaver.. The scene concludes with Try these fire starting methods yourself and share your favorite technique in the comments below!. Pure photorealistic cinematography, no text, no watermarks, no overlays, no captions. Ambient sounds of the environment fill the scene naturally.
Fast-paced TikTok style prepper content. clean modern home interior, prepping supplies organized, preparedness aesthetic. The scene opens with a dramatic attention-grabbing moment showcasing How to Build a Written Emergency Plan (20 Smart Steps) with quic
Fast-paced TikTok style prepper content. clean modern home interior, prepping supplies organized, preparedness aesthetic. The scene opens with a dramatic attention-grabbing moment showcasing How to Build a Written Emergency Plan (20 Smart Steps) with quick zoom and high energy. The camera rapidly cuts between angles showing key How to Build a Written Emergency Plan (20 Smart Steps) techniques with dynamic close-ups of details and action. The scene concludes with a powerful wide shot revealing the full impressive setup. Pure photorealistic cinematography, no text, no watermarks, no overlays, no captions. Ambient sounds of the environment fill the scene naturally.
Bright sunny garden, lush vegetables, someone tending plants, warm natural light. The scene opens with an attention-grabbing moment: Transform your backyard into a lush oasis. The camera smoothly transitions to show Start small, choose easy-grow plants, a
Bright sunny garden, lush vegetables, someone tending plants, warm natural light. The scene opens with an attention-grabbing moment: Transform your backyard into a lush oasis. The camera smoothly transitions to show Start small, choose easy-grow plants, and maximize vertical space. The scene concludes with Dive into urban farming and harvest your first crop tonight. Pure photorealistic cinematography, no text, no watermarks, no overlays, no captions. Ambient sounds of the environment fill the scene naturally.
Hilarious viral dachshund comedy. bright colorful home interior, exaggerated close-up of dachshund making dramatic facial expressions, sausage dog in silly situations, vibrant warm colors, chaotic playful energy. The scene opens with an attention-grabbing
Hilarious viral dachshund comedy. bright colorful home interior, exaggerated close-up of dachshund making dramatic facial expressions, sausage dog in silly situations, vibrant warm colors, chaotic playful energy. The scene opens with an attention-grabbing moment: Can your dachshund steal food without you noticing?. The camera smoothly transitions to show wn, with a mission to get its paws on your snacks. This little ninja has a knack for sniffing out food from a mile away. Watch as it dodges a broom, weaves through chair legs, and jumps over a toy to get to its prize. With its little legs moving a mile a minute, it's a comedy of errors as it tries t. The scene concludes with Follow for more!. Pure photorealistic cinematography, no text, no watermarks, no overlays, no captions. Ambient sounds of the environment fill the scene naturally.
Fast-paced TikTok style prepper content. forest and garden setting, edible plants and foraging basket, natural outdoor environment. The scene opens with a dramatic attention-grabbing moment showcasing Food Foraging with quick zoom and high energy. The cam
Fast-paced TikTok style prepper content. forest and garden setting, edible plants and foraging basket, natural outdoor environment. The scene opens with a dramatic attention-grabbing moment showcasing Food Foraging with quick zoom and high energy. The camera rapidly cuts between angles showing key Food Foraging techniques with dynamic close-ups of details and action. The scene concludes with a powerful wide shot revealing the full impressive setup. Pure photorealistic cinematography, no text, no watermarks, no overlays, no captions. Ambient sounds of the environment fill the scene naturally.
為真正的 API 工作流程而建
帳戶限制執行
用戶透過現有的 SdanceAI 生成流程登入、提交任務並消耗點數。
參考媒體處理
The studio supports uploaded reference media, direct URLs, previews, and form/API payload editing.
可擴展模型選擇
根據品質、成本和延遲需求，在標準模式和快速模式的 Seedance 2.0 之間切換。
Seedance 2.0 API 問題
Seedance 2.0 API 最適合用於什麼？
它最適合用於短片、電影風格的 AI 影片生成，特別是在提示控制和參考媒體重要的情況下，包括產品影片、社交短片、動作複製和多鏡頭敘事。
Seedance 2.0 和 Seedance 2.0 Fast 有什麼不同？
Seedance 2.0 專注於更高品質的輸出和更強的創意控制。Seedance 2.0 Fast 專為更快速的迭代和可擴展的批量工作流程進行了優化。
我可以在一次請求中使用圖片、影片和音訊嗎？
是的。Seedance 2.0 工作流程支持文本加混合參考輸入，包括圖像、影片片段和音頻參考。
我可以在哪裡在整合之前測試它？
Use the playground on this page to test prompts, references, resolution, aspect ratio, duration, and API payload behavior before moving into production.
Seedance 2.0 API 引入了哪些新功能？
Seedance 2.0 引入了更廣泛的多模態控制，包括文字、影像、影片和音頻參考。它的設計旨在提供更好的動作引導、更強的場景一致性以及更可預測的電影效果。
Seedance 2.0 API 與一般的 AI 視頻生成器有何不同？
許多影片生成器主要依賴提示語的解讀。Seedance 2.0 則更多依據參考資料，因此它可以使用來源媒體來引導攝影機運動、動作時機、過渡、主題風格和節奏。
我可以在 Seedance 2.0 API 項目中上傳多少個參考資料？
此工作流程最多支援 9 個圖片參考、最多 3 個影片參考以及最多 3 個音訊參考。影片與音訊的參考輸入應保持在文件中所述的時間限制內。
Seedance 2.0 API 是否支援語音指引和口型同步生成？
該模型工作流程支持音頻感知生成。您可以使用音頻參考來控制節奏和步調，並在所選版本和請求設置支持的情況下啟用生成的音頻。
有哪些影片長度和時間選項可用？
Seedance 2.0 是為短片段打造的，通常在 4 到 15 秒範圍內。應同時選擇時長、長寬比和解析度，以符合您的目標輸出格式。
我可以將 Seedance 2.0 API 用於商業專案嗎？
此頁面已配置為商業使用工作流程。若要進行生產使用，請檢查您的帳戶方案、信用餘額、模型可用性以及任何適用的內容政策要求。
將 Seedance 2.0 融入你的視頻工作流程
打開生成器，測試一個提示，然後當你準備好將 Seedance 2.0 接入生產環境時使用 API 文檔。