Seedance 2.0
字节跳动下一代多模态AI视频生成器。支持15参考文件、15秒高清输出、双声道立体声音频、角色一致性 —— 从文本、图片、音频或视频输入创建令人惊叹的AI视频。全球排名第一，Elo评分1,269。
为什么选择 Seedance 2.0？
统一多模态架构，音视频联合生成，前所未有的AI视频创作控制力。
多模态输入
Seedance 2.0支持文本、图片、音频和视频四种模态作为AI视频生成输入。上传最多9张图片、3个视频和3个音频文件，以像素级精度引导生成。
角色一致性
行业领先的AI视频生成长镜头角色和场景一致性。稳定的人脸、服装和环境 —— 不再有身份漂移或闪烁。
双声道音频
Seedance 2.0原生生成同步的双声道立体声音频 —— 对话、音效和背景音乐 —— 与AI生成的视频内容完美对齐。
智能编辑与续写
通过替换角色、修改场景或延长片段来编辑现有AI视频。Seedance 2.0的定向编辑功能支持无缝延续故事，保持视觉连续性。
物理准确运动
Seedance 2.0在Megaton物理基准测试中得分73.0，比Seedance 1.5 Pro高出31.7分。以严格的物理准确性渲染复杂的多主体交互。自然的重力、流体动力学和真实的材质行为。
导演级参考
在Seedance 2.0中从输入素材参考构图、镜头运动、动作节奏和视觉效果。上传分镜脚本、参考视频和音频片段 —— 你的参考素材就是AI视频生成的创作方向。
看看 Seedance 2.0 能创建什么
从电影叙事到产品广告 —— Seedance 2.0驱动的真实AI视频生成示例。
Product Commercial
The character in the painting looks guilty, darting glances left and right before leaning out of the picture frame. Very swiftly, they extend a hand outside the frame, grab a cola, take a sip, and reveal a look of deep satisfaction. Hearing footsteps approach, the character hastily puts the cola back just as a Western cowboy walks by and picks it up. The ending shot pushes in on a top-lit close-up of the cola against a pure black background, with artistic subtitles and a voiceover appearing at the bottom: "Yikou Cola, an absolute must-try!"
Extend the Video Length
Extend the video length. The camera follows a man in orange riding a brown horse. He speeds up and gallops to a large tree with orange flowers ahead, breaks off two blossoms from the branch. Then others ride into the frame one after another. The camera pushes in to shoot the man in orange clothes dismounting from the horse, then the camera quickly circles around him. He turns to walk toward a woman in white riding a white horse and presents the flowers to her. Style: Chinese classical lady painting, 3D, cheerful folk music, shadow puppet style, with black, white, and orange as the main color palette.
Multimodal All-Round Reference
Refer to the shooting script in @Image 1, and draw on the storyboard, shot scale, camera movement, visuals and copy in @Image 1. The character is from @Image 2, the scene is from @Image 3, and the props are from @Image 4. Create a 15-second healing short film.
Wuxia-Style Audiovisual Blockbuster
A Wuxia-style audiovisual blockbuster. A white-clad swordsman and a straw-caped blademaster face off in a bamboo forest. The camera slowly pushes in between them, shifting focus between raindrops and sword hilts. The atmosphere is extremely oppressive; only the sound of rain can be heard. Suddenly, a crack of thunder flashes, and both charge simultaneously. A fast-panning profile shot captures their mud-splattering footsteps. The precise moment their weapons clash, the footage switches to ultra-slow motion, clearly displaying the ring-shaped shockwaves of rainwater blasted away by the blades, along with bamboo leaves sliced by sword aura. Normal speed resumes as they land back-to-back. The straw-caped blademaster's bamboo hat splits open, and the scene cuts abruptly.
1920s Jazz Club Charleston Dance
1920s jazz club-style Charleston dance. A female dancer in a gold fringe dress and a male dancer in a striped suit perform a high-intensity routine. Moves include hyper-fast syncopated footwork, aerial catches, and exaggerated arm swings. The camera uses dynamic tracking, interspersed with close-ups of footwork. Emphasis is on physical details the fringe swinging wildly with every kick, the sheen of sweat on their skin, and the smoky, vintage film grain cinematic texture. A background jazz band and cheering audience amplify the frenzied party atmosphere.
Girl Hangs Laundry Gracefully
A girl hangs laundry gracefully. After finishing, she takes another piece of clothing from the bucket and shakes it vigorously.
Seedance 2.0 核心能力
探索让 Seedance 2.0 成为全球排名第一AI视频生成器的先进功能
四模态AI视频生成
不同于仅支持文本和图片输入的Seedance 1.5 Pro，Seedance 2.0接受四种输入模态 —— 文本提示、图片、音频文件和视频片段。同时上传最多15个参考文件，精确控制AI视频生成结果。
原生音视频联合生成
Seedance 2.0是唯一在一次生成中原生产出双声道立体声音频并同步视频的AI视频生成器。对话、音效和背景音乐同步生成 —— 无需额外音频工具。
定向视频编辑
Seedance 2.0为AI视频引入定向编辑功能 —— 替换特定角色、修改个别场景或延长片段，无需重新生成整个视频。Seedance 1.5 Pro每次修改都需要完整重新生成。
分镜脚本转视频
上传分镜脚本或拍摄计划作为参考图片，Seedance 2.0将遵循镜头尺度、镜头运动和视觉构图。AI视频生成器自动将你的创作方向转化为精美视频。
物理准确运动（Megaton 73.0）
Seedance 2.0在Megaton物理基准测试中得分73.0 —— 比Seedance 1.5 Pro高出31.7分。这款AI视频生成器以严格的物理准确性渲染真实的重力、流体动力学、布料模拟和多主体交互。
角色与场景一致性
在AI生成的视频中跨多个镜头保持稳定的角色身份、服装和环境。Seedance 2.0提供行业领先的一致性，消除身份漂移 —— 叙事和商业AI视频生成的必备能力。
技术规格
Seedance 2.0提供专业级AI视频生成输出，支持灵活的配置选项。
15 seconds
480P / 720P / 1080P
16:9, 9:16, 1:1, 4:3, 3:4, 21:9
Dual-channel stereo (native)
Up to 15 (9 images + 3 videos + 3 audio)
1,269 (#1 globally)
Text + Image + Audio + Video
ByteDance via APImart
Seedance 2.0 vs Seedance 1.5 Pro
每个维度的重大飞跃 —— 全球#1 AI视频生成器与前代对比。
| 特性 | Seedance 2.0 | Seedance 1.5 Pro |
|---|---|---|
| 最大时长 | 15s | 12s |
| 最大分辨率 | 1080P | 1080P |
| Elo评分（全球排名） | 1,269 (#1) | — |
| Megaton物理评分 | 73.0 | 53.0 |
| 音频输出 | 双声道立体声 | 单声道（协调生成） |
| 参考文件数 | 15 (9 img + 3 vid + 3 aud) | 3 |
| 输入模态 | 4 (Text + Image + Audio + Video) | 2 (Text + Image) |
| 角色一致性 | 行业领先 | 良好 |
| 物理准确性 | +31.7 pts vs 1.5 Pro | Baseline |
| 视频续写 | 支持 | 不支持 |
| 定向编辑 | 支持 | 不支持 |
| 分镜脚本转视频 | 支持 | 不支持 |
Turing AI