Seedance 2.0 API
字节跳动 Seedance 2.0——好莱坞级的电影感视频,具备原生音画同步、导演级的镜头与灯光控制,以及出色的运动稳定性。基于 Seed 统一的多模态架构构建。
提供 Standard、Fast 和 Turbo 档位,以及文生视频、图生视频、视频编辑和视频延长变体——输出 480p 至 4k,时长 4–15 秒。所有档位均带原生音频;文生视频和图生视频支持参考视频。
概览
关于 Seedance 2.0 API
Seedance 2.0 能做什么、它在 ByteDance 模型阵容中的定位,以及团队选择它的原因。
Seedance 2.0 是 ByteDance 推出的视频生成模型,可通过 WaveSpeedAI REST API 使用。字节跳动 Seedance 2.0——好莱坞级的电影感视频,具备原生音画同步、导演级的镜头与灯光控制,以及出色的运动稳定性。基于 Seed 统一的多模态架构构建。
提供 Standard、Fast 和 Turbo 档位,以及文生视频、图生视频、视频编辑和视频延长变体——输出 480p 至 4k,时长 4–15 秒。所有档位均带原生音频;文生视频和图生视频支持参考视频。
WaveSpeedAI 上的 Seedance 2.0 系列提供 21 个 REST 端点,涵盖 Text-To-Video, Image-To-Video, Video-Extend, Video-To-Video 个工作流。每个变体都有各自的定价、参数选项和示例输出——请选择与你的输入模态和生产约束相匹配的那一个,或使用同一个 API 密钥调用多个变体,组合成多步骤流水线。
使用与 WaveSpeedAI 上其他 1,000 多个 AI 模型相同的 API 密钥、账单账户和速率限制来运行 Seedance 2.0。无需单独对接供应商,无需各家 SDK,也无需应对各家不同的速率限制——一次集成即可覆盖从文生图、文生视频到音频合成、3D 生成、放大和编辑的全部能力。
端点
全部 Seedance 2.0 API 端点
WaveSpeedAI 现已提供 21 个 Seedance 2.0 端点——请选择适合你工作流的变体。
/filters:quality(82)/media/images/1777710751782434706_GfpzJS2H.webp)
Seedance 2.0 Fast Text To Video Turbo
Seedance 2.0 Fast (Text-to-Video Turbo) generates cinematic 720p/1080p videos from text prompts using speed-optimized inference —the fastest and most affordable Seedance option with native audio-visual synchronization and director-level control.
/filters:quality(82)/media/images/1777710766717897372_XNfpyHR0.webp)
Seedance 2.0 Fast Image To Video Turbo
Seedance 2.0 Fast (Image-to-Video Turbo) generates cinematic 720p/1080p videos from reference images using speed-optimized inference —the fastest and most affordable Seedance image-to-video option with native audio-visual synchronization and director-level control.
/filters:quality(82)/media/images/1782150104262652854_353YVSPP.webp)
Seedance 2.0 Mini Text To Video Turbo
Seedance 2.0 Mini Text to Video Turbo is ByteDance's faster, lower-cost text-to-video model for cinematic multi-shot videos. It generates narrative sequences from text prompts with AI camera control, consistent characters, 720P / 1080P output, 5-12s duration, and flexible aspect ratios. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/1777710782211882265_rR0PY8hr.webp)
Seedance 2.0 Text To Video Turbo
Seedance 2.0 (Text-to-Video Turbo) generates cinematic 720p/1080p videos from text prompts —a faster, more affordable high-resolution tier with native audio-visual synchronization, director-level control, and exceptional motion stability.
/filters:quality(82)/media/images/1777710796465656330_J8EMV5eo.webp)
Seedance 2.0 Image To Video Turbo
Seedance 2.0 (Image-to-Video Turbo) generates cinematic 720p/1080p videos from reference images —a faster, more affordable high-resolution tier with native audio-visual synchronization, director-level control, and exceptional motion stability.
/filters:quality(82)/media/images/1784118818944663760_u9FOX7gq.webp)
Seedance 2.0 Fast Text To Video
Seedance 2.0 Fast (Text-to-Video) generates cinematic videos from text prompts with native audio-visual synchronization, director-level camera and lighting control, and exceptional motion stability — optimized for faster generation at lower cost. Built on Seed's unified multimodal architecture.
/filters:quality(82)/media/images/1784115038043562153_fbqzJS1H.webp)
Seedance 2.0 Fast Image To Video
Seedance 2.0 Fast (Image-to-Video) generates cinematic videos from reference images and text prompts with native audio-visual synchronization, director-level control, and exceptional motion stability — optimized for faster generation at lower cost. Built on Seed's unified multimodal architecture.
/filters:quality(82)/media/images/1784114740421359958_fCL2KT3c.webp)
Seedance 2.0 Text To Video
Seedance 2.0 (Text-to-Video) generates Hollywood-grade cinematic videos from text prompts with native audio-visual synchronization, director-level camera and lighting control, and exceptional motion stability. Built on Seed's unified multimodal architecture, it leads on instruction adherence, motion quality, and visual aesthetics.
/filters:quality(82)/media/images/1784118140257739680_HayHQ0MW.webp)
Seedance 2.0 Fast Video Extend
Seedance 2.0 Fast (Video-Extend) extends an input video with a new cinematic continuation generated from its last frame and a natural-language prompt — at the faster, cheaper Seedance 2.0 Fast tier. Ready-to-use REST API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/1784115845488318278_s45eoxGP.webp)
Seedance 2.0 Mini Video Extend
Seedance 2.0 Mini Video Extend is ByteDance's faster, lower-cost video extension model for cinematic multi-shot continuation. It extends existing videos into seamless narrative sequences with AI camera control, consistent characters, motion continuity, 480P / 720P / 1080P / 4K output, 4-15s duration, and flexible aspect ratios. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/1784115207543444153_o8pe1PCq.webp)
Seedance 2.0 Video Extend
Seedance 2.0 (Video-Extend) extends an input video with a new cinematic continuation generated from its last frame and a natural-language prompt. Ready-to-use REST API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/1784117974221900004_TrAJS1vF.webp)
Seedance 2.0 Fast Video Edit
Seedance 2.0 Fast (Video-Edit) edits an input video from a natural-language prompt at a faster, cheaper tier. Built on ByteDance Seed's unified multimodal architecture, it preserves subject identity, composition, and motion while rewriting lighting, style, weather, environment, or specific elements as instructed. Ready-to-use REST API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/1777709897111402859_z86iqAJS.webp)
Seedance 2.0 Fast Video Edit Turbo
Seedance 2.0 Fast (Video-Edit Turbo) is the fastest, cheapest turbo tier for editing an input video from a natural-language prompt — high-resolution output with optimized cost and speed. Ready-to-use REST API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/1777709912318665482_YFuDNW5f.webp)
Seedance 2.0 Video Edit Turbo
Seedance 2.0 (Video-Edit Turbo) is the turbo tier for editing an input video from a natural-language prompt — faster, more affordable high-resolution output while preserving subject identity, composition, and motion. Ready-to-use REST API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/1784114527178681757_HyHRZ8h2.webp)
Seedance 2.0 Video Edit
Seedance 2.0 (Video-Edit) edits an input video from a natural-language prompt. The reference video drives subject identity, composition, and motion while the model rewrites lighting, style, weather, environment, or specific elements as instructed. Built on ByteDance Seed's unified multimodal architecture for cinematic, motion-stable output. Ready-to-use REST API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/1784114911044913513_tQ0MW5eo.webp)
Seedance 2.0 Mini Text To Video
Seedance 2.0 Mini Text to Video is ByteDance's faster, lower-cost text-to-video model for cinematic multi-shot videos. It generates narrative sequences from text prompts with AI camera control, consistent characters across scenes, 480P / 720P / 1080P / 4K output, 4-15s duration, and flexible aspect ratios. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/1784114374920321015_tUkW5enw.webp)
Seedance 2.0 Image To Video
Seedance 2.0 (Image-to-Video) generates Hollywood-grade cinematic videos from reference images and text prompts with native audio-visual synchronization, director-level camera and lighting control, and exceptional motion stability. Built on Seed's unified multimodal architecture, it preserves the input image's subject and composition while adding expressive, physically accurate motion.
/filters:quality(82)/media/images/1782150883895961015_UoILIIDE.webp)
Seedance 2.0 Mini Video Edit Turbo
Seedance 2.0 Mini is ByteDance's faster, lower-cost video generation model for text to video and image to video. It creates cinematic multi-shot videos with AI camera control, consistent characters across scenes, 720P / 1080P output, 5-12s duration, and flexible aspect ratios. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/1782150119735302611_8bsplife.webp)
Seedance 2.0 Mini Image To Video Turbo
Seedance 2.0 Mini Image to Video Turbo is ByteDance's faster, lower-cost image-to-video model for cinematic multi-shot videos. It turns reference images and optional text prompts into narrative sequences with AI camera control, consistent characters, 720P / 1080P output, 5-12s duration, and flexible aspect ratios. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/1784117507698664813_nXmwFOW6.webp)
Seedance 2.0 Mini Video Edit
Seedance 2.0 Mini Video Edit is ByteDance's faster, lower-cost video editing model for prompt-guided video modification. It edits existing videos with cinematic multi-shot quality, AI camera control, consistent characters, 480P / 720P / 1080P / 4K output, 4-15s duration, and flexible aspect ratios. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/1784114642196942243_fI6AKT2c.webp)
Seedance 2.0 Mini Image To Video
Seedance 2.0 Mini Image to Video is ByteDance's faster, lower-cost image-to-video model for cinematic multi-shot videos. It turns reference images and optional text prompts into narrative sequences with AI camera control, consistent characters across scenes, 480P / 720P / 1080P / 4K output, 4-15s duration, and flexible aspect ratios. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
示例
看看 Seedance 2.0 的实际效果
由 Seedance 2.0 API 生成的真实输出。悬停在任意视频上即可预览,点击可打开全尺寸查看器。
使用方法
如何使用 Seedance 2.0 API
从注册到完成一次生成,只需四步。完整的 Python、Node.js 和 cURL 示例见下方的 API 部分。
- 01
获取 API 密钥
注册 WaveSpeedAI 账号,并从控制台复制你的 API 密钥。新账号附带免费体验额度——足够在开始计费前把 Playground 运行几十次。
- 02
提交预测
把你的输入以 JSON 形式 POST 到 https://api.wavespeed.ai/api/v3/bytedance/seedance-2.0/text-to-video。端点会立即返回预测 ID——生成是异步的,因此推理期间你无需保持连接。
- 03
轮询完成状态
GET https://api.wavespeed.ai/api/v3/predictions/{request_id}/result。状态为 completed 时返回输出;状态为 failed、cancelled、timeout 或 deleted 时以错误终止;其他任何状态都继续轮询。
- 04
读取输出 URL
状态变为 "completed" 后,从 data.outputs[0] 读取 URL。该 URL 指向 WaveSpeedAI CDN 上你生成的媒体——具体是图片、视频、音频还是 3D 文件,取决于你调用的 Seedance 2.0 变体。
应用场景
用 Seedance 2.0 可以构建什么
开发者和创作者使用 Seedance 2.0 API 的常见工作流。
文生视频,带原生音频
bytedance/seedance-2.0/text-to-video 根据文本提示词一次性生成带同步音频的电影感片段——无需单独的音频模型或同步步骤。提示词中的镜头和灯光语言会直接对应到渲染出的运动。
以参考静态图生成视频
bytedance/seedance-2.0/image-to-video 根据文本引导让参考图像动起来,在加入运动、运镜和同步音频的同时,保留主体身份、构图和首帧细节。
视频编辑,针对性改变风格
bytedance/seedance-2.0/video-edit 根据自然语言提示词改写输入视频的光线、风格、天气和氛围——同时保留原始素材的主体身份、构图和运动。适用于对现有素材进行风格开发和风格迁移。
视频延长,制作更长的序列
bytedance/seedance-2.0/video-extend 从输入视频的最后一帧开始,按文本提示词生成电影感的续写——可连续延长,制作更长的序列,并精确控制转场到帧。
分档定价,从迭代到交付
Fast 档位(bytedance/seedance-2.0-fast/*)用于提示词迭代;Standard 用于交付(最高 4k);需要高分辨率但不想等待 Standard 档完整画质处理时,用 Turbo 快速输出 720p/1080p。
参考视频引导
在提示词之外提供参考视频(文生视频 / 图生视频),可加入运动风格引导——适合匹配现有片段的节奏或镜头语言。参考视频属于付费附加项,因此请留给确实需要匹配现有片段运动的镜头。
技巧
Seedance 2.0 提示词技巧
让 Seedance 2.0 输出更好结果的实用建议——总结自生产流水线中各类视频模型都适用的做法。
- 01
使用导演级的镜头语言
目录定位:「导演级的镜头和灯光控制」。具体的摄影术语(orbit、dolly-in、push-in、pan-left、crane shot、handheld follow)比笼统的运动描述更能直接转化为画面。
- 02
在描述画面的同时描述声音设计
目录中每个 Seedance 2.0 变体的说明都包含原生音画同步。在同一条提示词里描述脚步声、对白情绪、音乐类型和环境层次——模型会同时以音频和视频为条件,而不是通过单独的同步步骤。
- 03
用 Fast 迭代,用 Standard 交付,追求速度时选 Turbo
Fast 档位(bytedance/seedance-2.0-fast/*)用于提示词迭代;Standard 用于交付;需要快速输出高分辨率 720p/1080p 时用 Turbo。各档位的提示词格式相同——只需切换端点 URL。
- 04
根据素材选择合适的变体
全新提示词用文生视频;在保留主体和构图的同时为特定静态图添加动态用图生视频;在保持主体身份的前提下改写现有片段的光线/风格/天气用视频编辑;从现有片段的最后一帧续写用视频延长。
- 05
参考视频可增加运动风格引导
在提示词之外添加 reference_video,可为模型提供运动风格引导(镜头节奏、动作时机)。请留给确实需要匹配现有片段运动的镜头;参考视频会增加参考视频引导的计费,因此不要随意添加。
定价
Seedance 2.0 API 定价
按输出计费。最终费用会随你在各变体 Playground 中设置的参数(分辨率、时长、输出数量、参考素材)而变化。
API
调用 Seedance 2.0 API
在 wavespeed.ai/accesskey 注册并获取 API 密钥,然后通过 REST 提交预测。Playground 可以为任意输入组合生成可直接粘贴的示例代码。
POSThttps://api.wavespeed.ai/api/v3/bytedance/seedance-2.0/text-to-video
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/bytedance/seedance-2.0/text-to-video" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"aspect_ratio": "16:9",
"resolution": "720p",
"duration": 5,
"enable_web_search": false,
"generate_audio": true
}')
TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
printf 'Submission response did not contain a prediction id
' >&2
exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
# 2. Poll until the prediction finishes.
while true; do
RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
-H "Authorization: Bearer $WAVESPEED_API_KEY")
RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
case "$STATUS" in
completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
failed|cancelled|timeout|deleted) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
*) sleep 2 ;;
esac
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/bytedance/seedance-2.0/text-to-video";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');
async function requestJson(url, options = {}) {
const response = await fetch(url, options);
if (!response.ok) throw new Error(await response.text());
return response.json();
}
// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
method: "POST",
headers: {
"Authorization": `Bearer ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"aspect_ratio": "16:9",
"resolution": "720p",
"duration": 5,
"enable_web_search": false,
"generate_audio": true
}),
});
const task = body.data ?? body;
const resultUrl = `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;
// 2. Poll until the prediction finishes.
while (true) {
const resultBody = await requestJson(resultUrl, {
headers: { "Authorization": `Bearer ${apiKey}` },
});
const result = resultBody.data ?? resultBody;
if (result.status === "completed") {
console.log(result.outputs);
break;
}
if (["failed", "cancelled", "timeout", "deleted"].includes(result.status)) throw new Error(JSON.stringify(result));
await new Promise(resolve => setTimeout(resolve, 2000));
}import json
import os
import time
from urllib.request import Request, urlopen
api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"aspect_ratio": "16:9",
"resolution": "720p",
"duration": 5,
"enable_web_search": False,
"generate_audio": True
}
def request_json(url, data=None):
request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
with urlopen(request) as response:
return json.load(response)
# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/bytedance/seedance-2.0/text-to-video", json.dumps(payload).encode())
task = body.get("data", body)
result_url = f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"
# 2. Poll until the prediction finishes.
while True:
result_body = request_json(result_url)
result = result_body.get("data", result_body)
status = result.get("status")
if status == "completed":
print(result.get("outputs", []))
break
if status in {"failed", "cancelled", "timeout", "deleted"}:
raise RuntimeError(result)
time.sleep(2)对比
Seedance 2.0 与其他方案对比
在 WaveSpeedAI 上,何时应选择 Seedance 2.0 而不是同类模型。
Seedance 2.0 对比 Veo 3.1
Veo 3.1 在写实感和自然人脸方面领先。Seedance 2.0 的优势在于:每个档位都有原生音频合成(Veo 的音频取决于档位)、对电影镜头语言的遵循,以及更丰富的变体(文生视频、图生视频、视频编辑、视频延长,另有 Fast 和 Turbo 子档位)。
Seedance 2.0 对比 Kling 3.0
Kling 3.0 提供单独的运动控制端点。Seedance 2.0 在 4K 输出上与之持平,并在同一次生成中加入原生音频同步、视频编辑和视频延长——另有三个价格档位(Fast/Standard/Turbo),无需更换模型就能在成本和速度之间权衡。
Seedance 2.0 对比 Wan 2.7
Wan 2.7 提供独立的参考生视频端点,同系列中还有图像编辑变体。Seedance 2.0 的优势在于原生音频(Wan 2.7 仅在图生视频和视频延长中提供可选音频)、4k 输出,以及快速的 Turbo 档位。
常见问题
Seedance 2.0 API — 常见问题
定价、许可、集成——关于在 WaveSpeedAI 上运行 Seedance 2.0 的常见问题。
Seedance 2.0 API 是什么?
Seedance 2.0 是 ByteDance 的视频生成模型,在 WaveSpeedAI 上以 REST API 形式提供。字节跳动 Seedance 2.0——好莱坞级的电影感视频,具备原生音画同步、导演级的镜头与灯光控制,以及出色的运动稳定性。基于 Seed 统一的多模态架构构建。你可以通过编程方式调用它,也可以在上方链接的 Playground 中试用。
如何调用 Seedance 2.0 API?
注册 WaveSpeedAI 账号,从 /accesskey 复制你的 API 密钥,然后把输入以 JSON 形式 POST 到 https://api.wavespeed.ai/api/v3/bytedance/seedance-2.0/text-to-video。端点会返回预测 ID。从大约每 2 秒一次开始轮询结果端点,长耗时任务可适当拉长间隔,并在任何终止状态时停止。上方有面向生产环境的 Python / Node.js / cURL 示例。
Seedance 2.0 API 的费用是多少?
Seedance 2.0 每次调用 $0.50 起。实际费用会随你设置的参数(分辨率、时长、输出数量、参考素材)而变化。Playground 中“生成”按钮旁的实时费用预览会显示你当前输入对应的准确价格。
有哪些 Seedance 2.0 变体可用?
WaveSpeedAI 托管了 21 个已上线的 Seedance 2.0 端点:bytedance/seedance-2.0-fast/text-to-video-turbo, bytedance/seedance-2.0-fast/image-to-video-turbo, bytedance/seedance-2.0-mini/text-to-video-turbo, bytedance/seedance-2.0/text-to-video-turbo, bytedance/seedance-2.0/image-to-video-turbo, bytedance/seedance-2.0-fast/text-to-video, bytedance/seedance-2.0-fast/image-to-video, bytedance/seedance-2.0/text-to-video等。每个变体都有自己的 Playground 页面和定价。
Seedance 2.0 的输出可以商用吗?
商用权利遵循 ByteDance 的模型许可。大多数 ByteDance 模型允许商用输出;具体许可摘要请查看各模型的 Playground 页面,平台层面的条件请参阅 WaveSpeedAI 的服务条款。
为什么要在 WaveSpeedAI 上使用 Seedance 2.0,而不是直接对接?
一个 API 密钥、一个账单账户,即可使用 Seedance 2.0 以及来自其他提供方的 1,000 多个 AI 模型。无需逐家配置 SDK,无需应对各自独立的速率限制,也无需为每家重写集成代码。价格通常与 ByteDance 直接提供的 API 持平或更低。
提供方
关于 ByteDance
Seedance 2.0 及 WaveSpeedAI 上 ByteDance 更多模型背后的团队。
字节跳动——TikTok、CapCut 和豆包背后的公司——拥有全球规模最大的 AI 研究团队之一。其 Seed 和豆包团队推出了业界领先的视频生成(Seedance)、图像生成与编辑(Seedream、Nano Banana)以及数字人 / 口型同步模型。模型以内部规模的数据训练,先通过字节跳动的消费级应用投入生产,再以 API 形式对外发布。
在 WaveSpeedAI 上用 Seedance 2.0 开始构建
注册即送免费体验额度。一个 API 密钥,即可使用来自 ByteDance 及其他所有提供方的 1,000 多个 AI 模型。