seedance-2.5 AI 视频 API
ByteDance Seedance 2.5 是一款音视频生成模型,支持文生视频和图生视频工作流。可通过 Flatkey 的 /v1/videos 使用参考素材、首尾帧控制、4–30 秒请求和可选音频。
输出
预览使用 Seedance 2.0 生成
请求摘要
- 接口
- POST /v1/videos
- 模型 ID
- seedance-2.5
- 画面比例
- 16:9
- 分辨率
- 720p
- 时长
- 5s
- 生成音频
- 开
- 参考媒体
- 无
仅供预览。登录后即可向 Flatkey 提交此请求。
{
"model": "seedance-2.5",
"content": [
{
"type": "text",
"text": "Creative direction: A realistic hand touches a glowing lavender planet model on a black reflective tabletop. Concentric rings spread from the fingertip and small moons begin orbiting the sphere while the camera holds a close three-quarter view of the reflection.\n\nVisual treatment: Photoreal tabletop demonstration with controlled lavender emission and a dark reflection.\n\nShot sequence: 1. Frame the lavender sphere and its tabletop reflection.; 2. Bring the fingertip into contact and expand concentric light rings from that point.; 3. Let the small moons orbit while the three-quarter camera remains still.\n\nContinuity: Keep demonstration props, layout and hand contact consistent so the action remains legible.\nExclude: extra people or props, text, logos and watermarks."
}
],
"resolution": "720p",
"ratio": "16:9",
"duration": 5,
"generate_audio": true
}性能
Seedance 2.5 使用活动
当 Flatkey 积累足够请求流量后,这里会显示实时请求遥测数据。
活动
Seedance 2.5 使用活动
这里只展示真实的 Flatkey 请求数据;积累足够流量后才会显示图表。
价格
seedance-2.5 API 价格
下方价格来自当前模型的 Flatkey 定价数据,以及定价 API 返回的可见分组。
Seedance 2.5 功能
文档化契约覆盖文生视频和图生视频输入、参考素材、可选音频及受限输出设置。
文生视频与图生视频
可以从文字场景开始,也可以为已设计的主体、产品或分镜提供参考图。
参考素材与帧控制
请求可包含图片、视频和音频参考素材,并支持在参考驱动工作流中指定首帧和尾帧角色。
音视频生成
将音频生成作为明确的请求选项;不要假设所选路由未文档化的语言列表或音频行为。
时长与输出控制
提交任务前可选择 4–30 秒、480p 或 720p、自适应或支持的固定比例,以及音频设置。
对比
对比 Seedance 2.5 与 Seedance 2.0:文档化视频字段
此对比只记录已文档化的 Seedance 2.5 行为;Seedance 2.0 的未核实值不会被推测。
| 能力 | Seedance 2.0(未重新审计) | Seedance 2.5 |
|---|---|---|
| 片段时长 | 本次审计未核实 | 每次请求 4–30 秒 |
| 参考输入 | 本次审计未核实 | 总计最多 50 个:30 张图片、10 个视频和 10 个音频 |
| 帧控制 | 本次审计未核实 | 支持首帧和尾帧角色 |
| 音频 | 本次审计未核实 | 可在每次请求中启用音频生成 |
| 编辑工作流 | 本次审计未核实 | 参考驱动及首尾帧工作流 |
接入前先选对请求方式
核对支持的工作流、当前配置的实时费用,以及 Flatkey 实际使用的参数契约。
当目录提供固定单价时,根据当前 Playground 配置和实时目录价格计算。
- 当前配置
- 720p · 5s
- 实时单价
- from $0.188 / 秒 · 4s min
- 本次预估
- $0.940 $0.188 × 5s
最终费用以实际提交的请求和账户分组为准。Token 或分层计费无法简化成一个固定预估值。
工作流与 Model ID
只使用标记为可用的工作流。Flatkey 对外保持一个模型 ID,由请求体选择输入方式。
文生视频
通过文本提示词和支持的输出参数生成视频。
- 模型 ID
seedance-2.5- 接口
/v1/videos
图生视频
让一张或多张参考图动起来,并尽量保持主体与构图。
- 模型 ID
seedance-2.5- 接口
/v1/videos
参考生视频
使用已文档化的图片、视频或音频参考素材指导结果。
- 模型 ID
seedance-2.5- 接口
/v1/videos
视频编辑
在路由支持时编辑已有视频。
- 模型 ID
seedance-2.5- 接口
/v1/videos
视频续写
在路由支持时续写已有视频。
- 模型 ID
seedance-2.5- 接口
/v1/videos
参数兼容矩阵
以下取值与 Playground 和请求预览使用同一份模型配置。
resolution分辨率480p · 720p
默认值: 720pratio画面比例adaptive · 16:9 · 4:3 · 1:1 · 3:4 · 9:16
默认值: adaptiveduration时长4–30
默认值: 5generate_audio生成音频开 · 关
默认值: 开image参考素材上限30 个文件
接口: /v1/videosvideo参考素材上限10 个文件
接口: /v1/videosaudio参考素材上限10 个文件
接口: /v1/videos从首次测试到生产接入
Playground 与 API 使用同一套请求契约,并明确处理参数校验、余额、任务状态和产物获取。
请求生命周期
- 1
校验模型、提示词、参考素材和输出设置。
- 2
提交 POST 请求并保存返回的任务 ID。
- 3
轮询任务状态或处理已配置的回调。
- 4
从产物接口获取文件,并在失效前保存到自己的存储。
生产检查项
提交前拦截不支持的尺寸、时长、比例、格式或参考素材数量。
分别处理无效密钥、余额不足、限流和账户分组价格。
明确指出被拒绝的提示词或素材,让用户只替换失败的输入。
保留任务 ID,限制重试次数,且不能把超时当成生成成功。
提示词库
Seedance 2.5 提示词指南:六种工作流
这些按工作流编写的提示词可作为起点;输出取决于参考素材和请求设置。
使用 Seedance 2.0 生成
Creative direction: An anime student traces a winding black route across an aged parchment map at a wooden table inside a quiet library. The camera eases closer as warm specks of light appear between the bookshelves, then holds on the student's hand and the illuminated map. Visual treatment: Hand-drawn anime with warm library tones and restrained magical light. Shot sequence: 1. Establish the student, parchment and shelf depth.; 2. Follow the fingertip along the black route as warm light specks emerge.; 3. Ease into the illuminated map and hold the hand in focus. Continuity: Keep the character's face, clothing and key prop consistent; preserve screen direction across cuts. Exclude: extra people or props, text, logos and watermarks.
使用 Seedance 2.0 生成
Creative direction: A cream-enamel travel kettle with brushed-metal accents is presented on a warm gray studio surface. Its body, handle, spout and lid assemble through visible mechanical connections; once seated, a small plume of steam leaves the spout. The final frame shows the complete kettle from a clean three-quarter angle. Visual treatment: Photoreal product animation. A soft overhead key defines the enamel, and a narrow side light traces the brushed-metal edges. Shot sequence: 1. Show the separated parts and their connection points; 2. Assemble body, handle, spout and lid in a clear order without changing their shapes; 3. Hold the finished kettle as steam rises from the spout Continuity: Keep the product silhouette, cap or hinge, materials and prop positions stable; hold the final hero frame. Exclude: extra people or props, text, logos and watermarks.
使用 Seedance 2.0 生成
Creative direction: A white armored sci-fi rover rolls through a dusty landscape toward a monumental dark structure. Start close on its massive treaded wheel, track beside the moving vehicle as dust lifts, then widen to reveal the rover's destination. Visual treatment: Photoreal science-fiction previs with weathered armor, dusty air and monumental scale. Shot sequence: 1. Track the rotating tread from a low close-up.; 2. Continue alongside the white rover as its wheels throw dust backward.; 3. Widen to include the monumental dark destination without reversing travel direction. Continuity: Maintain scene geography, subject scale and motivated light direction throughout the camera move. Exclude: extra people or props, text, logos and watermarks.
使用 Seedance 2.0 生成
Creative direction: A cloaked traveler stands on a rust-colored canyon ridge at sunset. Move from a side view to behind the figure, revealing a vast settlement and a long curved structure across the canyon, then hold the traveler as a clear foreground silhouette. Visual treatment: Rendered fantasy game cinematic with rust-colored terrain and sunset backlight. Shot sequence: 1. Frame the cloaked traveler in profile on the ridge.; 2. Arc slowly behind the traveler to reveal the settlement and curved structure.; 3. Rest behind the foreground silhouette with the canyon open beyond. Continuity: Maintain character design, equipment geometry and travel direction from first to final frame. Exclude: extra people or props, text, logos and watermarks.
使用 Seedance 2.0 生成
Creative direction: A realistic hand touches a glowing lavender planet model on a black reflective tabletop. Concentric rings spread from the fingertip and small moons begin orbiting the sphere while the camera holds a close three-quarter view of the reflection. Visual treatment: Photoreal tabletop demonstration with controlled lavender emission and a dark reflection. Shot sequence: 1. Frame the lavender sphere and its tabletop reflection.; 2. Bring the fingertip into contact and expand concentric light rings from that point.; 3. Let the small moons orbit while the three-quarter camera remains still. Continuity: Keep demonstration props, layout and hand contact consistent so the action remains legible. Exclude: extra people or props, text, logos and watermarks.
使用 Seedance 2.0 生成
Creative direction: A lone performer silhouette stands on a low black stage while luminous ribbons sweep across the backdrop. Teal waves arrive first, followed by amber light ribbons that curl into layered arcs, ending in a centered wide composition around the figure. Visual treatment: Stage-projection visual with a black silhouette and layered teal-to-amber light. Shot sequence: 1. Establish the lone silhouette on the black stage.; 2. Sweep teal ribbons behind the figure, then introduce amber arcs.; 3. Complete the layered arcs and hold the centered wide stage. Continuity: Keep the main subject, palette and light behavior consistent as the visual pattern develops. Exclude: extra people or props, text, logos and watermarks.
为什么选择 Flatkey
为什么通过 Flatkey 使用 Seedance 2.5?
一个 Key 覆盖模型目录,清楚查看请求契约,并让价格与所选设置保持一致。
一个 Key 覆盖模型目录
视频、图片、音频和文本任务共用同一个 Flatkey 账号与 API Key。
文档化视频契约
在集成中明确 Seedance 的 content[] 请求、/v1/videos endpoint 和异步任务流程。
价格随请求变化
分辨率、时长和视频参考输入会改变公式;目录值不是统一的每秒价格承诺。
仅在有数据时显示实时指标
只有积累足够真实 Flatkey 流量时才显示遥测卡片,否则保持未报告状态。
API
Seedance 2.5 API:如何使用 /v1/videos
发送 Seedance content[] 项,保存 task id,并从 /v1/videos/{task_id}/content 获取结果。
curl https://router.flatkey.ai/v1/videos \ -H "Content-Type: application/json" \ -H "Authorization: Bearer sk-***" \ -d '{"model":"seedance-2.5","content":[{"type":"text","text":"Creative direction: An anime student traces a winding black route across an aged parchment map at a wooden table inside a quiet library. The camera eases closer as warm specks of light appear between the bookshelves, then holds on the student'"'"'s hand and the illuminated map.\n\nVisual treatment: Hand-drawn anime with warm library tones and restrained magical light.\n\nShot sequence: 1. Establish the student, parchment and shelf depth.; 2. Follow the fingertip along the black route as warm light specks emerge.; 3. Ease into the illuminated map and hold the hand in focus.\n\nContinuity: Keep the character'"'"'s face, clothing and key prop consistent; preserve screen direction across cuts.\nExclude: extra people or props, text, logos and watermarks."}],"ratio":"adaptive","resolution":"720p","duration":5,"generate_audio":true}' # Poll for the result (replace TASK_ID with the returned task id) curl "https://router.flatkey.ai/v1/videos/TASK_ID" \ -H "Authorization: Bearer sk-***"
常见问题
Seedance 2.5
API、价格和发布日期常见问题
价格、兼容性、限制,以及提示词和生成文件的处理方式。