跳转到内容

FLUX 3 Max Text to Video

集成

模型 id blackforestlabs/flux-3-max/text-to-video
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://vit.doitong.com/api/v1/run/blackforestlabs/flux-3-max/text-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Four-way CCTV-style split-screen showing the same real-time event inside a convenience shop. Divide the frame into four equal security-camera views with timestamps. Top left: wide ceiling-corner view covering aisles, entrance, and cashier. Top right: overhead view above the central aisle. Bottom left: camera facing the checkout counter. Bottom right: camera near the entrance looking inward. At the 2-second mark, a customer takes a boxed item from a shelf, accidentally bumps a display, catches one falling bottle, then places the box on the checkout counter. The cashier turns, scans it, and hands over a receipt as another shopper crosses behind them. All four views must remain perfectly synchronized, showing identical people, movements, object positions, occlusions, timestamps, lighting, and physical reactions. Use realistic low-resolution CCTV footage, slight lens distortion, fixed cameras, and no cinematic camera movement.",
    "duration": 5,
    "resolution": "720p",
    "aspect_ratio": "16:9",
    "generate_audio": false
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://vit.doitong.com/api/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

与示例类似的文件: $0.425 425 API 积分 运行前会测量你的文件 在此页面运行

获取 API 密钥
Black Forest Labs 文生视频 原生音频5–20 秒最高 1080p #audio#long-clips#1080p

Black Forest Labs 的视频模型,生成带声音的 5 到 20 秒视频片段,支持 720p 或 1080p。

示例

输出 · ~30 秒

提示词Four-way CCTV-style split-screen showing the same real-time event inside a convenience shop. Divide the frame into four equal security-camera views with timestamps. Top left: wide ceiling-corner view covering aisles, entrance, and cashier. Top right: overhead view above the central aisle. Bottom left: camera facing the checkout counter. Bottom right: camera near the entrance looking inward. At the 2-second mark, a customer takes a boxed item from a shelf, accidentally bumps a display, catches one falling bottle, then places the box on the checkout counter. The cashier turns, scans it, and hands over a receipt as another shopper crosses behind them. All four views must remain perfectly synchronized, showing identical people, movements, object positions, occlusions, timestamps, lighting, and physical reactions. Use realistic low-resolution CCTV footage, slight lens distortion, fixed cameras, and no cinematic camera movement.

5 s720p16:9generate_audio: false$0.213 · 213 API 积分

X 上 @umesh_ai 的提示词

构建请求

控件根据模型架构生成。更改控件时,代码和价格会同步更新。

•必填

所需视频的文本描述。

duration 5 s

输出视频长度,单位为秒。

resolution

输出视频的分辨率。

aspect_ratio

生成视频的宽高比;`auto` 会匹配第一张图像,但如果输入是文本提示词,则选择 16:9。

高级 reasoning_level · seed
reasoning_level 默认 high

推理工作量控制生成速度与执行器用于理解提示词的工作量之间的权衡:工作量越大,耗时越长。

生成种子;省略时使用随机值。

POST /run/blackforestlabs/flux-3-max/text-to-video?wait=20 报价 → $0.425
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://vit.doitong.com/api/v1/run/blackforestlabs/flux-3-max/text-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Four-way CCTV-style split-screen showing the same real-time event inside a convenience shop. Divide the frame into four equal security-camera views with timestamps. Top left: wide ceiling-corner view covering aisles, entrance, and cashier. Top right: overhead view above the central aisle. Bottom left: camera facing the checkout counter. Bottom right: camera near the entrance looking inward. At the 2-second mark, a customer takes a boxed item from a shelf, accidentally bumps a display, catches one falling bottle, then places the box on the checkout counter. The cashier turns, scans it, and hands over a receipt as another shopper crosses behind them. All four views must remain perfectly synchronized, showing identical people, movements, object positions, occlusions, timestamps, lighting, and physical reactions. Use realistic low-resolution CCTV footage, slight lens distortion, fixed cameras, and no cinematic camera movement.",
    "duration": 5,
    "resolution": "720p",
    "aspect_ratio": "16:9",
    "generate_audio": false
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://vit.doitong.com/api/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

运行此请求

你的密钥会保留在此浏览器中:仅发送到 Doitong API;只有勾选“记住”后才会保存到 localStorage。 获取 API 密钥

关于 FLUX 3 Max Text to Video

FLUX 3 Max 将 FLUX 风格带入视频:细节丰富、光照良好的帧、自然运动和生成的音频。渲染前会对提示词进行推理过程(高或低强度),支持 5 到 20 秒的视频片段,以及从 9:16 到 21:9 的八种宽高比,分辨率为 720p 或 1080p。使用种子可让运行结果可重复。

参数

名称类型 默认值允许值 描述
prompt必填
类型string
所需视频的文本描述。
duration可选
类型enum
默认值5
567891011121314151617181920
输出视频长度,单位为秒。
resolution可选
类型enum
默认值720p
720p1080p
输出视频的分辨率。
reasoning_level可选
类型enum
默认值high
lowhigh
推理工作量控制生成速度与执行器用于理解提示词的工作量之间的权衡:工作量越大,耗时越长。
aspect_ratio可选
类型enum
默认值auto
auto21:92:116:94:31:13:49:16
生成视频的宽高比;`auto` 会匹配第一张图像,但如果输入是文本提示词,则选择 16:9。
generate_audio可选
类型boolean
默认值true
控制视频是否包含生成的音频。
seed可选
类型integer | null
生成种子;省略时使用随机值。
必填

输出

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "blackforestlabs/flux-3-max/text-to-video",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 425,
    "usd": "0.425",
    "charged": 425,
    "refunded": 0
  },
  "input": {
    "prompt": "A red panda walks along a mossy log in a sunlit forest, pauses to sniff the air, then climbs over a branch",
    "duration": 5,
    "resolution": "720p"
  },
  "output": {
    "video": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_name": "0-output.mp4",
      "file_size": 1843200,
      "width": 1024,
      "height": 768,
      "fps": 1.0,
      "duration": 5,
      "num_frames": 1
    },
    "seed": 42,
    "timings": {}
  },
  "outputs": [
    {
      "type": "video",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_size": 1843200,
      "width": 1280,
      "height": 720,
      "duration": 5,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://vit.doitong.com/api/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://vit.doitong.com/api/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
你的文件,由你选择每个 outputs[].url 都是存储中的副本:可永久保存(按 GB-月付费),也可免费保存 7 天,由账户设置或 ?storage= 决定。
每个模型的结构相同图像、视频和音频均包含 type、url、content_type、width、height 和 duration。output 是模型自身的结果对象。
输出字段
video
object {url, content_type, file_name, file_size, width, height, fps, duration, num_frames}模型生成的视频。
seed
integer生成过程中使用的种子值。
timings
object计时数据;`inference` 中省略提示词扩展、解码和上传耗时,仅计算模型视频去噪的秒数。

更多模型:文生视频

对于 AI 代理:此页面的 Markdown 版本位于 https://doitong.com/zh/developers/models/blackforestlabs/flux-3-max/text-to-video.md. 所有模型和指南: https://doitong.com/developers/llms.txt