跳到主要内容
Black Forest Labs检查中

FLUX 3 Video / Text To Video

flux-3-video-text-to-video

文生视频输出: 视频输入: 文本
正在加载价格…
官方原价 · 未验证

模型能力

Generate or continue a video with optional audio and draft mode.

HD / FHD · up to 20 seconds · draft mode

输入参数

仅列出此模型接受的字段。必填字段必须提供。

字段类型必填默认值可选值与约束
prompt
string必填—

Text prompt for video generation.

1–20480 chars

aspectRatio
string可选"auto"

Output aspect ratio; auto lets the model decide.

可选值: "auto", "21:9", "2:1", "16:9", "4:3", "1:1", "3:4", "9:16"

duration
integer可选—

Video duration in seconds (5-20); omit to auto-fit.

5–20

resolution
string必填"hd"

Video resolution: hd, or fhd (finished by the upsampler).

可选值: "hd", "fhd"

draft
boolean可选false

Draft mode: fast HD preview at a lower price.

generateAudio
boolean可选true

Generate synchronized audio (free).

safetyTolerance
integer可选2

Harm moderation tolerance, 0 strictest to 4, default 2.

0–4

限制与行为

  • 仅支持异步:先提交任务,再轮询结果。
  • prompt: 1–20480 chars
  • duration: 5–20
  • safetyTolerance: 0–4