正在加载模板…
⚡ 通过 API 调用

Google DeepMind’s upgraded AI video model for realistic motion generation, extended clip duration, multi-image reference control, and synchronized audio output in native 1080p.

模型类型:

定价: 36 积分 /条,不随时长变化。

在线试跑

表单已按模型规格预填 —— 可直接运行,也可先改任意字段。

可用
提示词

Describe the video: subject, action, camera, style and sound.

参考图

Optional. 1 image = first frame, 2 images = first and last frame (or 1–3 reference images for REFERENCE_2_VIDEO on Lite / Fast).

generation_type

Optional. Chosen automatically from the images when left empty.

画面比例

Output aspect ratio.

分辨率

1080p and 4K cost more than 720p.

时长

Video length in seconds. Reference to Video supports 8 seconds only.

余额: —预估预扣36 积分(生成前为预估,完成后显示实际扣除积分)
结果
历史

该变体的示例输出 —— 点「运行」生成你自己的。

费率表
lite36 积分 /条
fast72 积分 /条
quality300 积分 /条

按次计费(一口价),不随时长变化。

快速开始
POST/v1/videos/generations
curl https://modelfold.ai/v1/videos/generations \
  -H "Authorization: Bearer $MODELFOLD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"veo-3-1","prompt":"...","resolution":"720p","duration":5}'