Wan 2.6 - 文转视频

接口

POST /videos/generations

完整 URL: https://modelfold.ai/v1/videos/generations

鉴权：所有请求都需要 Authorization: Bearer <API_KEY> 请求头。

模型参数直接放在 JSON 请求体中，不要套 input。请求等待生成完成后返回 data[].url；支持的媒体模型也可使用 异步创建、轮询及回调。示例素材地址须替换为自己的公开可访问文件。计费及错误说明见 API 网关。

生成任务的输入参数

请求参数

请求体 (application/json)

参数	类型	必填	说明
model	string	是	用于生成的模型名称。必填字段。 - 此端点必须为 wan/2-6-text-to-video 默认值："wan/2-6-text-to-video"。 可选值：wan/2-6-text-to-video。 示例：wan/2-6-text-to-video。
prompt	string	是	本站网关要求传入 prompt，最长 2000 字。视频生成的文本提示。同时支持中文和英文，最少1个字符，最多5,000个字符。（最大长度：5000个字符） maxLength: 2000. 示例：In a hyperrealistic ASMR video, a hand uses a knitted knife to slowly slice a burger made entirely of knitted wool. The satisfyingly crisp cut reveals a detailed cross-section of knitted meat, lettuce, and tomato slices. Captured in a close-up with a shallow depth of field, the scene is set against a stark, matte black surface. Cinematic lighting makes the surreal yarn textures shine with clear reflections. The focus is on the deliberate, satisfying motion and the unique, tactile materials.。
duration	string	否	生成视频的持续时间（秒） 默认值："5"。 可选值：5 / 10 / 15。 示例：5。
resolution	string	否	输出分辨率：720p 或 1080p。请显式传入。 可选值：720p / 1080p。 示例：1080p。
multi_shots	boolean	否	多镜头参数。用于控制AI视频生成时的镜头构图风格，决定生成的视频是单个连续镜头，还是多个带有转场的镜头。 默认值：false。 示例：false。
nsfw_checker	boolean	否	默认 false。为 false 时不额外进行内容过滤，结果由模型直接返回。

请求示例

curl -X POST "https://modelfold.ai/v1/videos/generations" \
  -H "Authorization: Bearer $MODELFOLD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "wan/2-6-text-to-video",
  "prompt": "In a hyperrealistic ASMR video, a hand uses a knitted knife to slowly slice a burger made entirely of knitted wool. The satisfyingly crisp cut reveals a detailed cross-section of knitted meat, lettuce, and tomato slices. Captured in a close-up with a shallow depth of field, the scene is set against a stark, matte black surface. Cinematic lighting makes the surreal yarn textures shine with clear reflections. The focus is on the deliberate, satisfying motion and the unique, tactile materials.",
  "duration": "5"
}'

{
  "model": "wan/2-6-text-to-video",
  "prompt": "In a hyperrealistic ASMR video, a hand uses a knitted knife to slowly slice a burger made entirely of knitted wool. The satisfyingly crisp cut reveals a detailed cross-section of knitted meat, lettuce, and tomato slices. Captured in a close-up with a shallow depth of field, the scene is set against a stark, matte black surface. Cinematic lighting makes the surreal yarn textures shine with clear reflections. The focus is on the deliberate, satisfying motion and the unique, tactile materials.",
  "duration": "5"
}

响应

200 — 生成完成。usage 返回实际计费明细；结果地址仅作结构示例。

{
  "ok": true,
  "created": 1792134000,
  "data": [
    {
      "url": "https://modelfold.ai/uploads/outputs/result.mp4"
    }
  ],
  "usage": {}
}