多元探索 API多元探索 API
Omni Video

omni-fast Video Generation

Call `omni-fast` via `POST /v1/videos` to generate text-to-video, image-to-video, first/last frame, and multi-reference image video.

POSThttps://zx1.deepwl.net/v1/videos
Request
curl -X POST https://zx1.deepwl.net/v1/videos \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '
{
  "model": "omni-fast",
  "prompt": "Ocean waves gently rolling onto a sandy beach at golden hour, cinematic, warm sunlight",
  "seconds": "8",
  "aspect_ratio": "16:9",
  "resolution": "720p"
}'
Response
{
  "id": "video_abc123",
  "task_id": "video_abc123",
  "object": "video",
  "model": "omni-fast",
  "status": "queued",
  "progress": 0,
  "created_at": 1735689600,
  "video_url": ""
}

omni-fast submits asynchronous video tasks with a JSON request body, suitable for text-to-video, first-frame image-to-video, first/last frame, and multi-reference image video.

  • Asynchronous processing mode; returns id or task_id after submission.
  • Text-to-video only requires model, prompt, seconds, and the aspect ratio field.
  • First-frame image-to-video uses first_image_url.
  • First/last frame uses first_image_url and last_image_url.
  • Multi-reference images use images, up to 5; for reference video use omni-fast-v2v.

Request Headers

Authorizationstring必填

Authentication header. Uses a Bearer token, e.g. Bearer YOUR_API_KEY.

Content-Typestring必填

Request content type, must be application/json.

Request Body

modelstring必填

Fixed value omni-fast. Example: "omni-fast".

promptstring必填

Video prompt. Example: "Ocean waves gently rolling onto a sandy beach at golden hour".

secondsstring

Video duration. Recommended as a string; recommended range is 4 to 30 seconds. Example: "8".

aspect_ratiostring

Aspect ratio. Example values: "16:9", "9:16".

resolutionstring

Resolution field. Example values: "720p", "1080p", "2k", "4k".

first_image_urlstring

First frame image. Passing it enters first-frame image-to-video mode. Supports public URL or data:image/...;base64,.... Example: "https://example.com/first-frame.jpg".

last_image_urlstring

Last frame image. Must be used together with first_image_url. Example: "https://example.com/last-frame.jpg".

imagesarray<string>

Multi-reference image list, up to 5. Supports public URL or data:image/...;base64,.... Example: ["https://example.com/character.jpg"].

Request Examples

Response Examples

Response Fields

idstring

Video task ID. Can be used later for GET /v1/videos/{task_id} queries.

task_idstring

Compatibility field for the video task ID. Usually the same as id.

objectstring

Object type, usually video.

modelstring

The model used for this task, for example omni-fast.

statusstring

Task status. Common values are queued, in_progress, completed, failed.

progressnumber

Task progress, commonly in the range 0 to 100.

video_urlstring

The video URL after completion.

errorobject

The error object returned when a task fails or an API error occurs, usually containing message and code.

Use Cases

Vertical Text-to-Video

{
  "model": "omni-fast",
  "prompt": "A woman walking through a neon-lit Tokyo street at night, rain reflections, cinematic",
  "seconds": "8",
  "aspect_ratio": "9:16",
  "resolution": "720p"
}

First-Frame Image-to-Video

{
  "model": "omni-fast",
  "prompt": "The scene comes alive with gentle wind and drifting clouds",
  "first_image_url": "https://example.com/first-frame.jpg",
  "seconds": "8",
  "aspect_ratio": "16:9",
  "resolution": "720p"
}

Multi-Reference Image Video

{
  "model": "omni-fast",
  "prompt": "Use the first image as the character reference and the second image as the visual style reference.",
  "images": [
    "https://example.com/character.jpg",
    "https://example.com/style.jpg"
  ],
  "seconds": "8",
  "aspect_ratio": "16:9",
  "resolution": "720p"
}

Notes

  • omni-fast does not support the video, video_url, input_video reference-video fields.
  • images supports up to 5 images.
  • Image fields use JSON; multipart is not required.
  • It is recommended to poll GET /v1/videos/{task_id}, and after completion retrieve the generated MP4 from the returned video_url.
  • Reference-video editing or extension must use omni-fast-v2v.