Skip to main content
POST

omni-fast

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.

Method and Path

Request Examples

Response Examples

Authentication

Use Bearer Token authentication:
All request examples must include the Authorization header. JSON requests must also include:

Body

string
required
Fixed value omni-fast. Example: "omni-fast".
string
required
Video prompt. Example: "Ocean waves gently rolling onto a sandy beach at golden hour".
string
Video duration. Recommended as a string; recommended range is 4 to 30 seconds. Example: "8".
string
Aspect ratio. Example values: "16:9", "9:16".
string
Resolution field. Example values: "720p", "1080p", "2k", "4k".
string
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".
string
Last frame image. Must be used together with first_image_url. Example: "https://example.com/last-frame.jpg".
array<string>
Multi-reference image list, up to 5. Supports public URL or data:image/...;base64,.... Example: ["https://example.com/character.jpg"].

Response

string
Video task ID. Can be used later for GET /v1/videos/{task_id} queries.
string
Compatibility field for the video task ID. Usually the same as id.
string
Object type, usually video.
string
The model used for this task, for example omni-fast.
string
Task status. Common values are queued, in_progress, completed, failed.
number
Task progress, commonly in the range 0 to 100.
string
The video URL after completion.
object
The error object returned when a task fails or an API error occurs, usually containing message and code.

Use Cases

Vertical Text-to-Video

First-Frame Image-to-Video

Multi-Reference Image Video

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.