Skip to main content
POST
  • Use gemini-omni-flash (or the configured gemini_omni_flash alias) in the model field
  • Supports text-to-video and reference-image-to-video
  • Supports 4 / 6 / 10 second durations
  • Supports 720p and 1080p; 1080p is landscape-only
  • Async task API: submit a task, then query by task ID
This page documents the non-official legacy/FlowReverse-style omni_flash channel. It uses the channel’s configured upstream endpoint and API key, not the Vertex AI Interactions API. Other legacy channel implementations may have different limits. See the separate gemini-omni-flash-preview-official page for the Vertex Service Account/OAuth channel.
Upload local images with the Upload 이미지 API first, then pass the returned URLs in image_urls. Do not pass base64 image data directly.

Authorizations

string
필수
Use Bearer Token authentication:

Body

string
기본값:"gemini-omni-flash"
필수
모델 name. Use gemini-omni-flash; some channels expose the gemini_omni_flash alias.
string
필수
Text prompt for video generation.
integer
기본값:"6"
Video duration. Supported values: 4, 6, or 10 seconds.
string
기본값:"16:9"
Video aspect ratio:
  • 16:9 landscape
  • 9:16 portrait
string
기본값:"720p"
Video resolution: 720p or 1080p; 1080p is landscape-only.
string[]
Optional public reference image URL array with up to 3 items. Omit it for text-to-video. Base64/data URIs and video inputs are not supported by this channel.

응답

string
Task ID for status polling.
string
Object type, usually generation.task.
string
모델 name used for the request.
string
Task status: queued, in_progress, completed, or failed.
integer
Task creation timestamp.
string
Generated video URL when the task completes.

Examples

Query Task

The generation endpoint returns a task ID. Use the common video task status endpoint to fetch status and results: