← All models
Gemini Omni Flash 1.1 Reference to Video
google/gemini-omni-flash/v1.1/reference-to-video
Video generationby Google
Gemini Omni Flash 1.1 is Google's multimodal video model. Reasoning across all inputs to produce a single coherent result, with characters retaining their face, clothing, and voice throughout
Example
Details
- Accepts
- text + image + video
Pricing
- Price
- 0.021 cr / second
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| promptrequired | string | The text prompt describing the video. Reference media is sent in list order before the prompt. |
| duration | integer | The duration of the generated video, in seconds. |
| image_urls | array | URLs of reference images to incorporate into the video. |
| resolution | stringenum: 360p, 720p, 1080p, 4k | The resolution of the generated video. |
| aspect_ratio | stringenum: 16:9, 9:16 | The aspect ratio of the generated video. |
| reference_video_urls | array | URLs of up to three reference videos. Each video must be at most three seconds long. |
Output
| Field | Type | Description |
|---|---|---|
| video | — | The generated video. |
| interaction_id | — | The Google interaction ID. Pass this as previous_interaction_id to extend the generated video. |