gemini-omni-flash-1-1-reference-to-video API | MuAPI: Image-to-Video
Jelajahi dan integrasikan model AI gemini-omni-flash-1-1-reference-to-video melalui MuAPI. Dapatkan inferensi berkecepatan tinggi dan harga kompetitif.
Jelajahi dan integrasikan model AI gemini-omni-flash-1-1-reference-to-video melalui MuAPI. Dapatkan inferensi berkecepatan tinggi dan harga kompetitif.
About this model
Model gemini-omni-flash-1-1-reference-to-video menyediakan kemampuan generasi AI mutakhir di platform MuAPI.
Cost analysis
| Provider | Cost | Notes |
|---|---|---|
| muapi | $0.048–$0.48 per second of output (by resolution) | Pay-per-generation, no subscription. Combine up to 7 reference images and 3 short reference video clips in one call. |
| Fal.ai | Harga per detik yang sebanding | 相同的底层模型（google/gemini-omni-flash/v1.1/reference-to-video）。 |
| Replicate | Tidak tersedia | Gemini Omni 1.1 Flash Reference to Video is not listed on Replicate. |
Pay-per-generation, no subscription. Combine up to 7 reference images and 3 short reference video clips in one call.
相同的底层模型（google/gemini-omni-flash/v1.1/reference-to-video）。
Gemini Omni 1.1 Flash Reference to Video is not listed on Replicate.
** Competitor pricing is estimated based on similar model architectures and usage tiers.
Configuration schema
| Parameter | Type | Description | Default |
|---|---|---|---|
| Prompt Teks | string | 描述Video的文本Prompt teks。参考媒体按列表顺序在Prompt teks中引用，例如 <IMAGE_REF_0>、<VIDEO_REF_0>。 | A cat inspired by <IMAGE_REF_0> walks through the setting in <VIDEO_REF_0>. |
| 参考Gambar | array | URLs of reference images to incorporate into the video, referenced in the prompt as <IMAGE_REF_0>, <IMAGE_REF_1>, etc. | - |
| 参考Video | array | Up to 3 reference video clips, each at most 3 seconds long, referenced in the prompt as <VIDEO_REF_0>, <VIDEO_REF_1>, etc. | - |
| Rasio Aspek | Enum (2 options) | OutputVideo的Rasio aspek。 | 16:9 |
| Resolusi | Enum (4 options) | Output resolution. Billed per second of generated video: $0.048/s at 360p, $0.16/s at 720p, $0.24/s at 1080p, $0.48/s at 4K. | 720p |
| Durasi (Detik)（秒） | int | Duration of the generated video, in seconds. | 8 |
描述Video的文本Prompt teks。参考媒体按列表顺序在Prompt teks中引用，例如 <IMAGE_REF_0>、<VIDEO_REF_0>。
A cat inspired by <IMAGE_REF_0> walks through the setting in <VIDEO_REF_0>.URLs of reference images to incorporate into the video, referenced in the prompt as <IMAGE_REF_0>, <IMAGE_REF_1>, etc.
-Up to 3 reference video clips, each at most 3 seconds long, referenced in the prompt as <VIDEO_REF_0>, <VIDEO_REF_1>, etc.
-OutputVideo的Rasio aspek。
16:9Output resolution. Billed per second of generated video: $0.048/s at 360p, $0.16/s at 720p, $0.24/s at 1080p, $0.48/s at 4K.
720pDuration of the generated video, in seconds.
8Developer documentation
Panduan integrasi cepat untuk gemini-omni-flash-1-1-reference-to-video. Hubungkan dengan kunci API MuAPI Anda dan mulai lakukan panggilan inferensi.
Frequently asked
它会根据提示词生成新视频；提示词通过标签——`<IMAGE_REF_0>`、`<VIDEO_REF_0>` 等——引用参考图像和短参考视频片段，并在一次请求中组合最多 7 张图像和 3 个视频片段。
参考媒体按 URL 列出的顺序进行引用：第一个 `image_urls` 项是 `<IMAGE_REF_0>`，第二个是 `<IMAGE_REF_1>`，依此类推；第一个 `reference_video_urls` 项是 `<VIDEO_REF_0>`，以此类推。请直接在 `prompt` 文本中使用这些标签。
每个参考视频片段最长为 3 秒，每次请求最多可提供 3 个参考视频。
根据生成视频的分辨率按秒计费：360p 为 $0.048/s，720p 为 $0.16/s，1080p 为 $0.24/s，4K 为 $0.48/s。10 秒的 1080p 片段费用为 $2.40。
视频编辑使用一个源视频和一条编辑指令，返回同一片段的重新设计版本。参考图生视频则根据提示词生成新视频，并利用按标签引用的多张参考图像和片段。