Gemini Omni Imagem para Vídeo: Image-to-Video

Como Usar Gemini Omni Imagem para Vídeo

1. 上传参考图 通过 image_urls 提供 1–5 张图像。每张图像都会作为视觉锚点，模型会在各帧之间保持主体身份。

2. 编写动作和场景Prompt 描述视频中发生的事情——动作、场景、光照和音频提示。例如：'The subject slowly turns to face the camera as golden-hour light sweeps across the scene, leaves rustling in the breeze.'

3. 选择时长和分辨率 选择 4、6、8 或 10 秒。选择 360p 获得快速、低成本的草稿，选择 720p / 1080p 获得标准Saída，或选择 4K 获得更高分辨率。

4. 选择宽高比

   • 16:9 — 宽屏、电影感
   • 9:16 — 竖屏、移动端优先

5. 提交并轮询 POST 到 /api/v1/gemini-omni-image-to-video，并轮询 GET /api/v1/predictions/{request_id}/result，直到 status 为 completed。

6. 请求示例

   curl -X POST https://api.muapi.ai/api/v1/gemini-omni-image-to-video \
     -H "Authorization: Bearer YOUR_API_KEY" \
     -H "Content-Type: application/json" \
     -d '{
       "prompt": "The subject slowly turns to face the camera as golden-hour light sweeps across the scene.",
       "image_urls": ["https://example.com/reference.jpg"],
       "duration": 8,
       "resolution": "1080p"
     }'