跳到主要内容
Google检查中

gemini-omni-flash/image-to-video

gemini-omni-flash-image-to-video-economy

图生视频输出: 视频输入: 文本 + 图像
正在加载价格…
官方原价 · 未验证

模型能力

Gemini Omni Flash Image-to-Video turns reference images into dynamic short videos. It supports single-image video generation with 1 image and reference fusion with 3 images, offering 720p, 1080p, and 4k outputs with 4, 6, 8, and 10-second durations for character animation, product showcases, creative shots, and multi-reference video creation.

Image-Driven VideoSingle-Image Animation3-Image Reference Fusion720p/1080p/4k4-10s DurationFlexible Aspect Ratios

输入参数

仅列出此模型接受的字段。必填字段必须提供。

字段类型必填默认值可选值与约束
prompt
string必填"make the character smile and slowly turn around, cinematic camera motion"

Video prompt. Describe how the reference image should move, camera motion, visual style, and audio cues in detail.

1–2048 chars

imageUrls
string[]必填—

Reference images. Use 1 image for single-image video generation or 3 images for reference fusion. 2 images are not supported.

≤ 3 items · HTTPS image URL or media:<uuid>

duration
string必填"6"

Video duration in seconds. Supported values: 4, 6, 8, 10.

可选值: "4", "6", "8", "10"

resolution
string必填"720p"

Video resolution.

可选值: "720p", "1080p", "4k"

aspectRatio
string可选"16:9"

Video aspect ratio.

可选值: "16:9", "9:16"

限制与行为

  • 仅支持异步:先提交任务,再轮询结果。
  • prompt: 1–2048 chars
  • imageUrls: ≤ 3 items
  • 媒体输入接受公开 HTTPS URL,或 POST /api/v1/media 返回的 media:<uuid> 引用。