跳到主要内容
xAI检查中

xai/grok-imagine-v1.5/image-to-video

xai-grok-imagine-v1-5-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

It is engineered to breathe life into static concepts while maintaining absolute subject identity. By deeply analyzing the geometric structure and material properties of a reference image, it synthesizes motion that aligns perfectly with physical intuition. The model excels in temporal stability and lighting inheritance, ensuring that core elements remain undistorted during intense transitions. It provides a seamless bridge from a single visual reference to a high-tension, cinematic sequence characterized by fluid motion and professional-grade rendering.

Identity-Locked SynthesisDynamic Physics ModelingMaterial Lighting InheritanceStrong Temporal StabilityCinematic Motion FidelityUltra-Low Flickering Quality

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—

1–20000 chars

aspectRatio
string必填"16:9"

可选值: "2:3", "3:2", "1:1", "16:9", "9:16"

imageUrls
string[]可选—

≤ 7 items · HTTPS image URL or media:<uuid>

resolution
string必填"480p"

可选值: "720p", "480p"

duration
integer必填6

Video duration (seconds), range 6-15s

6–15

限制与行为

  • 仅支持异步:先提交任务,再轮询结果。
  • prompt: 1–20000 chars
  • imageUrls: ≤ 7 items
  • duration: 6–15
  • 媒体输入接受公开 HTTPS URL,或 POST /api/v1/media 返回的 media:<uuid> 引用。