提供源视频和描述接下来应发生什么的文本 prompt，以扩展现有视频。结果是一个从输入视频最后一帧无缝衔接并继续生成内容的完整视频。

源视频可以是公开 URL、base64 编码的 data URI，或来自file_id的Files API。有关如何使用Imagine → Files API Integration作为 input，请参阅file_id。

该 duration参数控制仅扩展部分的长度，而不是总输出长度。例如，如果输入视频为 10 秒，并将duration设为 5，则返回的视频长度为 15 秒（10 秒原视频 + 5 秒扩展）。

import os
import xai_sdk

client = xai_sdk.Client(api_key=os.getenv("XAI_API_KEY"))

response = client.video.extend(
    prompt="The shot pans to an over the shoulder perspective. Calm controlled scene.",
    model="grok-imagine-video",
    video_url="<VIDEO_URL>",
    duration=10,
)

print(response.url)

import os
import time
import requests

headers = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer {os.environ['XAI_API_KEY']}",
}

response = requests.post(
    "https://api.x.ai/v1/videos/extensions",
    headers=headers,
    json={
        "model": "grok-imagine-video",
        "prompt": "The shot pans to an over the shoulder perspective. Calm controlled scene.",
        "duration": 10,
        "video": {"url": "<VIDEO_URL>"},
    },
)

request_id = response.json()["request_id"]

while True:
    result = requests.get(
        f"https://api.x.ai/v1/videos/{request_id}",
        headers={"Authorization": headers["Authorization"]},
    )
    data = result.json()
    if data["status"] == "done":
        print(data["video"]["url"])
        break
    elif data["status"] in ("expired", "failed"):
        print(f"Request {data['status']}")
        break
    time.sleep(5)

import { xai } from "@ai-sdk/xai";
import { experimental_generateVideo as generateVideo } from "ai";

const source = await generateVideo({
    model: xai.video("grok-imagine-video-1.5"),
    prompt: "A cat sitting on a sunlit windowsill, tail gently swishing.",
    duration: 5,
    aspectRatio: "16:9",
    providerOptions: {
        xai: {
            pollTimeoutMs: 600000,
        },
    },
});

const sourceUrl = source.providerMetadata?.xai?.videoUrl;

const extended = await generateVideo({
    model: xai.video("grok-imagine-video"),
    prompt: "The cat turns its head, notices a butterfly, and leaps off.",
    duration: 6,
    providerOptions: {
        xai: {
            mode: "extend-video",
            videoUrl: sourceUrl,
            pollTimeoutMs: 600000,
        },
    },
});

const extendedVideoUrl = extended.providerMetadata?.xai?.videoUrl;
console.log(extendedVideoUrl);

# Start the video extension request
REQUEST_ID=$(curl -s -X POST https://api.x.ai/v1/videos/extensions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $XAI_API_KEY" \
  -d '{
    "model": "grok-imagine-video",
    "prompt": "The shot pans to an over the shoulder perspective. Calm controlled scene.",
    "duration": 10,
    "video": {"url": "<VIDEO_URL>"}
  }' | jq -r '.request_id')

# Poll until the video is ready
while true; do
  RESULT=$(curl -s https://api.x.ai/v1/videos/$REQUEST_ID \
    -H "Authorization: Bearer $XAI_API_KEY")
  STATUS=$(echo "$RESULT" | jq -r '.status')
  if [ "$STATUS" = "done" ]; then
    echo "$RESULT" | jq -r '.video.url'
    break
  elif [ "$STATUS" = "failed" ] || [ "$STATUS" = "expired" ]; then
    echo "Request $STATUS"; echo "$RESULT" | jq .
    break
  fi
  sleep 5
done

Video editing 使用/v1/videos/editsendpoint，以及 Python SDK 中的client.video.generate(video_url=...)。在 AI SDK 中，将providerOptions.xai.mode设置为"edit-video"或"extend-video"，并传入providerOptions.xai.videoUrl。两个流程都使用相同的 asynchronous polling pattern，AI SDK 会在providerMetadata.xai.videoUrl中返回由 xAI 托管的输出 URL。

Video Generation，根据文本 prompt 生成视频
Video Editing，编辑现有视频
Image-to-Video，让静态图像动起来
API Reference，完整的 endpoint 文档
Imagine API Landing Page，查看 Imagine API 的实际效果

模型能力

Video Extension

相关内容