輸出解析度
根據已發布的 endpoint schema,支援 720p, 1080p。
curl -X POST https://runapi.ai/api/v1/wan/image_to_video \
-H "Authorization: Bearer $RUNAPI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "wan-2.5-image-to-video",
"image_url": "https://cdn.runapi.ai/public/samples/image.jpg",
"prompt": "Generate a 5-second video of a cat jumping onto a bookshelf, natural indoor lighting, handheld camera feel."
}'
import { WanClient } from "@runapi.ai/wan";
const client = new WanClient();
const result = await client.imageToVideo.run({
model: "wan-2.5-image-to-video",
image_url: "https://cdn.runapi.ai/public/samples/image.jpg",
prompt: "Generate a 5-second video of a cat jumping onto a bookshelf, natural indoor lighting, handheld camera feel.",
});
import os
import requests
response = requests.post(
"https://runapi.ai/api/v1/wan/image_to_video",
headers={"Authorization": f"Bearer {os.environ['RUNAPI_API_KEY']}"},
json={"model":"wan-2.5-image-to-video","image_url":"https://cdn.runapi.ai/public/samples/image.jpg","prompt":"Generate a 5-second video of a cat jumping onto a bookshelf, natural indoor lighting, handheld camera feel."}
)
response.raise_for_status()
<?php
$client = curl_init("https://runapi.ai/api/v1/wan/image_to_video");
curl_setopt_array($client, [
CURLOPT_HTTPHEADER => ["Authorization: Bearer " . getenv("RUNAPI_API_KEY"), "Content-Type: application/json"],
CURLOPT_POSTFIELDS => json_encode([
'model' => 'wan-2.5-image-to-video',
'image_url' => 'https://cdn.runapi.ai/public/samples/image.jpg',
'prompt' => 'Generate a 5-second video of a cat jumping onto a bookshelf, natural indoor lighting, handheld camera feel.',
])
]);
$response = curl_exec($client);
RunApi client = new RunApi(System.getenv("RUNAPI_API_KEY"));
Task task = client.imageToVideo().run({"model":"wan-2.5-image-to-video","image_url":"https://cdn.runapi.ai/public/samples/image.jpg","prompt":"Generate a 5-second video of a cat jumping onto a bookshelf, natural indoor lighting, handheld camera feel."});
task.waitForResult();
require "runapi/wan"
client = RunApi::Wan::Client.new
result = client.image_to_video.run(
model: "wan-2.5-image-to-video",
image_url: "https://cdn.runapi.ai/public/samples/image.jpg",
prompt: "Generate a 5-second video of a cat jumping onto a bookshelf, natural indoor lighting, handheld camera feel."
)
client := runapi.NewClient(os.Getenv("RUNAPI_API_KEY"))
task, err := client.imageToVideo.Run({"model":"wan-2.5-image-to-video","image_url":"https://cdn.runapi.ai/public/samples/image.jpg","prompt":"Generate a 5-second video of a cat jumping onto a bookshelf, natural indoor lighting, handheld camera feel."})
if err != nil { log.Fatal(err) }
task.Wait()
$ runapi generate \
--model wan-2.5-image-to-video \
--endpoint image_to_video \
--wait
18 個版本可用
選擇任意模型,數秒內即可開始生成。
選擇任意模型,數秒內即可開始生成。
| 提供者 | Alibaba |
| 模型 ID | wan-2.5-image-to-video |
| 模態 | Video |
| 任務類型 | Asynchronous |
| API 端點 | /api/v1/wan/image_to_video |
| 計費單位 | second |
| 輸入參數 | duration_seconds, first_frame_image_url, output_resolution |
| 最大解像度 | 720p, 1080p |
| 目錄狀態 | 可正常運作 |
免費註冊後,在控制台建立 wan-2.5-image-to-video 的 API 金鑰。
向 /api/v1/wan/image_to_video 發送 POST 請求,並傳入 wan-2.5-image-to-video 模型 ID 和參數。
輪詢工作或按照回呼取得已完成的 wan-2.5-image-to-video 結果。
根據已發布的 endpoint schema,支援 720p, 1080p。
可設定 3 個已記錄的參數,包括 duration_seconds, first_frame_image_url, output_resolution。
開放 1 個公開 endpoint:image_to_video。
按 second 計量,無需訂閱。
duration_seconds暫無描述。
output_resolution暫無描述。 (720p, 1080p)
first_frame_image_url暫無描述。
由文字 brief 生成產品發佈短片同短版廣告,將製作時間由幾星期縮短到幾個鐘。
無需攝影機或團隊,都可以大規模將課程腳本轉成動畫解說影片。
直接由 prompt 為社交平台製作易爆紅的短內容。
傳入 quickstart 顯示嘅 model ID。
每個 key 的 rate limit 會按使用層級而定。請查看定價頁了解最新限制。
可以——variant 只係一個旗標。只要更改 model 參數就可以切換。
在可用 streaming 的情況下,RunAPI 會端到端串流。
可以在公開 GitHub repo 開 issue,或者電郵支援團隊。