文生视频
- Python
- cURL
- Node.js
from openai import OpenAI
import time
client = OpenAI(
api_key="EZTOKENS_API_KEY",
base_url="https://api.eztokens.ai/v1"
)
response = client.chat.completions.create(
model="kling",
messages=[{
"role": "user",
"content": "A panda eating bamboo in a bamboo forest, cinematic lighting"
}],
max_tokens=3000
)
task_id = response.id
while True:
status = client.chat.completions.task_status(task_id)
if status.status == "succeed":
print(f"Video ready: {status.video_url}")
break
elif status.status == "failed":
print("Generation failed")
break
time.sleep(5)
# 提交任务
curl https://api.eztokens.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $EZTOKENS_API_KEY" \
-d '{
"model": "kling",
"messages": [{
"role": "user",
"content": "A panda eating bamboo in a bamboo forest, cinematic lighting"
}],
"max_tokens": 3000
}'
import OpenAI from "openai";
const client = new OpenAI({
apiKey: "EZTOKENS_API_KEY",
baseURL: "https://api.eztokens.ai/v1",
});
const response = await client.chat.completions.create({
model: "kling",
messages: [{
role: "user",
content: "A panda eating bamboo in a bamboo forest, cinematic lighting"
}],
max_tokens: 3000,
});
const taskId = response.id;
console.log(`Task created: ${taskId}`);
// Poll for result
let status;
do {
status = await client.chat.completions.task_status(taskId);
if (status.status === "succeed") break;
await new Promise(r => setTimeout(r, 5000));
} while (status.status !== "failed");
图生视频
response = client.chat.completions.create(
model="kling",
messages=[{
"role": "user",
"content": [
{"type": "text", "text": "Make the ocean waves move in this image"},
{"type": "image_url", "image_url": {"url": "https://example.com/ocean.jpg"}}
]
}],
max_tokens=3000
)
可灵视频生成是异步任务，请通过任务 ID 轮询获取结果。具体模型 ID 请查看控制台模型库。