Veo-3.1 最佳实践

response = client.chat.completions.create(
    model="veo-3.1-fl",
    messages=[{
        "role": "user",
        "content": [
            {
                "type": "text",
                "text": "让这张图片中的场景动起来,微风吹动树叶,云彩缓缓移动"
            },
            {
                "type": "image_url",
                "image_url": {
                    "url": "https://example.com/scene.jpg"
                }
            }
        ]
    }],
    stream=True
)

response = client.chat.completions.create(
    model="veo-3.1-fl",
    messages=[{
        "role": "user",
        "content": [
            {
                "type": "text",
                "text": "创建从第一张图到第二张图的平滑过渡,保持自然流畅的运动"
            },
            {
                "type": "image_url",
                "image_url": {"url": "https://example.com/start.jpg"}
            },
            {
                "type": "image_url",
                "image_url": {"url": "https://example.com/end.jpg"}
            }
        ]
    }],
    stream=True
)

优秀示例:
"黄昏时分,金色阳光从右侧斜照,在地面投下长长的影子,光线穿过薄雾形成丁达尔效应"

要点:
✓ 时间(黄昏时分)
✓ 光源方向(从右侧斜照)
✓ 光影效果(长影子、丁达尔效应)
✓ 环境因素(薄雾)

response = client.chat.completions.create(
    model="veo-3.1-fast",
    messages=[{
        "role": "user",
        "content": [{"type": "text", "text": "日落海滩场景"}]
    }],
    n=4,  # 同时生成4个不同结果
    stream=True
)

import asyncio
from openai import AsyncOpenAI

client = AsyncOpenAI(
    api_key="sk-YOUR_API_KEY",
    base_url="https://api.laozhang.ai/v1"
)

async def generate_video(prompt, model="veo-3.1-fast"):
    response = await client.chat.completions.create(
        model=model,
        messages=[{
            "role": "user",
            "content": [{"type": "text", "text": prompt}]
        }],
        stream=True
    )

    async for chunk in response:
        if chunk.choices[0].delta.content:
            print(f"{prompt[:20]}: {chunk.choices[0].delta.content}")

# 并发生成多个视频
prompts = [
    "日落海滩",
    "城市夜景",
    "森林晨光",
    "雨中街道"
]

await asyncio.gather(*[generate_video(p) for p in prompts])

常用风格关键词:

视觉效果:
- 电影感、纪录片风格、MV质感
- 慢镜头、延时摄影、超慢速
- 高清、4K质感、胶片感

色调:
- 暖色调、冷色调、复古色调
- 高对比、低饱和、莫兰迪色系
- 赛博朋克、蒸汽波、油画风格

光影:
- 伦勃朗光、侧光、逆光
- 柔光、硬光、霓虹灯光
- 金色时刻、蓝调时刻、魔法时刻

import sys

response = client.chat.completions.create(
    model="veo-3.1",
    messages=[...],
    stream=True
)

# 实时输出,不缓冲
for chunk in response:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end='', flush=True)
        sys.stdout.flush()

from openai import OpenAI
import httpx

client = OpenAI(
    api_key="sk-YOUR_API_KEY",
    base_url="https://api.laozhang.ai/v1",
    http_client=httpx.Client(
        timeout=httpx.Timeout(
            connect=10.0,  # 连接超时
            read=300.0,    # 读取超时(5分钟)
            write=10.0,    # 写入超时
            pool=10.0      # 连接池超时
        )
    )
)