多模态 AI 指南——通过一个兼容 OpenAI 的 API 处理文本、图像、视频和音频

# Text-to-image: same OpenAI SDK, different model slug
img = client.images.generate(
    model="nano-banana-pro",          # Google's flagship — best text rendering
    prompt="a marketing hero for a fintech app, isometric, soft blue palette",
    size="1024x1024",
)
print(img.data[0].url)  # permanent: https://files.kunavo.com/...

# Image-to-video: upload a hero image, animate into an 8-second product clip
# (every Veo clip is 8 seconds; the Veo models ignore "duration").
# The OpenAI SDK has no method for the video route, so post to it with the
# same client.
video = client.post(
    "/video/generations",
    body={
        "model": "veo-3",
        "prompt": "camera slowly orbits, soft cinematic light, product hero shot",
        "image_url": hero_image_url,
        "aspect_ratio": "9:16",   # vertical for Reels / TikTok / IG short
        "resolution": "1080p",
    },
    cast_to=object,
    options={"timeout": 600.0},   # a clip takes minutes
)
print(video["data"][0]["url"])

# Pipeline: GPT-Image generates a marketing hero, Veo 3 animates it,
# Suno scores the BGM. One API, one bill.
# Here client is AsyncOpenAI(api_key=..., base_url="https://api.kunavo.com/v1").
async def make_marketing_clip(product: dict) -> dict:
    # 1. Hero image
    img = await client.images.generate(
        model="gpt-image-2",
        prompt=f"hero shot of {product['name']}, premium aesthetic",
        size="1024x1792",
    )

    # 2. Animate to 8s vertical (the length of every Veo clip). The SDK has
    #    no method for the video and music routes, so post to them directly.
    video = await client.post(
        "/video/generations",
        body={
            "model": "veo-3",
            "prompt": f"camera orbits {product['name']}, cinematic lighting",
            "image_url": img.data[0].url,
            "aspect_ratio": "9:16",
        },
        cast_to=object,
        options={"timeout": 600.0},
    )

    # 3. BGM
    bgm = await client.post(
        "/audio/music",
        body={
            "model": "suno-v5",
            "prompt": "upbeat synth, 30 seconds, brand-friendly",
        },
        cast_to=object,
        options={"timeout": 600.0},
    )

    return {"video": video["data"][0]["url"], "bgm": bgm["data"][0]["url"]}