Vidu Q4 Preview 参考生视频

vidu/q4-preview/reference-to-video

根据提示词生成 3~16 秒视频,可选最多 15 张参考图片和 3 段参考音频,支持宽高比选择、音频生成及 540p~4k 分辨率。

示例

Vidu Q4 Preview 参考生视频 示例 1

参数

名称类型默认约束说明
prompt *提示词textarea—≤ 5000 chars用于生成的正向提示词。
images图片image_upload—image/* · 0–15 items参考图片 URL 数组(最多 15 张)。
audios音频audio_upload_group—audio/* · 0–3 items可选的参考音频文件,用于生成。最多支持 3 段参考音频。
aspect_ratio宽高比select16:916:9 | 9:16 | 1:1 | 3:4 | 4:3生成内容的宽高比。
resolution分辨率select720p540p | 720p | 1080p | 2k | 4k生成内容的分辨率。
duration时长slider53 ~ 16 · step 1生成内容的时长(秒)。
generate_audio生成音频booleantrue—是否生成音频。
seed随机种子number—step 1用于生成的随机种子。设为 0 或留空时,将使用随机种子。

输出字段

字段类型说明
videosarray<string>

API

通过统一 REST API 调用本模型;在 API Keys 页获取密钥。

cURL
# 1) Submit — returns { "task_uuid": "..." }
curl -X POST "https://www.namifusion.com/api/v1/marketplace/run/vidu/q4-preview/reference-to-video" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "input": {
    "prompt": "Create a polished cinematic product video featuring the same matte black wireless headphones from the reference images on a clean studio set. Start with a slow rotating close-up that highlights the soft ear cushions and brushed metal details, then transition to a lifestyle shot of a young adult placing the headphones on while warm ambient light glows in the background. Keep the subject design fully consistent with the references, use smooth camera motion, realistic reflections, shallow depth of field, premium commercial styling, and subtle motion graphics for a modern brand ad.",
    "images": [
      "https://d1s3annbwribom.cloudfront.net/marketplace/examples/2026/10/09/794a150611fc.jpeg",
      "https://d1s3annbwribom.cloudfront.net/marketplace/examples/2026/10/09/1612d26e4530.jpeg",
      "https://d1s3annbwribom.cloudfront.net/marketplace/examples/2026/10/09/87a14c8b9623.jpeg"
    ],
    "audios": [],
    "aspect_ratio": "16:9",
    "resolution": "720p",
    "duration": 5,
    "generate_audio": true,
    "seed": 123456
  }
}'

# 2) Poll until status is "completed", then read the output URLs
curl "https://www.namifusion.com/api/v1/marketplace/run/tasks/TASK_UUID" \
  -H "Authorization: Bearer YOUR_API_KEY"
Python
import time, requests

API_KEY = "YOUR_API_KEY"
HEADERS = {"Authorization": f"Bearer {API_KEY}"}

# 1) Submit
resp = requests.post(
    "https://www.namifusion.com/api/v1/marketplace/run/vidu/q4-preview/reference-to-video",
    headers=HEADERS,
    json={
        "input": {
            "prompt": "Create a polished cinematic product video featuring the same matte black wireless headphones from the reference images on a clean studio set. Start with a slow rotating close-up that highlights the soft ear cushions and brushed metal details, then transition to a lifestyle shot of a young adult placing the headphones on while warm ambient light glows in the background. Keep the subject design fully consistent with the references, use smooth camera motion, realistic reflections, shallow depth of field, premium commercial styling, and subtle motion graphics for a modern brand ad.",
            "images": [
                "https://d1s3annbwribom.cloudfront.net/marketplace/examples/2026/10/09/794a150611fc.jpeg",
                "https://d1s3annbwribom.cloudfront.net/marketplace/examples/2026/10/09/1612d26e4530.jpeg",
                "https://d1s3annbwribom.cloudfront.net/marketplace/examples/2026/10/09/87a14c8b9623.jpeg"
            ],
            "audios": [],
            "aspect_ratio": "16:9",
            "resolution": "720p",
            "duration": 5,
            "generate_audio": True,
            "seed": 123456
        }
    },
)
resp.raise_for_status()  # 401/402/429/5xx stop here instead of polling a bad task
task = resp.json()

# 2) Poll until a terminal state (completed / failed / cancelled).
#    This model is allowed up to 1800s server-side.
deadline = time.time() + 1860
while task.get("status") not in ("completed", "failed", "cancelled"):
    if time.time() > deadline:
        raise TimeoutError(f"still {task.get('status')} — keep the task_uuid and poll later")
    time.sleep(3)
    poll = requests.get(f"https://www.namifusion.com/api/v1/marketplace/run/tasks/{task['task_uuid']}", headers=HEADERS)
    poll.raise_for_status()
    task = poll.json()

print(task["status"], task.get("output"))
JavaScript
const API_KEY = "YOUR_API_KEY";
const HEADERS = { Authorization: `Bearer ${API_KEY}` };

// 1) Submit
const resp = await fetch("https://www.namifusion.com/api/v1/marketplace/run/vidu/q4-preview/reference-to-video", {
  method: "POST",
  headers: { ...HEADERS, "Content-Type": "application/json" },
  body: JSON.stringify({
    "input": {
      "prompt": "Create a polished cinematic product video featuring the same matte black wireless headphones from the reference images on a clean studio set. Start with a slow rotating close-up that highlights the soft ear cushions and brushed metal details, then transition to a lifestyle shot of a young adult placing the headphones on while warm ambient light glows in the background. Keep the subject design fully consistent with the references, use smooth camera motion, realistic reflections, shallow depth of field, premium commercial styling, and subtle motion graphics for a modern brand ad.",
      "images": [
        "https://d1s3annbwribom.cloudfront.net/marketplace/examples/2026/10/09/794a150611fc.jpeg",
        "https://d1s3annbwribom.cloudfront.net/marketplace/examples/2026/10/09/1612d26e4530.jpeg",
        "https://d1s3annbwribom.cloudfront.net/marketplace/examples/2026/10/09/87a14c8b9623.jpeg"
      ],
      "audios": [],
      "aspect_ratio": "16:9",
      "resolution": "720p",
      "duration": 5,
      "generate_audio": true,
      "seed": 123456
    }
  }),
});
if (!resp.ok) throw new Error(`submit failed: ${resp.status} ${await resp.text()}`);
let task = await resp.json();

// 2) Poll until a terminal state (completed / failed / cancelled).
//    This model is allowed up to 1800s server-side.
const deadline = Date.now() + 1860 * 1000;
while (!["completed", "failed", "cancelled"].includes(task.status)) {
  if (Date.now() > deadline) throw new Error(`still ${task.status} — keep the task_uuid and poll later`);
  await new Promise((r) => setTimeout(r, 3000));
  const poll = await fetch(`https://www.namifusion.com/api/v1/marketplace/run/tasks/${task.task_uuid}`, { headers: HEADERS });
  if (!poll.ok) throw new Error(`poll failed: ${poll.status}`);
  task = await poll.json();
}

console.log(task.status, task.output);

文档

Vidu Q4 Preview 参考生视频

vidu/q4-preview/reference-to-video

根据提示词生成 3~16 秒视频,可选最多 15 张参考图片和 3 段参考音频,支持宽高比选择、音频生成及 540p~4k 分辨率。

参数

参数类型必填默认值范围/说明
promptstring是—max 5000 chars; 用于生成的正向提示词。
imagesarray否—0–15 URLs; 参考图片 URL 数组(最多 15 张)。
audiosarray否—0–3 URLs; 可选的参考音频文件,用于生成。最多支持 3 段参考音频。
aspect_ratiostring否"16:9"16:9, 9:16, 1:1, 3:4, 4:3; 生成内容的宽高比。
resolutionstring否"720p"540p, 720p, 1080p, 2k, 4k; 生成内容的分辨率。
durationinteger否53–16; step 1; 生成内容的时长(秒)。
generate_audioboolean否true是否生成音频。
seedinteger否—用于生成的随机种子。设为 0 或留空时,将使用随机种子。

仅 prompt 必填。images 支持 0~15 张参考图片 URL,audios 支持 0~3 段参考音频 URL;两者均可省略或传空数组。seed=0 或不传表示随机种子;aspect_ratio 默认为 16:9。本接口不提供 enable_prompt_expansion 参数。

价格

ResolutionUSD / secondCredits / secondUSD / 5 seconds
540p$0.0454.5$0.225
720p$0.0959.5$0.475
1080p$0.1212$0.6
2k$0.1919$0.95
4k$0.3939$1.95

总价=分辨率单价 × duration。duration 支持 3~16 的整数秒,默认 720p、5 秒、开启音频,默认总价为 $0.475,即 47.5 积分。只有分辨率和时长影响价格,音频生成、种子及本接口支持的参考素材或提示词扩展不额外收费。1 美元=100 积分。标价与 WaveSpeed 一致,账户折扣另行计算。

API

curl -X POST https://www.namifusion.com/api/v1/marketplace/run/vidu/q4-preview/reference-to-video \
  -H "Authorization: Bearer $API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "input": {
    "prompt": "Create a polished cinematic product video featuring the same matte black wireless headphones from the reference images on a clean studio set. Start with a slow rotating close-up that highlights the soft ear cushions and brushed metal details, then transition to a lifestyle shot of a young adult placing the headphones on while warm ambient light glows in the background. Keep the subject design fully consistent with the references, use smooth camera motion, realistic reflections, shallow depth of field, premium commercial styling, and subtle motion graphics for a modern brand ad.",
    "images": [
      "https://d1s3annbwribom.cloudfront.net/marketplace/examples/2026/10/09/794a150611fc.jpeg",
      "https://d1s3annbwribom.cloudfront.net/marketplace/examples/2026/10/09/1612d26e4530.jpeg",
      "https://d1s3annbwribom.cloudfront.net/marketplace/examples/2026/10/09/87a14c8b9623.jpeg"
    ],
    "aspect_ratio": "16:9",
    "resolution": "720p",
    "duration": 5,
    "generate_audio": true,
    "seed": 123456
  }
}'
curl 'https://www.namifusion.com/api/v1/marketplace/run/tasks/TASK_UUID' \
  -H "Authorization: Bearer $API_KEY"

提交响应返回 task_uuid;轮询至 completed 或 failed。成功时 output.videos 是视频 URL 数组。

WaveSpeed

相关模型

xAI Grok Imagine Video v1.5 参考图转视频
参考图生视频X Ai

xAI Grok Imagine Video v1.5 参考图转视频

使用提示词和 1-7 张参考图片生成 1-15 秒视频,支持 480p 和 720p。

起 $0.850 / 每次
MiniMax H3 参考图生视频
参考图生视频Minimax

MiniMax H3 参考图生视频

MiniMax H3 Reference to Video 可根据自然语言提示词和多模态参考内容生成连贯的 2K 视频,支持图片、视频和音频输入,可引导主体一致性、运动、时序、视觉风格和场景连贯性。提供开箱即用的 REST 推理 API,性能出色,无冷启动,价格实惠。

起 $0.650 / 每次
Gemini Omni Flash 参考图生视频 API
参考图生视频Google

Gemini Omni Flash 参考图生视频 API

Gemini Omni Flash 参考图生视频可根据一张或多张参考图片和文本提示词生成带同步音频的短视频,保持视觉主体一致性,并依据提供的参考内容进行引导式多模态视频生成。即开即用的 REST 推理 API,性能出色,无冷启动,价格实惠。

起 $1.28 / 每次
Seedance 2.0 Mini 参考生视频
参考图生视频Doubao

Seedance 2.0 Mini 参考生视频

Seedance 2.0 Mini 参考图生视频 (Reference-to-Video) 是字节跳动推出的一款高速度、低成本的视频生成模型,专注于创作具有电影质感的多镜头视频。该模型能够完美融合参考图与文本提示词,生成极具叙事感的连续视频片段。它不仅支持灵动的 AI 镜头控制,更攻克了跨场景角色一致性的难题。模型支持从 480P 到 4K 的多分辨率输出,时长跨越 4-15 秒,并适配灵活的宽高比。提供开箱即用的 REST 推理 API,性能卓越,告别冷启动,是极具性价比的专业视频创作利器

起 $0.378 / 每次
Seedance 2.5 参考图/视频转视频
参考图生视频Doubao

Seedance 2.5 参考图/视频转视频

Seedance 2.5 的“参考生视频”功能是视觉统一的终极方案。它能精准提取参考素材的艺术风格、光影基调或构图意向,并将其完美融入新生成的视频中,确保您的系列创作拥有高度一致的视觉语言。

起 $0.691 / 每次
Seedance 2.0 Fast 视频编辑
参考图生视频Doubao

Seedance 2.0 Fast 视频编辑

Seedance 2.0 Fast(reference-to-video)可根据自然语言提示词对输入视频进行编辑,速度更快、成本更低。基于字节跳动 Seed 统一多模态架构构建,在按指令重写光照、风格、天气、环境或特定元素的同时,保留主体身份、构图和运动。提供开箱即用的 REST API,性能出色,无冷启动,价格实惠。

起 $0.713 / 每次
Wan 2.6 Flash 参考生视频
参考图生视频Alibaba

Wan 2.6 Flash 参考生视频

根据参考图片或视频生成 2~10 秒视频,支持 720P、1080P 和可选音频。

起 $0.375 / 每次