ViduVideo model检查中
Vidu Q3 API
vidu-text-to-video-q3-proVidu Q3 video generation across reference, text, image and first-to-last-frame variants.
- Reference to video
- 图生视频
- 文生视频
- Up to 7 input images
- Up to 16 seconds
- 720p or 1080p output
- Start and end frames
在 Playground 中运行 Vidu Q3
The form is the request body: every field shows its key. Sign in to run it; a run is billed like an API task.
参数
modelVidu Q3Text to video providu-text-to-video-q3-pro
任务接收时预留额度,仅成功后扣费。失败任务释放预留额度;结果未确认时会保留额度,直到核实。
请求预览
{"model": "vidu-text-to-video-q3-pro","input": {"style": "general","aspectRatio": "16:9","resolution": "720p","duration": "5","audio": true}}网页 Playground 使用你的登录会话发送此请求体。在代码中请使用 API Key 发送相同内容。
结果
运行请求后,结果会显示在这里,并附上状态和费用。
Vidu Q3 价格
各可用版本和规格的价格以美元显示,计费单位随费率注明;只有找到可匹配的官方标价时才显示参考价格。
- Charged only on success仅对成功任务扣费。失败任务释放预留额度;结果尚未确认的任务会保留额度,直到结果核实。
- Safe retries使用相同幂等密钥重试不会重复扣费。
- Price changes发送 expectedPriceMicros:若展示后价格发生变化,任务会以 PRICE_CHANGED 被拒绝。
对比 Vidu Q3 各版本
每个变体都有独立的模型 ID 和输入参数。请先选择任务和版本;变体存在差异时会显示额外字段。
vidu-reference-to-video-q3-mixReference to video; 文本, 图像, audio; 1–16 s; 720p, 1080p; 16:9, 9:16, 4:3, 3:4, 1:1
audioUrlsvidu-reference-to-video-q3Reference to video; 文本, 图像; 3–16 s; 540p, 720p, 1080p; 16:9, 9:16, 4:3, 3:4, 1:1
vidu-start-end-to-video-q3-pro图生视频; 文本, 图像; 1–16 s; 540p, 720p, 1080p
firstImageUrllastImageUrlmovementAmplitudevidu-start-end-to-video-q3-turbo图生视频; 文本, 图像; 1–16 s; 540p, 720p, 1080p
firstImageUrllastImageUrlmovementAmplitudevidu-image-to-video-q3-turbo图生视频; 文本, 图像; 1–16 s; 540p, 720p, 1080p
imageUrlvidu-text-to-video-q3-turbo文生视频; 文本; 1–16 s; 540p, 720p, 1080p; 4:3, 3:4, 16:9, 9:16, 1:1
vidu-image-to-video-q3-pro图生视频; 文本, 图像; 1–16 s; 360p, 540p, 720p, 1080p, 2K
imageUrlvidu-text-to-video-q3-pro文生视频; 文本; 1–16 s; 360p, 540p, 720p, 1080p; 4:3, 3:4, 16:9, 9:16, 1:1
vidu-reference-to-video-q3-dramaReference to video; 文本, 图像; 2–15 s; 1080p; 16:9, 9:16, 4:3, 3:4, 1:1
vidu-reference-to-video-q3-adReference to video; 文本, 图像, audio; 3–16 s; 720p, 1080p; 16:9, 9:16, 4:3, 3:4, 1:1
audioUrls
| 版本 | 任务类型 | 输入 | 时长 | 分辨率 | Aspect ratios | Extra fields |
|---|---|---|---|---|---|---|
Reference to video mixvidu-reference-to-video-q3-mix | Reference to video | 文本, 图像, audio | 1–16 s | 720p, 1080p | 16:9, 9:16, 4:3, 3:4, 1:1 | audioUrls |
Reference to videovidu-reference-to-video-q3 | Reference to video | 文本, 图像 | 3–16 s | 540p, 720p, 1080p | 16:9, 9:16, 4:3, 3:4, 1:1 | — |
Start end to video providu-start-end-to-video-q3-pro | 图生视频 | 文本, 图像 | 1–16 s | 540p, 720p, 1080p | — | firstImageUrllastImageUrlmovementAmplitude |
Start end to video turbovidu-start-end-to-video-q3-turbo | 图生视频 | 文本, 图像 | 1–16 s | 540p, 720p, 1080p | — | firstImageUrllastImageUrlmovementAmplitude |
Image to video turbovidu-image-to-video-q3-turbo | 图生视频 | 文本, 图像 | 1–16 s | 540p, 720p, 1080p | — | imageUrl |
Text to video turbo默认值vidu-text-to-video-q3-turbo | 文生视频 | 文本 | 1–16 s | 540p, 720p, 1080p | 4:3, 3:4, 16:9, 9:16, 1:1 | — |
Image to video providu-image-to-video-q3-pro | 图生视频 | 文本, 图像 | 1–16 s | 360p, 540p, 720p, 1080p, 2K | — | imageUrl |
Text to video providu-text-to-video-q3-pro | 文生视频 | 文本 | 1–16 s | 360p, 540p, 720p, 1080p | 4:3, 3:4, 16:9, 9:16, 1:1 | — |
Reference to video dramavidu-reference-to-video-q3-drama | Reference to video | 文本, 图像 | 2–15 s | 1080p | 16:9, 9:16, 4:3, 3:4, 1:1 | — |
Reference to video advidu-reference-to-video-q3-ad | Reference to video | 文本, 图像, audio | 3–16 s | 720p, 1080p | 16:9, 9:16, 4:3, 3:4, 1:1 | audioUrls |
Vidu Q3 能做什么
Vidu describes Q3 as a video family focused on subject consistency and audio-video output, with Turbo and other variants for different workflows. The manufacturer's product lineup is broader than any one Hermes endpoint.
The Hermes catalog lists text-to-video and image-to-video Pro and Turbo variants, first-to-last-frame variants, and reference-to-video Q3, Mix, Ad and Drama options. The reference schemas list up to seven images; Mix and Ad also list up to three audio references. Each variant has its own duration, resolution and other fields.
Check the selected variant's current status and price before submitting a task.
能力
Up to 16 seconds
Choose a length from 1 to 16 seconds.
durationEvery variant
Start and end frames
Set the first frame and, optionally, the last frame the clip moves to.
firstImageUrllastImageUrl版本: Start end to video pro, Start end to video turbo
720p or 1080p output
Pick the output resolution: 720p or 1080p.
resolutionEvery variant except Reference to video drama
5 aspect ratios
16:9, 9:16, 4:3, 3:4 or 1:1.
aspectRatioEvery variant except Start end to video pro, Start end to video turbo, Image to video turbo, Image to video pro
Up to 7 input images
Send up to 7 images in one request as HTTPS URLs or uploaded media references.
imageUrls版本: Reference to video mix, Reference to video, Reference to video drama, Reference to video ad
Audio input
Accepts reference audio as input.
audioUrls版本: Reference to video mix, Reference to video ad
使用场景
Create a clip from a description
Select a text-to-video variant and describe the scene.
Animate or transition between frames
Choose image-to-video or a first-to-last-frame variant for the media you have.
Work from character or visual references
Use a reference-to-video variant and its listed image and audio inputs.
用代码调用 Vidu Q3
Every image, video and music model uses the same asynchronous job API: submit a task, then poll for the result.
- 1
创建 API Key
In the dashboard, with the jobs:create and jobs:read scopes. API 密钥 - 2
提交任务
POST /api/v1/jobswith the model ID and an input object. The response is 202 with a task ID. - 3
Poll for the result
GET /api/v1/jobs/{id}until the status is succeeded, then download the output URLs.
最小请求
Required fields only, generated from the schema of Text to video pro. Set HERMES_API_KEY in your environment.
- 模型 ID
vidu-text-to-video-q3-pro- 端点
https://api.hermes-ai.net/api/v1/jobs
# 1. Submit the task (asynchronous; returns 202 with a task id)
curl -X POST https://api.hermes-ai.net/api/v1/jobs \
-H "Authorization: Bearer $HERMES_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{
"model": "vidu-text-to-video-q3-pro",
"input": {
"prompt": "A lighthouse on a rocky coast at sunrise, soft light",
"style": "general",
"aspectRatio": "16:9",
"resolution": "720p",
"duration": "5",
"audio": true
}
}'
# 2. Poll until status is succeeded, failed or reconciliation_required
curl https://api.hermes-ai.net/api/v1/jobs/TASK_ID \
-H "Authorization: Bearer $HERMES_API_KEY"输入参数
Fields of Text to video pro (vidu-text-to-video-q3-pro). 未知字段会被拒绝并返回 INVALID_MODEL_INPUT。
| 字段 | 类型 | 必填 | 默认值 | 可选值与约束 |
|---|---|---|---|---|
prompt | string | 必填 | — | ≤ 4000 chars |
style | string | 必填 | "general" | 可选值: |
aspectRatio | string | 必填 | "16:9" | 可选值: |
resolution | string | 必填 | "720p" | 可选值: |
duration | string | 必填 | "5" | 可选值: |
audio | boolean | 必填 | true | Whether to use the audio and video direct output capability |
Headers, response, task statuses and errors
| 请求头 | 值 | 说明 |
|---|---|---|
Authorization | Bearer <API key> | 也可以通过 x-api-key 发送密钥。 |
Content-Type | application/json | |
Idempotency-Key | <unique string ≤128> | 必填。仅在重试完全相同的请求时复用。 |
| 字段 | 类型 | 说明 |
|---|---|---|
id | string | Hermes AI 任务 ID,用于轮询。 |
model | string | 模型 slug。 |
status | string | 参见任务状态。 |
errorCode | string | null | 任务失败或需要核对时设置。 |
priceMicros | integer | 接收时锁定的报价,美元微单位。 |
currency | "USD" | |
createdAt / updatedAt | string | ISO 8601 时间戳。 |
assets[] | array | { id, type, url?, text? }。url 为同源 /api/v1/results/<uuid> 链接。 |
replayed | boolean | 仅提交时返回。幂等重试命中时为 true。 |
| 状态 | 终态 | 含义 |
|---|---|---|
queued | 否 | 已接收,等待执行。 |
submitting | 否 | 正在提交给模型提供方。 |
running | 否 | 模型生成中。 |
succeeded | 是 | 已完成,结果位于 assets。 |
failed | 是 | 未产生结果,预留额度已释放。 |
reconciliation_required | 是 | 结果正在核实。请保留任务 ID,不要自动重新提交。 |
| HTTP | 代码 | 含义与处理方式 |
|---|---|---|
401 | AUTH_REQUIRED | 缺少或无效的 API Key 或会话。 |
403 | INSUFFICIENT_SCOPE | API Key 缺少此端点所需的权限。 |
403 | PERMISSION_DENIED | 此凭据无权执行该操作。 |
429 | API_KEY_RATE_LIMITED | 已达到 API Key 的频率限制,请遵循 Retry-After。 |
429 | API_KEY_USAGE_EXCEEDED | API Key 已达到使用上限,请创建新密钥。 |
400 | INVALID_REQUEST | 请求体不是 JSON 对象,或缺少必需值。 |
400 | INVALID_IDEMPOTENCY_KEY | Idempotency-Key 必须是 1–128 个可打印 ASCII 字符。 |
400 | INVALID_MODEL_INPUT | input 与模型 schema 不匹配(未知字段、缺少必填字段或值无效)。 |
400 / 413 | INPUT_TOO_LARGE | 请求体超过 256 KB。请先上传媒体并发送媒体引用。 |
404 | REQUEST_NOT_FOUND | No chat request with this ID belongs to your account. |
404 | MODEL_NOT_FOUND | 没有此 slug 对应的模型。 |
404 | JOB_NOT_FOUND | 你的账户中没有此 ID 的任务。 |
409 | IDEMPOTENCY_CONFLICT | 此 Idempotency-Key 已用于不同的输入。新请求请使用新密钥。 |
409 | PRICE_CHANGED | 价格与 expectedPriceMicros 不一致。请重新获取价格并确认。 |
409 | MODEL_PRICE_UNAVAILABLE | 此模型尚未配置价格,暂不可运行。 |
409 | PAYMENT_REVIEW_REQUIRED | 退款后余额不足。请联系支持或补足余额后再提交任务。 |
409 | INSUFFICIENT_CREDITS | 可用额度不足以支付此任务。 |
429 | RATE_LIMITED | 每分钟提交次数过多,请稍后重试。 |
429 | EXPORT_RATE_LIMITED | 本分钟内导出 CSV 次数过多,请按 Retry-After 等待后重试。 |
429 | CONCURRENCY_LIMITED | 未完成任务过多,请等待任务完成。 |
503 | EXECUTION_UNAVAILABLE | 此模型当前未配置执行能力。 |
429 | UPSTREAM_RATE_LIMITED | The model provider is rate limiting chat requests. Retry with backoff; nothing was charged. |
502 | UPSTREAM_ERROR | The model provider failed the chat request. Nothing was charged; retry later. |
503 | PLATFORM_BUDGET_EXCEEDED | 此模型暂时不可用,请稍后重试。 |
503 | EXECUTION_TEMPORARILY_UNAVAILABLE | 执行暂时不可用,请使用相同的 Idempotency-Key 重试。 |
503 | AUTH_UNAVAILABLE | 身份验证暂时不可用,请稍后重试。 |
503 | API_UNAVAILABLE | API 暂时不可用,请稍后重试。 |
Vidu Q3 API 常见问题
Answers built from the model's schema and the Hermes AI API contract.
Which variant accepts reference audio?
The Mix and Ad reference-to-video schemas list audioUrls. Other variants have different input fields, so check the selected schema.
What can the Vidu Q3 API do?
Vidu 的 Vidu Q3 支持参考生视频, 图生视频 和 文生视频。目录列有10 variants, each,每个变体都有自己的模型 ID 和输入参数。提交请求前请先确认当前可用状态。
Which durations, resolutions and aspect ratios does Vidu Q3 support?
Across its variants, Vidu Q3 supports durations from 1 to 16 seconds, 720p, 1080p, 540p, 360p 和 2K resolution 和 aspect ratios 16:9, 9:16, 4:3, 3:4 和 1:1. Each variant accepts its own subset; the variants table on this page lists them.
What input does Vidu Q3 accept?
A text prompt of up to 5,000 characters, plus 图像 或 audio input (up to 7 images per request). Media fields take a public HTTPS URL or a media:<uuid> reference returned by POST /api/v1/media, so local files can be uploaded first. 未知字段会被拒绝并返回 INVALID_MODEL_INPUT。
How is Vidu Q3 priced and billed?
You pay per successful task from prepaid credits, with no subscription. The price depends on the variant and the specification you choose, such as resolution or duration; see the pricing table on this page or the pricing page. Credits are reserved when a task is accepted and charged only when it succeeds; a failed task returns the reservation to your balance.
Which Vidu Q3 variant should I choose?
For reference to video, Reference to video mix, Reference to video, Reference to video drama 和 Reference to video ad differ in fields: Reference to video mix adds audioUrls; Reference to video ad adds audioUrls; for 图生视频, Start end to video pro, Start end to video turbo, Image to video turbo 和 Image to video pro differ in fields: Start end to video pro adds firstImageUrl, lastImageUrl, movementAmplitude; Start end to video turbo adds firstImageUrl, lastImageUrl, movementAmplitude; Image to video turbo adds imageUrl; Image to video pro adds imageUrl; for 文生视频, Text to video turbo 和 Text to video pro take the same input fields and differ in tier and price. Pick the task first, then compare the tiers in the variants table.
How do I call the Vidu Q3 API from code?
Send POST https://api.hermes-ai.net/api/v1/jobs with the variant's model ID and an input object, then poll GET /api/v1/jobs/{id} until the status is succeeded or failed. The API section has cURL, JavaScript and Python examples generated from the schema.
Can I try Vidu Q3 without writing code?
Yes. Sign in and use the playground on this page: it sends the same request as the API with your session and charges the same price. Code needs an API key from the dashboard.
What happens when a task fails or I hit a rate limit?
A failed task is not charged and its reserved credits are returned. Too many submissions per minute return 429 RATE_LIMITED, and too many unfinished tasks return 429 CONCURRENCY_LIMITED; retry later or wait for a task to finish.