AlibabaImage model检查中
Wan 2.7 API
wan-2-7-image-editWan 2.7 brings image and video creation and editing tasks together in a family of Hermes variants.
- 文生图
- Image tools
- 文生视频
- 图生视频
- Video edit
- Reference to video
- Up to 9 input images
在 Playground 中运行 Wan 2.7
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
modelWan 2.7Image editwan-2-7-image-edit
高级参数 (2)
input.widthOutput width, range 512-4096, default 1024. Leave empty to skip size. 512–4096
input.heightOutput height, range 512-4096, default 1024. Leave empty to skip size. 512–4096
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": "wan-2-7-image-edit","input": {"width": 1024,"height": 1024}}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。
Wan 2.7 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 Wan 2.7 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。
wan-2-7-text-to-image-pro文生图; 文本
wan-2-7-text-to-image文生图; 文本
wan-2-7-image-edit-proImage tools; 文本, 图像
wan-2-7-image-editImage tools; 文本, 图像
wan-2-7-text-to-video文生视频; 文本, audio; 2–15 s; 720p, 1080p; 16:9, 9:16, 1:1, 4:3, 3:4
wan-2-7-image-to-video图生视频; 文本, 图像, audio; 2–15 s; 720p, 1080p
wan-2-7-video-extendVideo edit; 文本, 视频, audio; 2–15 s; 720p, 1080p
audioUrlwan-2-7-reference-to-videoReference to video; 文本, 图像, 视频, audio; 2–10 s; 720p, 1080p; 16:9, 9:16, 1:1, 4:3, 3:4
wan-2-7-video-editVideo edit; 文本, 图像, 视频; 2–10 s; 720p, 1080p; 16:9, 9:16, 1:1, 4:3, 3:4
imageUrlsaspectRatio
| 版本 | 任务类型 | 输入 | 时长 | 分辨率 | Aspect ratios | Extra fields |
|---|---|---|---|---|---|---|
Text to image pro默认值wan-2-7-text-to-image-pro | 文生图 | 文本 | — | — | — | — |
文生图wan-2-7-text-to-image | 文生图 | 文本 | — | — | — | — |
Image edit prowan-2-7-image-edit-pro | Image tools | 文本, 图像 | — | — | — | — |
Image editwan-2-7-image-edit | Image tools | 文本, 图像 | — | — | — | — |
文生视频wan-2-7-text-to-video | 文生视频 | 文本, audio | 2–15 s | 720p, 1080p | 16:9, 9:16, 1:1, 4:3, 3:4 | — |
图生视频wan-2-7-image-to-video | 图生视频 | 文本, 图像, audio | 2–15 s | 720p, 1080p | — | — |
Video extendwan-2-7-video-extend | Video edit | 文本, 视频, audio | 2–15 s | 720p, 1080p | — | audioUrl |
Reference to videowan-2-7-reference-to-video | Reference to video | 文本, 图像, 视频, audio | 2–10 s | 720p, 1080p | 16:9, 9:16, 1:1, 4:3, 3:4 | — |
Video editwan-2-7-video-edit | Video edit | 文本, 图像, 视频 | 2–10 s | 720p, 1080p | 16:9, 9:16, 1:1, 4:3, 3:4 | imageUrlsaspectRatio |
Wan 2.7 能做什么
Alibaba describes Wan 2.7 text-to-video as supporting audio-video generation and multi-shot narratives. Its image-to-video guide also describes first and last frames and video continuation. These are manufacturer capabilities; check the selected Hermes variant for the fields it actually exposes.
The Hermes catalog separates text-to-image and image editing from video tasks, including text-to-video, image-to-video, reference-to-video, video extension and video editing. Video schemas list 720P and 1080P options. The image editing variants accept up to nine input images; the video variants use different image, video and audio fields, so their requests are not interchangeable.
Check the current status and price for the exact task before running it. Model Studio features and pricing do not automatically apply to this channel.
能力
Up to 15 seconds
Choose a length from 2 to 15 seconds.
durationEvery variant except Text to image pro, 文生图, Image edit pro, Image edit
Start and end frames
Set the first frame and, optionally, the last frame the clip moves to.
firstImageUrllastImageUrl版本: 图生视频
720p or 1080p output
Pick the output resolution: 720p or 1080p.
resolutionEvery variant except Text to image pro, 文生图, Image edit pro, Image edit
5 aspect ratios
16:9, 9:16, 1:1, 4:3 or 3:4.
aspectRatio版本: 文生视频, Reference to video, Video edit
Up to 9 input images
Send up to 9 images in one request as HTTPS URLs or uploaded media references.
imageUrls版本: Image edit pro, Image edit, Reference to video, Video edit
Video input
Accepts a source video as input.
videoUrlvideoUrls版本: Video extend, Reference to video, Video edit
Audio input
Accepts reference audio as input.
audioUrl版本: 文生视频, 图生视频, Video extend, Reference to video
反向提示词
Describe what to keep out of the result.
negativePromptEvery variant except Text to image pro, 文生图, Image edit pro, Image edit
随机种子
Accepts a seed value.
seedEvery variant except Text to image pro, 文生图, Image edit pro, Image edit
使用场景
Animate a still
Start with an image and a motion prompt; the image-to-video schema also lists an optional last frame.
Develop a sequence
Use video extension when you have a starting clip, with the inputs supported by that variant.
Edit visual assets
Choose the separate image editing or video editing task according to the source media.
用代码调用 Wan 2.7
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 Image edit. Set HERMES_API_KEY in your environment.
- 模型 ID
wan-2-7-image-edit- 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": "wan-2-7-image-edit",
"input": {
"imageUrls": [
"https://example.com/input.png"
],
"prompt": "A lighthouse on a rocky coast at sunrise, soft light"
}
}'
# 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 Image edit (wan-2-7-image-edit). 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 |
|---|---|---|---|---|
imageUrls | string[] | 必填 | — | Input images for editing (1-9 images). ≤ 9 items, HTTPS image URL or media:<uuid> |
prompt | string | 必填 | — | Edit instruction describing what to change and what to keep. ≤ 2048 chars |
width | integer | 可选 | 1024 | Output width, range 512-4096, default 1024. Leave empty to skip size. 512–4096 |
height | integer | 可选 | 1024 | Output height, range 512-4096, default 1024. Leave empty to skip size. 512–4096 |
先上传本地文件
用返回的媒体引用替换示例 URL。
curl -X POST https://api.hermes-ai.net/api/v1/media \
-H "Authorization: Bearer $HERMES_API_KEY" \
-H "Content-Type: image/png" \
--data-binary @input.png
# → { "reference": "media:<uuid>", ... } Use the reference in an image, video or audio field.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。 |
Wan 2.7 API 常见问题
Answers built from the model's schema and the Hermes AI API contract.
Can I use the same request for image and video generation?
No. Pick the task-specific model ID and follow its schema: image generation takes dimensions, while video variants use options such as duration and resolution.
Does every variant accept audio or video references?
No. Reference fields differ by task. Consult the selected model's parameters before submitting media.
What can the Wan 2.7 API do?
Alibaba 的 Wan 2.7 支持文生图, 图像工具, 文生视频, 图生视频, 视频编辑 和 参考生视频。目录列有9 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 Wan 2.7 support?
Across its variants, Wan 2.7 supports durations from 2 to 15 seconds, 720p 和 1080p resolution 和 aspect ratios 16:9, 9:16, 1:1, 4:3 和 3:4. Each variant accepts its own subset; the variants table on this page lists them.
What input does Wan 2.7 accept?
A text prompt of up to 5,000 characters, plus 图像, 视频 或 audio input (up to 9 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 Wan 2.7 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 Wan 2.7 variant should I choose?
For 文生图, Text to image pro 和 文生图 take the same input fields and differ in tier and price; for image tools, Image edit pro 和 Image edit take the same input fields and differ in tier and price; for 文生视频, use 文生视频; for 图生视频, use 图生视频; for video edit, Video extend 和 Video edit differ in fields: Video extend adds audioUrl; Video edit adds imageUrls, aspectRatio; for reference to video, use Reference to video. Pick the task first, then compare the tiers in the variants table.
How do I call the Wan 2.7 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 Wan 2.7 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.