ByteDanceImage model检查中
Seedream 5.0 API
dola-seedream-5-0-flash-image-to-imageSeedream 5.0 Pro and Flash image generation and editing.
- 文生图
- 图生图
- Up to 10 input images
- 1K, 1.5K or 2K output
- 格式选项
在 Playground 中运行 Seedream 5.0
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
modelSeedream 5.0Flash image to imagedola-seedream-5-0-flash-image-to-image
高级参数 (2)
input.width240–8192
input.height240–8192
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": "dola-seedream-5-0-flash-image-to-image","input": {"width": 1024,"height": 1024,"outputFormat": "jpeg"}}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。
Seedream 5.0 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 Seedream 5.0 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。
dola-seedream-5-0-flash-text-to-image文生图; 文本; 1K, 1.5K, 2K
dola-seedream-5-0-flash-image-to-image图生图; 文本, 图像; 1K, 1.5K, 2K
seedream-5-0-pro-text-to-image文生图; 文本; 1K, 1.5K, 2K
seedream-5-0-pro-image-to-image图生图; 文本, 图像; 1K, 1.5K, 2K
dola-seedream-5-0-pro-text-to-image文生图; 文本; 1K, 1.5K, 2K
dola-seedream-5-0-pro-image-to-image图生图; 文本, 图像; 1K, 1.5K, 2K
| 版本 | 任务类型 | 输入 | 分辨率 |
|---|---|---|---|
Flash text to image默认值dola-seedream-5-0-flash-text-to-image | 文生图 | 文本 | 1K, 1.5K, 2K |
Flash image to imagedola-seedream-5-0-flash-image-to-image | 图生图 | 文本, 图像 | 1K, 1.5K, 2K |
Pro text to imageseedream-5-0-pro-text-to-image | 文生图 | 文本 | 1K, 1.5K, 2K |
Pro image to imageseedream-5-0-pro-image-to-image | 图生图 | 文本, 图像 | 1K, 1.5K, 2K |
Pro text to image (Dola)dola-seedream-5-0-pro-text-to-image | 文生图 | 文本 | 1K, 1.5K, 2K |
Pro image to image (Dola)dola-seedream-5-0-pro-image-to-image | 图生图 | 文本, 图像 | 1K, 1.5K, 2K |
Seedream 5.0 能做什么
ByteDance describes Seedream 5.0 Pro as an image model focused on information visualization, text rendering, layout and visual coherence. Review text, factual details and fine structure before publishing generated content.
The Hermes catalog lists Pro and Flash text-to-image and image-to-image variants. Edit variants list up to 10 reference images and the schemas list 1K, 1.5K and 2K resolution options. The cited announcement concerns Pro; do not assume all of its product claims apply identically to Flash. Check status and price for the exact task.
能力
格式选项
请求参数列出了这些格式;具体可用性和结果交付取决于所选变体。
JPEG · PNG
outputFormatEvery variant
1K, 1.5K or 2K output
Pick the output resolution: 1K, 1.5K or 2K.
resolutionEvery variant
Up to 10 input images
Send up to 10 images in one request as HTTPS URLs or uploaded media references.
imageUrls版本: Flash image to image, Pro image to image, Pro image to image (Dola)
使用场景
Draft an information graphic
Describe content and layout and verify every label.
Edit with references
Supply images and describe what to change and preserve.
Compare variants
Evaluate Pro and Flash for quality and turnaround on your own prompts.
用代码调用 Seedream 5.0
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 Flash image to image. Set HERMES_API_KEY in your environment.
- 模型 ID
dola-seedream-5-0-flash-image-to-image- 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": "dola-seedream-5-0-flash-image-to-image",
"input": {
"prompt": "A lighthouse on a rocky coast at sunrise, soft light",
"imageUrls": [
"https://example.com/input.png"
]
}
}'
# 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 Flash image to image (dola-seedream-5-0-flash-image-to-image). 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 | — | Edit or fusion instruction 5–5000 chars |
width | integer | 可选 | 1024 | 240–8192 |
height | integer | 可选 | 1024 | 240–8192 |
imageUrls | string[] | 必填 | — | Reference images, 1 to 10 ≤ 10 items, HTTPS image URL or media:<uuid> |
resolution | string | 可选 | — | Takes priority over width and height. When resolution is set, pixel width and height are ignored. Leave empty to use custom width and height. 可选值: |
outputFormat | string | 可选 | "jpeg" | Output image format, png or jpeg 可选值: |
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。 |
Seedream 5.0 API 常见问题
Answers built from the model's schema and the Hermes AI API contract.
How many images can I provide for editing?
The Hermes image-to-image schemas list up to 10 imageUrls. Consult the selected variant for its full request contract.
What can the Seedream 5.0 API do?
ByteDance 的 Seedream 5.0 支持文生图 和 图生图。目录列有6 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 Seedream 5.0 support?
Across its variants, Seedream 5.0 supports 1K, 1.5K 和 2K resolution. Each variant accepts its own subset; the variants table on this page lists them.
What input does Seedream 5.0 accept?
A text prompt of up to 5,000 characters, plus 图像 input (up to 10 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 Seedream 5.0 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 Seedream 5.0 variant should I choose?
For 文生图, Flash text to image, Pro text to image 和 Pro text to image (Dola) take the same input fields and differ in tier and price; for 图生图, Flash image to image, Pro image to image 和 Pro image to image (Dola) 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 Seedream 5.0 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 Seedream 5.0 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.