本文へスキップ

ByteDanceImage model確認中

Seedream 5.5 API

Model IDdola-seedream-5-5-image-to-image

Seedream 5.5 is ByteDance's image model for text-to-image creation and reference-based editing, with a focus on detail, text and iterative edits.

  • Text to image
  • Image to image
  • Up to 10 input images
  • 1K, 1.5K or 2K output
  • Format options

プレイグラウンドで Seedream 5.5 を実行

The form is the request body: every field shows its key. Sign in to run it; a run is billed like an API task.

パラメーター

モデル
model

Seedream 5.5Image to image (Dola)dola-seedream-5-5-image-to-image

必須
input.prompt

Edit or fusion instruction 5–5000 chars

input.imageUrls

Reference images, 1 to 10 ≤ 10 items · HTTPS image URL or media:<uuid>

一般的なオプション
input.resolution

Takes priority over width and height. Values are 1K, 1.5K, and 2K. Default 2K.

input.outputFormat

Output image format, png or jpeg. Default png.

input.watermark

Add a watermark. true or false. Default false. Omitted requests are still sent as false.

input.background

Background. auto follows the prompt and output format. jpeg with auto is opaque. jpeg with transparent is rejected. opaque is an opaque background. Default auto.

input.optimizePromptMode

Prompt optimization. Only standard is allowed. Omitted requests are still sent as standard. fast is rejected upstream.

詳細設定 (3)
input.width

Width, 240 to 8595. The product with height must be 921600 to 4624220, and the aspect ratio must be 1/16 to 16. Ignored when resolution is set. 240–8595

input.height

Height, 240 to 8595. The product with width must be 921600 to 4624220, and the aspect ratio must be 1/16 to 16. Ignored when resolution is set. 240–8595

input.safetyIdentifier

Stable English identifier of the end user, at most 64 characters. A hash such as sha256_user_abc123 is recommended. Empty values are not sent. 0–64 chars

Estimated cost
料金を読み込み中…

タスクが受け付けられるとクレジットが確保され、成功した場合のみ課金されます。失敗したタスクは確保を解除し、結果未確定のものは確認まで確保されたままです。

リクエストのプレビュー

{"model": "dola-seedream-5-5-image-to-image","input": {"width": 1024,"height": 1024,"resolution": "2K","outputFormat": "png","watermark": "false","background": "auto","optimizePromptMode": "standard"}}

Web Playground はサインイン中のセッションでこのボディを送信します。コードからは同じボディを API キーとともに送信してください。

結果

Run the request and the result appears here, with its status and cost.

Seedream 5.5 の料金

Prices are shown in USD for each available variant and specification. The billing unit is shown with its rate; an official reference appears only when a matching list price is published.

料金を読み込み中…
  • Charged only on successOnly successful tasks are charged. Failed tasks release reserved credits; tasks with an unconfirmed outcome keep their reservation until the result is verified.
  • Safe retries同じキーによる冪等な再試行で二重に課金されることはありません。
  • Price changesexpectedPriceMicros を送ると、表示後に料金が変わった場合に PRICE_CHANGED でタスクを拒否できます。

Seedream 5.5 のバリアントを比較

Each variant has its own model ID and input schema. Pick the task first, then the tier. Additional fields are shown when variants differ.

  • Text to imageデフォルト

    seedream-5-5-text-to-image

    Text to image; テキスト; 1K, 1.5K, 2K

  • Image to image

    seedream-5-5-image-to-image

    Image to image; テキスト, 画像; 1K, 1.5K, 2K

  • Text to image (Dola)

    dola-seedream-5-5-text-to-image

    Text to image; テキスト; 1K, 1.5K, 2K

  • Image to image (Dola)

    dola-seedream-5-5-image-to-image

    Image to image; テキスト, 画像; 1K, 1.5K, 2K

Seedream 5.5 でできること

ByteDance describes Seedream 5.5 as an image generation and editing model. Its release announcement emphasizes preserving unchanged regions across edits, transparent and semi-transparent assets, and more natural materials and text. These are the manufacturer's reported improvements; results depend on the input and request.

The Hermes catalog lists text-to-image and image-to-image variants, including Dola variants. The edit schema accepts one to ten reference images. The listed resolution choices are 1K, 1.5K and 2K; requests may also specify width and height. For transparent backgrounds, select the transparent background option and PNG output, and check the returned asset.

Check each variant's live status and pricing before making a request. A listed model may be unavailable while execution and billing are being configured.

できること

  • Format options

    The request schema lists these formats. Availability and delivery depend on the variant.

    PNG · JPEG

    outputFormat

    Every variant

  • 1K, 1.5K or 2K output

    Pick the output resolution: 1K, 1.5K or 2K.

    resolution

    Every variant

  • Up to 10 input images

    Send up to 10 images in one request as HTTPS URLs or uploaded media references.

    imageUrls

    バリアント: Image to image, Image to image (Dola)

ユースケース

  1. Iterate on an image

    Use a reference image and describe the change while identifying the parts to keep.

  2. Create reusable assets

    Explore transparent-background PNG output for stickers, product elements or design assets.

  3. Combine references

    Supply up to ten images to the edit variant and describe the role of each reference in the prompt.

コードから Seedream 5.5 を呼び出す

Every image, video and music model uses the same asynchronous job API: submit a task, then poll for the result.

  1. 1

    API キーを作成

    In the dashboard, with the jobs:create and jobs:read scopes. API キー
  2. 2

    タスクを送信

    POST /api/v1/jobs with the model ID and an input object. The response is 202 with a task ID.
  3. 3

    Poll for the result

    GET /api/v1/jobs/{id} until the status is succeeded, then download the output URLs.

最小リクエスト

Required fields only, generated from the schema of Image to image (Dola). Set HERMES_API_KEY in your environment.

Model ID
dola-seedream-5-5-image-to-image
エンドポイント
https://api.hermes-ai.net/api/v1/jobs
Full task API reference
# 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-5-5-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"

入力パラメーター

Fields of Image to image (Dola) (dola-seedream-5-5-image-to-image). 不明なフィールドは INVALID_MODEL_INPUT で拒否されます。

フィールド型必須デフォルト許可される値と制約
prompt
string必須—

Edit or fusion instruction

5–5000 chars

width
integer任意1024

Width, 240 to 8595. The product with height must be 921600 to 4624220, and the aspect ratio must be 1/16 to 16. Ignored when resolution is set.

240–8595

height
integer任意1024

Height, 240 to 8595. The product with width must be 921600 to 4624220, and the aspect ratio must be 1/16 to 16. Ignored when resolution is set.

240–8595

imageUrls
string[]必須—

Reference images, 1 to 10

≤ 10 items, HTTPS image URL or media:<uuid>

resolution
string任意"2K"

Takes priority over width and height. Values are 1K, 1.5K, and 2K. Default 2K.

選択肢: "1K", "1.5K", "2K"

outputFormat
string任意"png"

Output image format, png or jpeg. Default png.

選択肢: "png", "jpeg"

watermark
string任意"false"

Add a watermark. true or false. Default false. Omitted requests are still sent as false.

選択肢: "false", "true"

background
string任意"auto"

Background. auto follows the prompt and output format. jpeg with auto is opaque. jpeg with transparent is rejected. opaque is an opaque background. Default auto.

選択肢: "auto", "transparent", "opaque"

optimizePromptMode
string任意"standard"

Prompt optimization. Only standard is allowed. Omitted requests are still sent as standard. fast is rejected upstream.

選択肢: "standard"

safetyIdentifier
string任意—

Stable English identifier of the end user, at most 64 characters. A hash such as sha256_user_abc123 is recommended. Empty values are not sent.

0–64 chars

まずローカルファイルをアップロード

例の URL を、返されたメディア参照に置き換えてください。

POST /api/v1/media
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
ヘッダー値備考
AuthorizationBearer <API key>または x-api-key でキーを送信します。
Content-Typeapplication/json
Idempotency-Key<unique string ≤128>必須。まったく同じリクエストを再試行する場合のみ再利用してください。
フィールド型備考
idstringHermes AI のタスク ID。ポーリングに使用します。
modelstringモデル slug。
statusstringタスクのステータスを参照。
errorCodestring | nullタスクが失敗した場合や確認が必要な場合に設定されます。
priceMicrosinteger受付時に確定した見積もり(USD マイクロ単位)。
currency"USD"
createdAt / updatedAtstringISO 8601 形式のタイムスタンプ。
assets[]array{ id, type, url?, text? }。url は同一オリジンの /api/v1/results/<uuid> リンクです。
replayedboolean送信時のみ。冪等な再試行が一致した場合は true。
ステータス終了状態意味
queuedいいえ受け付け済みで、ワーカーを待っています。
submittingいいえモデルプロバイダーに送信中です。
runningいいえモデルが生成中です。
succeededはい完了しました。結果は assets にあります。
failedはい結果なしで終了しました。予約は解放されます。
reconciliation_requiredはいThe result is being verified. Keep the task ID and do not resubmit automatically.
HTTPコード意味と対応
401AUTH_REQUIREDAPI キーまたはセッションがない、または無効です。
403INSUFFICIENT_SCOPEAPI キーにこのエンドポイントで必要な権限がありません。
403PERMISSION_DENIEDこの認証情報ではこの操作を実行できません。
429API_KEY_RATE_LIMITEDAPI キーのレート制限に達しました。Retry-After に従ってください。
429API_KEY_USAGE_EXCEEDEDAPI キーが使用上限に達しました。新しいキーを作成してください。
400INVALID_REQUESTボディが JSON オブジェクトではないか、必須の値がありません。
400INVALID_IDEMPOTENCY_KEYIdempotency-Key は 1〜128 文字の印字可能な ASCII 文字である必要があります。
400INVALID_MODEL_INPUTinput がモデルのスキーマと一致しません(不明なフィールド、必須フィールドの欠落、または無効な値)。
400 / 413INPUT_TOO_LARGEリクエストボディが 256 KB を超えています。先にメディアをアップロードし、メディア参照を送信してください。
404REQUEST_NOT_FOUNDNo chat request with this ID belongs to your account.
404MODEL_NOT_FOUNDこの slug のモデルはありません。
404JOB_NOT_FOUNDこの ID のタスクはお客様のアカウントに存在しません。
409IDEMPOTENCY_CONFLICTこの Idempotency-Key は別の入力で使用されています。新しいリクエストには新しいキーを使ってください。
409PRICE_CHANGED料金が expectedPriceMicros と異なります。料金を取得して再度確認してください。
409MODEL_PRICE_UNAVAILABLEこのモデルにはまだ料金が設定されていないため、実行できません。
409PAYMENT_REVIEW_REQUIREDA refund left an uncovered balance. Contact support or cover the balance before submitting tasks.
409INSUFFICIENT_CREDITS利用可能なクレジットがタスクの料金に足りません。
429RATE_LIMITED1 分あたりのタスク送信数が多すぎます。後で再試行してください。
429EXPORT_RATE_LIMITEDToo many CSV exports this minute. Honor Retry-After.
429CONCURRENCY_LIMITED未完了のタスクが多すぎます。いずれかが完了するまでお待ちください。
503EXECUTION_UNAVAILABLE現在、このモデルの実行は設定されていません。
429UPSTREAM_RATE_LIMITEDThe model provider is rate limiting chat requests. Retry with backoff; nothing was charged.
502UPSTREAM_ERRORThe model provider failed the chat request. Nothing was charged; retry later.
503PLATFORM_BUDGET_EXCEEDEDThis model is temporarily unavailable. Try again later.
503EXECUTION_TEMPORARILY_UNAVAILABLE一時的に実行できません。同じ Idempotency-Key で再試行してください。
503AUTH_UNAVAILABLE一時的に認証を利用できません。後で再試行してください。
503API_UNAVAILABLE一時的に API を利用できません。後で再試行してください。

Seedream 5.5 API のよくある質問

Answers built from the model's schema and the Hermes AI API contract.

What is the difference between text to image and image to image?

Text to image starts with a prompt. Image to image also requires imageUrls, containing one to ten references. Dola variants have their own model IDs, so check their current status and price separately.

Does Seedream 5.5 always preserve unchanged pixels?

ByteDance reports improved preservation of unedited regions in its model announcement. That is a manufacturer claim, not a guarantee for every input or every Hermes request; inspect the result for the details important to your workflow.

What can the Seedream 5.5 API do?

Seedream 5.5 by ByteDance handles テキストから画像 および 画像から画像. The catalog lists 4 variants, each with its own model ID and input schema. Check the current availability before sending a request.

Which durations, resolutions and aspect ratios does Seedream 5.5 support?

Across its variants, Seedream 5.5 supports 1K, 1.5K および 2K resolution. Each variant accepts its own subset; the variants table on this page lists them.

What input does Seedream 5.5 accept?

A text prompt of up to 5,000 characters, plus 画像 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. 不明なフィールドは INVALID_MODEL_INPUT で拒否されます。

How is Seedream 5.5 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 5.5 variant should I choose?

For text to image, Text to image および Text to image (Dola) take the same input fields and differ in tier and price; for image to image, Image to image および 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 5.5 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 5.5 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.