ByteDanceImage modelChecking
Seedream 5.5 API
seedream-5-5-image-to-imageSeedream 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
Run Seedream 5.5 in the playground
The form is the request body: every field shows its key. Sign in to run it; a run is billed like an API task.
Parameters
modelSeedream 5.5Image to imageseedream-5-5-image-to-image
Advanced (3)
input.widthWidth, 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.heightHeight, 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.safetyIdentifierStable 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
Credits are reserved when a task is accepted and charged only on success. Failed tasks release the reservation; unconfirmed outcomes remain reserved until verified.
Request preview
{"model": "seedream-5-5-image-to-image","input": {"width": 1024,"height": 1024,"resolution": "2K","outputFormat": "png","watermark": "false","background": "auto","optimizePromptMode": "standard"}}The web playground sends this body with your signed-in session. From code, send the same body with an API key.
Result
Run the request and the result appears here, with its status and cost.
Seedream 5.5 pricing
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.
- 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 retriesIdempotent retries with the same key do not create a second charge.
- Price changesSend expectedPriceMicros to reject the task with PRICE_CHANGED if the price changed after you displayed it.
Compare Seedream 5.5 variants
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 imageDefault
seedream-5-5-text-to-imageText to image; Text; 1K, 1.5K, 2K
seedream-5-5-image-to-imageImage to image; Text, image; 1K, 1.5K, 2K
dola-seedream-5-5-text-to-imageText to image; Text; 1K, 1.5K, 2K
dola-seedream-5-5-image-to-imageImage to image; Text, image; 1K, 1.5K, 2K
| Variant | Task | Input | Resolution |
|---|---|---|---|
Text to imageDefaultseedream-5-5-text-to-image | Text to image | Text | 1K, 1.5K, 2K |
Image to imageseedream-5-5-image-to-image | Image to image | Text, image | 1K, 1.5K, 2K |
Text to image (Dola)dola-seedream-5-5-text-to-image | Text to image | Text | 1K, 1.5K, 2K |
Image to image (Dola)dola-seedream-5-5-image-to-image | Image to image | Text, image | 1K, 1.5K, 2K |
What Seedream 5.5 can do
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.
Capabilities
Format options
The request schema lists these formats. Availability and delivery depend on the variant.
PNG · JPEG
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.
imageUrlsVariants: Image to image, Image to image (Dola)
Use cases
Iterate on an image
Use a reference image and describe the change while identifying the parts to keep.
Create reusable assets
Explore transparent-background PNG output for stickers, product elements or design assets.
Combine references
Supply up to ten images to the edit variant and describe the role of each reference in the prompt.
Call Seedream 5.5 from code
Every image, video and music model uses the same asynchronous job API: submit a task, then poll for the result.
- 1
Create an API key
In the dashboard, with the jobs:create and jobs:read scopes. API keys - 2
Submit a task
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.
Minimal request
Required fields only, generated from the schema of Image to image. Set HERMES_API_KEY in your environment.
- Model ID
seedream-5-5-image-to-image- Endpoint
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": "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"Input parameters
Fields of Image to image (seedream-5-5-image-to-image). Unknown fields are rejected with INVALID_MODEL_INPUT.
| Field | Type | Required | Default | Allowed values and constraints |
|---|---|---|---|---|
prompt | string | required | — | Edit or fusion instruction 5–5000 chars |
width | integer | optional | 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 | optional | 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[] | required | — | Reference images, 1 to 10 ≤ 10 items, HTTPS image URL or media:<uuid> |
resolution | string | optional | "2K" | Takes priority over width and height. Values are 1K, 1.5K, and 2K. Default 2K. One of: |
outputFormat | string | optional | "png" | Output image format, png or jpeg. Default png. One of: |
watermark | string | optional | "false" | Add a watermark. true or false. Default false. Omitted requests are still sent as false. One of: |
background | string | optional | "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. One of: |
optimizePromptMode | string | optional | "standard" | Prompt optimization. Only standard is allowed. Omitted requests are still sent as standard. fast is rejected upstream. One of: |
safetyIdentifier | string | optional | — | 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 |
Upload a local file first
Replace the example URL with the returned media reference.
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
| Header | Value | Notes |
|---|---|---|
Authorization | Bearer <API key> | Or send the key in x-api-key. |
Content-Type | application/json | |
Idempotency-Key | <unique string ≤128> | Required. Reuse it only to retry the identical request. |
| Field | Type | Notes |
|---|---|---|
id | string | Hermes AI task ID. Use it to poll. |
model | string | Model slug. |
status | string | See task statuses. |
errorCode | string | null | Set when a task fails or needs review. |
priceMicros | integer | Quote fixed at admission, USD micro-units. |
currency | "USD" | |
createdAt / updatedAt | string | ISO 8601 timestamps. |
assets[] | array | { id, type, url?, text? }. url is a same-origin /api/v1/results/<uuid> link. |
replayed | boolean | Submit only. true when an idempotent retry matched. |
| Status | Terminal | Meaning |
|---|---|---|
queued | no | Accepted and waiting for a worker. |
submitting | no | Being sent to the model provider. |
running | no | The model is generating. |
succeeded | yes | Finished. Results are in assets. |
failed | yes | Finished without a result. The hold is released. |
reconciliation_required | yes | The result is being verified. Keep the task ID and do not resubmit automatically. |
| HTTP | Code | Meaning and action |
|---|---|---|
401 | AUTH_REQUIRED | Missing or invalid API key or session. |
403 | INSUFFICIENT_SCOPE | The API key lacks the scope this endpoint needs. |
403 | PERMISSION_DENIED | This credential cannot perform the operation. |
429 | API_KEY_RATE_LIMITED | The API key's rate limit was reached. Honor Retry-After. |
429 | API_KEY_USAGE_EXCEEDED | The API key reached its usage limit. Create a new key. |
400 | INVALID_REQUEST | The body is not a JSON object or a required value is missing. |
400 | INVALID_IDEMPOTENCY_KEY | Idempotency-Key must be 1–128 printable ASCII characters. |
400 | INVALID_MODEL_INPUT | input does not match the model schema (unknown field, missing required field, or invalid value). |
400 / 413 | INPUT_TOO_LARGE | The request body is larger than 256 KB. Upload media first and send a media reference. |
404 | REQUEST_NOT_FOUND | No chat request with this ID belongs to your account. |
404 | MODEL_NOT_FOUND | No model has this slug. |
404 | JOB_NOT_FOUND | No task with this ID belongs to your account. |
409 | IDEMPOTENCY_CONFLICT | This Idempotency-Key was used with different input. Use a new key for a new request. |
409 | PRICE_CHANGED | The price differs from expectedPriceMicros. Fetch the price and confirm again. |
409 | MODEL_PRICE_UNAVAILABLE | No price is configured for this model yet, so it cannot run. |
409 | PAYMENT_REVIEW_REQUIRED | A refund left an uncovered balance. Contact support or cover the balance before submitting tasks. |
409 | INSUFFICIENT_CREDITS | Available credits do not cover the task price. |
429 | RATE_LIMITED | Too many task submissions per minute. Retry later. |
429 | EXPORT_RATE_LIMITED | Too many CSV exports this minute. Honor Retry-After. |
429 | CONCURRENCY_LIMITED | Too many unfinished tasks. Wait for one to finish. |
503 | EXECUTION_UNAVAILABLE | Execution is not configured for this model right now. |
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 | This model is temporarily unavailable. Try again later. |
503 | EXECUTION_TEMPORARILY_UNAVAILABLE | Execution is temporarily unavailable. Retry with the same Idempotency-Key. |
503 | AUTH_UNAVAILABLE | Authentication is temporarily unavailable. Retry later. |
503 | API_UNAVAILABLE | The API is temporarily unavailable. Retry later. |
Seedream 5.5 API FAQ
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 text to image and image to image. 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 and 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 image 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. Unknown fields are rejected with INVALID_MODEL_INPUT.
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 and Text to image (Dola) take the same input fields and differ in tier and price; for image to image, Image to image and 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.