Seedream 5.0 Pro Text-to-Image API

bytedance/seedream-v5.0-pro/text-to-image

1K/2K · 8 ratios · JPEG/PNG

The Seedream 5.0 Pro Text-to-Image API turns creative briefs into structured posters, infographics, product visuals, and realistic scenes. Use the prompt to direct information hierarchy, composition, lighting, materials, and multilingual in-image copy, then choose from eight aspect ratios, 1K or 2K resolution, and JPEG or PNG output.

Input

Prompt705/10000

Size

Resolution

Output format

Safety checker

The Playground sends enable_safety_checker explicitly with a default of true.

Ready

Continue with

Seedream 5.0 Pro Image Edit

Examples

Create a rigorous bilingual scientific infographic titled exactly "THE ANATOMY OF LIGHT / 光的构成" on a warm ivory background. Center a clear hand-blown glass prism and show three light paths with thin precise arrows, labeled exactly "KEY LIGHT / 主光", "FILL LIGHT / 补光", and "RIM LIGHT / 轮廓光". At the bottom include a three-step sequence labeled exactly "SHAPE / 塑形", "BALANCE / 平衡", and "POLISH / 精修". Use a clean Swiss editorial grid, accurate optical relationships, restrained cobalt and vermilion accents, realistic glass refraction, generous whitespace, crisp readable typography. Educational editorial design only; no brand, no logo, no product promotion, no advertisement, no watermark, no extra text.

Create a quiet editorial material-study still life, not an advertisement. On a worn oak worktable place exactly one hand-blown clear glass vase, one matte celadon ceramic bowl, and one folded undyed linen cloth. Soft north-window daylight reveals realistic glass thickness, subtle liquid refraction, tiny artisan bubbles, ceramic glaze variation, wood grain, and natural fabric fibers. Three-quarter eye-level composition, calm museum-study atmosphere, restrained neutral palette, physically believable shadows, photographic realism. No people, no brand, no logo, no packaging, no sales styling, no promotional text, no watermark.

Create a vertical bilingual natural-history field-guide page titled exactly "MIGRATION AT NIGHT / 夜间迁徙". Depict three scientifically plausible migratory birds in flight at different altitudes beneath a moonlit sky, with clean fine-line callouts labeled exactly "STAR COMPASS / 星辰罗盘", "MAGNETIC SENSE / 磁场感知", and "REST STOP / 迁徙停歇地". Include a small north arrow, a restrained route map, and a simple altitude scale. Museum field-guide layout, precise information hierarchy, midnight blue and parchment palette, crisp readable Chinese and English typography, natural feather detail, educational purpose only. No event promotion, no brand, no logo, no advertisement, no watermark, no extra text.

REST API

Quick Start

Authenticate, submit one minimal text-to-image task, then use its task_id to retrieve every generated image URL.

Authenticate the request

Create an API key, keep it on your server, and send Authorization: Bearer VIDGO_API_KEY.

Endpoint: POSThttps://api.vidgo.ai/api/generate/submit
Authentication: Authorization: Bearer VIDGO_API_KEY

Submit one generation task

Send the model ID at the top level and a prompt plus supported controls inside input. The response returns immediately with task_id.

Submit request

curl --request POST \
  --url "https://api.vidgo.ai/api/generate/submit" \
  --header "Authorization: Bearer $VIDGO_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "seedream-v5.0-pro",
  "input": {
    "prompt": "A clean product campaign image with controlled studio lighting.",
    "size": "1:1",
    "resolution": "1K",
    "output_format": "jpeg"
  }
}'

Wait for the result

Poll the status path while the task is not_started or running. On finished, read data.files[].file_url; on failed, stop and inspect the error.

Track status

GET https://api.vidgo.ai/api/generate/status/{task_id}

Poll every 2–5 seconds while status is not_started or running. Stop on finished or failed. On success, read every data.files[].file_url; for production, callback_url can receive the terminal result instead.

not_startedrunningfinishedfailed

Submit response

{
  "code": 200,
  "data": {
    "task_id": "task-unified-...",
    "status": "not_started",
    "created_time": "2026-08-22T10:00:00Z"
  }
}

Finished response

{
  "code": 200,
  "data": {
    "task_id": "task-unified-...",
    "status": "finished",
    "files": [
      {
        "file_url": "https://storage.vidgo.ai/generated/image.jpg",
        "file_type": "image"
      }
    ],
    "progress": 100,
    "error_message": null
  }
}

Complete runnable example

Expand this example for submission, polling, terminal-state checks, error handling, and extraction of all returned file URLs.

Complete runnable example

set -euo pipefail
: "${VIDGO_API_KEY:?Set VIDGO_API_KEY in your environment}"

REQUEST_BODY=$(cat <<'JSON'
{
  "model": "seedream-v5.0-pro",
  "input": {
    "prompt": "A clean product campaign image with controlled studio lighting.",
    "size": "1:1",
    "resolution": "1K",
    "output_format": "jpeg"
  }
}
JSON
)

SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --request POST \
  --url "https://api.vidgo.ai/api/generate/submit" \
  --header "Authorization: Bearer $VIDGO_API_KEY" \
  --header "Content-Type: application/json" \
  --data "$REQUEST_BODY")

TASK_ID=$(printf '%s' "$SUBMIT_RESPONSE" | jq -r '.data.task_id // .task_id // empty')
if [ -z "$TASK_ID" ]; then
  printf 'Submit response did not include task_id:
%s
' "$SUBMIT_RESPONSE" >&2
  exit 1
fi

while true; do
  STATUS_RESPONSE=$(curl --silent --show-error --fail-with-body \
    --url "https://api.vidgo.ai/api/generate/status/$TASK_ID" \
    --header "Authorization: Bearer $VIDGO_API_KEY")
  STATUS=$(printf '%s' "$STATUS_RESPONSE" | jq -r '.data.status // .status // empty')

  case "$STATUS" in
    finished)
      printf '%s' "$STATUS_RESPONSE" | jq -r '(.data.files // .files // [])[]?.file_url'
      break
      ;;
    failed)
      printf '%s' "$STATUS_RESPONSE" | jq -r '.data.error_message // .error_message // "Generation failed"' >&2
      exit 1
      ;;
    not_started|running)
      sleep 2
      ;;
    *)
      printf 'Unexpected task status: %s
' "$STATUS" >&2
      exit 1
      ;;
  esac
done

Request Parameters

The input object supports the following image-generation parameters.

Field	Type	Required	Default	Description
input.prompt	string	Yes	—	Non-empty after trimming; maximum 10,000 characters.
input.size	string	No	1:1	One of 1:1, 4:3, 3:4, 16:9, 9:16, 2:3, 3:2, or 21:9.
input.resolution	string	No	1K	1K or 2K.
input.output_format	string	No	jpeg	jpeg or png.
input.enable_safety_checker	boolean	No	— (Playground: true)	The playground sends true by default.

Response Fields

Submission returns task identity. Status responses add progress, files, or an error message.

Field	Type	Description
code	integer	Application result code; successful responses use 0 or 200.
message	string	Human-readable message when present.
data.task_id	string	Identifier used in the status endpoint.
data.status	string	not_started, running, finished, or failed.
data.created_time	string	Task creation time.
data.progress	integer	Completion percentage when reported.
data.files[]	array	All generated files after a successful task.
data.files[].file_url	string	Public URL of a generated image.
data.files[].file_type	string	Media type, expected to be image for Seedream 5.0 Pro Text-to-Image API.
data.files[].watermark_url	string \| null	Watermarked file URL when available.
data.error_message	string \| null	Failure detail when status is failed.

Task Lifecycle

Continue polling only in non-terminal states. finished and failed both stop the lifecycle.

not_started
Accepted and waiting to begin; continue polling.
running
Generation is in progress; continue polling.
finished
Successful terminal state; read every data.files[].file_url.
failed
Failed terminal state; read data.error_message and stop.

Polling and Errors

AuthenticationA 401 response means the Bearer API key is missing or invalid.
ValidationA 400 response identifies an invalid model, prompt, enum value, or prompt length.
Network failureA submit or status request can fail before the task state changes; preserve inputs and retry deliberately.
Polling intervalStart around 2–5 seconds and back off on 429 or 5xx responses.
Terminal statesContinue only for not_started or running; stop immediately for finished or failed.
Callback optionAdd callback_url at the top level to receive a flat terminal task object by POST.

Model Specifications

Specification	Value	Details
Input mode	Text prompt	A prompt defines the subject, composition, and visual treatment.
Output	Image	The asynchronous task can return one or more image files.
Resolution	1K / 2K	1K is the backend default.
Aspect ratio	8 presets	1:1, 4:3, 3:4, 16:9, 9:16, 2:3, 3:2, and 21:9.
File format	JPEG / PNG	JPEG is the backend default when output_format is omitted.
Frontend estimate	15 credits / request	The current frontend estimator returns the same value for every supported configuration.

View Seedream 5.0 Pro Text-to-Image API documentation

Seedream 5.0 Pro Text-to-Image API

Seedream 5.0 Pro Text-to-Image API accepts a prompt of up to 10,000 characters and returns an asynchronous image task. Choose one of eight aspect ratios, 1K or 2K resolution, and JPEG or PNG output.

Why Choose Seedream 5.0 Pro Text-to-Image API?

Plan dense visual layouts.Turn timelines, sections, labels, charts, and supporting imagery into a clear information hierarchy.
Direct the whole image in one prompt.Control the subject, camera, composition, palette, lighting, materials, and atmosphere as one creative brief.
Build multilingual copy into the design.Provide the exact wording and describe its placement, scale, and typographic role in the image.
Specify observable surface and lighting details.Describe product surfaces, skin texture, reflections, fabric, glass, and studio or natural light in the prompt.
Choose explicit output settings.Select from eight aspect ratios, 1K or 2K resolution, and JPEG or PNG output; the frontend estimate is 15 credits per request.

Parameters

Parameter	Requirement	Description
prompt	Required	Describe the subject, information hierarchy, composition, visual style, and exact in-image wording in up to 10,000 characters.
size	Optional	Choose the output aspect ratio for the intended placement. Default`1:14:33:416:99:162:33:221:9`
resolution	Optional	Choose the output resolution tier. Default`1K2K`
output_format	Optional	Choose JPEG or PNG for the generated file. Default`jpegpng`
enable_safety_checker	Optional	Set the boolean content-safety check for the request. `truefalse`

How to Use

Frame the deliverableName the audience, format, subject, message, and visual result the image needs to achieve.
Write the layout hierarchyDescribe the headline, focal subject, supporting information, placement, camera, lighting, and palette in reading order.
Specify in-image copyPut required wording in quotation marks and state its language, position, scale, and emphasis.
Choose the outputMatch the aspect ratio to the placement, then select 1K or 2K and JPEG or PNG.
Submit and reviewRun the request, retrieve every returned image, and inspect hierarchy, copy, materials, and small details.

Pricing

The current frontend estimate is 15 credits per request. At $0.005 per credit, the estimated cost is $0.075 for every supported ratio, resolution, and output format.

Usage	Rate	Details
Frontend request estimate	15 credits	The estimate is unchanged across 1K/2K, all eight ratios, JPEG, and PNG.

Best Use Cases

Product Campaign VisualsTurn a product brief, placement instructions, and lighting direction into launch artwork.
Posters with Exact CopyQuote a headline and supporting text, then specify hierarchy and placement for a composed poster.
Infographics and ExplainersTurn structured concepts into an information-led image with clear sections, labels, and visual emphasis.
Multilingual Social AssetsDescribe localized copy and platform ratio to create market-specific image concepts.

Pro Tips

Write subject and setting first, then composition, camera, lighting, palette, and finishing detail.
Put any required in-image wording in quotation marks and describe where it should appear.
State the visual hierarchy explicitly when the image contains several blocks of information.
Choose the delivery ratio before describing edge placement or negative space.
Keep instructions compatible and remove secondary details that compete with the main subject.

Notes

prompt supports up to 10,000 characters for the complete creative brief.
size supports eight aspect ratios, and resolution supports 1K or 2K output.
output_format defaults to jpeg; enable_safety_checker is available as a boolean input control.
The request returns an asynchronous task ID; finished results provide image URLs in data.files[].file_url.

Related Models

Seedream 5.0 LiteUse the faster Seedream companion for text generation and reference-guided editing.

Seedream 4.5Create or edit images with the established Seedream 4.5 workflow.

GPT Image 2Compare image generation and editing across flexible quality tiers.

Nano Banana ProUse a Google image workflow for text rendering, blending, and image editing.

FLUX.2Explore text-to-image and multi-reference editing across Pro and Flex variants.

Seedream 4Use the earlier Seedream generation and editing family for compatible workflows.

Frequently Asked Questions about Seedream 5.0 Pro Text-to-Image API

What is the Seedream 5.0 Pro Text-to-Image API?

Seedream 5.0 Pro is ByteDance’s Seed image model for design-oriented generation, available through the Vidgo REST API. It turns a prompt into structured posters, infographics, product visuals, realistic scenes, and multilingual in-image text, returned through an asynchronous image task.

How do I call the Seedream 5.0 Pro Text-to-Image API?

POST to /api/generate/submit with Authorization: Bearer VIDGO_API_KEY, model set to seedream-v5.0-pro, and model inputs inside input. The response gives you a task_id for status retrieval.

How much does Seedream 5.0 Pro Text-to-Image cost?

The current frontend estimate is 15 credits per request. At $0.005 per credit, the estimated cost is $0.075 for any supported ratio, resolution, or format.

What inputs does Seedream 5.0 Pro Text-to-Image accept?

The input object supports prompt, size, resolution, output_format, and optional enable_safety_checker. Use prompt for the subject, hierarchy, composition, visual style, lighting, materials, and exact in-image copy.

How do I get the generated images?

Poll GET /api/generate/status/{task_id} until finished or failed. On success, read every data.files[].file_url, or supply callback_url when submitting to receive the terminal task.

Which Seedream 5.0 Pro API mode should I choose?

Choose Text-to-Image when the request contains a prompt but no source images. Choose Image Edit when the request includes one to ten ordered source-image URLs.