Bytedance Seedream V4 Sequential API Documentation

Bytedance Seedream V4 Sequential API Documentation

Playground

Seedream 4.0 by creates 4K images with editing, character/object consistency and sequential multi-image generation. Ready-to-use REST API, best performance, no coldstarts, affordable pricing.

Features

What is it?

Seedream v4 sequential is ’s SOTA image model that use for sequential/group generation in one pipeline—built for cross-image consistency and rapid iteration.

Why choose Seedream?

• All-in-one, multi-modal: T2I, edit, and multi-image sets without switching models.
• Five strengths: precise instruction editing, high feature retention, deep understanding, ultra-fast inference, ultra-high-res output.
• Speed: as little as ~1.8 s for a 2K image (T2I).
• Powerful edits: add/remove objects, attribute & style changes, structural ops (e.g., face swap), texture/brush/frame edits.
• Sequential consistency: maintains identity, palette, and layout across a set/series.

Designed for

• Commercial design — Posters, apparel, packaging, e-commerce visuals; fast varianting and brand-safe edits.
• Entertainment IP — Anime/film characters; style-consistent key art, poses, and look dev.
• Art creation — High-res illustration, stylistic explorations, and series with coherent aesthetics.
• Architecture — Concept renders, façade studies, material/lighting variations across sets.
• Brand content — Campaign assets and social creatives with locked palette, logo, and identity.

How to use

1. Write prompt: action + object + target feature. For sets add “a series of N images” and style locks.
2. Set the parameter: size, max_images.

Price

• $0.027 per image.
• Total price = max_images * $0.027

Prompt Examples

• Instruction edit: Replace [A] with [B]; keep [lighting/style]; preserve [logo/identity].
• T2I coherent: A [subject] in [scene/time/weather], [camera/lens], [lighting], [style]; key props [X]; composition [framing].
• Sequential set: Generate a series of [N] images of [subject/brand] in [scenario]; keep consistent [palette/logo/identity]; vary [poses/angles/backgrounds].

Note

Please set the max_image first, and then input how many images you want to generate in prompt! Such as:

• max_image = 4.
• Prompt: I want to generate 4 images… + (your prompt)

Recommended Resolutions

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "size": "2048*2048",
  "max_images": 1
}
JSON
)

# 1. Submit the prediction once. Never retry this request automatically:
# a retry after an unclear failure can create a second, billed task.
CHECK='The task may already exist. Check History or the predictions list before submitting again.'
if ! SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --connect-timeout 10 --max-time 60 \
  -X POST "https://api.wavespeed.ai/api/v3/bytedance/seedream-v4/sequential" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}"); then
  printf 'Submit failed. %s\n' "${CHECK}" >&2
  exit 1
fi

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id. %s\n' "${CHECK}" >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction reaches a final status.
BODY_FILE=$(mktemp)
trap 'rm -f "${BODY_FILE}"' EXIT
while true; do
  # Transient errors (429, 5xx) are retried, honoring Retry-After.
  HTTP_CODE=$(curl --silent --show-error --fail-with-body \
    --connect-timeout 10 --max-time 60 --retry 5 --retry-delay 2 \
    --output "${BODY_FILE}" --write-out '%{http_code}' \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}" || true)
  case "${HTTP_CODE}" in
    2??) ;;
    000|429|5??)  # dropped connection or temporary error: keep polling
      printf 'Task %s: HTTP %s, polling again in 10s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      sleep 10; continue ;;
    *) printf 'Task %s: HTTP %s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      cat "${BODY_FILE}" >&2; exit 1 ;;
  esac
  RESULT=$(jq 'if type == "object" and has("data") then .data else . end' "${BODY_FILE}")
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted)
      printf 'Task %s ended with status %s\n' "${PREDICTION_ID}" "${STATUS}" >&2
      printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Every model also accepts the global request options enable_sync_mode and enable_base64_output; see their pages for details.

Response Parameters

Result Request Parameters

Result Response Parameters