Bytedance Seedream V5.5 API Documentation

Bytedance Seedream V5.5 API Documentation

Playground

Seedream 5.5 Text to Image by ByteDance generates images from text prompts with improved photographic realism and aesthetics, native transparent-background output, aspect ratio selection, and 1K, 1.5K and 2K output tiers. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Seedream 5.5 is ByteDance’s image model focused on photographic realism, visual aesthetics, and consistent editing. It generates images from text prompts, supports flexible aspect ratios and resolution tiers up to 2K, and can output images with a native transparent background (RGBA).

Why Choose This?

• Photographic realism and aesthetics
  Built for lifelike detail, natural light, and polished compositions.

• Native transparent background
  Set background to transparent to get a PNG with an alpha channel straight from the model, with no separate cut-out step.

• Flexible resolution tiers up to 2K
  Choose 1k or 1.5k for lower-cost generation, or 2k for higher-resolution output.

• Flexible aspect ratios
  Supports square, portrait, landscape, tall, wide, and cinematic aspect ratios.

• PNG by default
  Output is PNG unless you ask for jpeg.

Parameters

How to Use

1. Write your prompt — Describe the subject, scene, style, lighting, composition, and visual details.
2. Choose aspect ratio — Select the layout that matches your target format.
3. Choose resolution — Use 1k or 1.5k for lower-cost drafts, or 2k for higher-resolution output.
4. Choose background — Use transparent for cut-out assets such as stickers, product shots, and game or design elements.
5. Submit — Generate the final image.

Pricing

Pricing is based on selected resolution.

Best Use Cases

• Photorealistic imagery — Product, lifestyle, and portrait visuals with natural detail.
• Transparent assets — Stickers, icons, characters, and objects ready to place on any background.
• Marketing visuals — Campaign assets, social media graphics, and promotional images.
• Creative concepting — Explore characters, environments, products, and visual styles.
• Layout-specific assets — Square, portrait, landscape, tall, wide, or cinematic images.

Pro Tips

• Use detailed prompts with subject, composition, lighting, style, mood, and background details.
• Choose 1k or 1.5k for faster and lower-cost prompt iteration, and 2k for final images.
• Use 9:16 for vertical mobile content and 16:9 for widescreen layouts.
• For a cut-out, ask for the subject on its own in the prompt and set background to transparent.

Related Models

• Seedream 5.5 Edit — Edit images with up to 10 references.
• Seedream 5.5 Layer Decomposition — Split an image into a base image and transparent layers.
• Seedream V5.0 Pro — The previous Pro model.

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",
  "aspect_ratio": "1:1",
  "resolution": "1k",
  "output_format": "png",
  "background": "auto"
}
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-v5.5" \
  -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