Bytedance Seedream V5.0 Pro API Documentation

Bytedance Seedream V5.0 Pro API Documentation

Playground

Seedream V5.0 Pro Text to Image by ByteDance generates high-quality images from text prompts, with aspect ratio selection, strong prompt following, and 1K / 2K output tiers for flexible image creation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Seedream V5.0 Pro is a multimodal image model built for professional work: high-density infographics, precise composition, photographic realism, and native multilingual text. It supports flexible aspect ratios, multiple resolution tiers, prompt optimization, and standard image output formats for production image workflows.

Why Choose This?

• Pro image quality
  Designed for high-quality image generation with strong prompt adherence.

• Flexible resolution tiers
  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.

• Prompt optimization
  Use standard prompt optimization for fuller prompt rewriting, or fast mode for quicker generation with lighter optimization.

• Standard output formats
  Generate images in jpeg or png format.

• Clean text-to-image workflow
  Provide a prompt, choose output settings, and generate the final image.

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 output format — Select jpeg or png.
5. Set prompt optimization optional — Use standard for fuller prompt rewriting or fast for quicker generation with lighter optimization.
6. Submit — Generate the final image.

Pricing

Pricing is based on selected resolution.

Best Use Cases

• High-quality image generation — Create polished images from detailed text prompts.
• Marketing visuals — Generate campaign assets, social media graphics, and promotional images.
• Creative concepting — Explore characters, environments, products, and visual styles.
• Layout-specific assets — Generate square, portrait, landscape, tall, wide, or cinematic images.
• Production image workflows — Use 2k when higher-resolution output is needed.
• Fast visual iteration — Use fast prompt optimization when speed matters more than detailed prompt rewriting.

Pro Tips

• Use prompt_optimization_mode: fast for quick iterations and standard for the final image; the difference is a few seconds versus tens of seconds on the same prompt.

• Use detailed prompts with subject, composition, lighting, style, mood, and background details.

• Choose 1k or 1.5k for faster and lower-cost prompt iteration.

• Choose 2k when you need higher-resolution final images.

• Use 9:16 for vertical mobile content and 16:9 for widescreen layouts.

• Use jpeg for general-purpose images and png when PNG output is needed.

• Use standard prompt optimization for complex or detailed prompts.

• Use fast prompt optimization when you want quicker generation and lighter prompt rewriting.

• Keep prompts clear and focused for stronger prompt adherence.

Related Models

• Seedream V5.0 Pro Edit — Edit images with text instructions.
• Seedream V5.0 Lite — Lightweight image generation 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": "jpeg",
  "prompt_optimization_mode": "standard"
}
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-v5.0-pro" \
  -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