Bytedance Seedream V5.0 Flash Edit API Documentation

Bytedance Seedream V5.0 Flash Edit API Documentation

Playground

Seedream V5.0 Flash Edit by ByteDance edits and generates images from single-image or multi-reference inputs faster and at lower cost than Seedream V5.0 Pro Edit, supporting up to 10 reference images, aspect ratio selection, and 1K / 1.5K / 2K output at one price. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Seedream V5.0 Flash Edit is the fast, lower-cost tier of Seedream 5.0 image editing. It shares Seedream V5.0 Pro Edit’s capabilities — interactive precision editing, multi-reference control, and native multilingual text — and returns edits faster at a lower price.

Why Choose This?

• Multi-image reference editing
  Use up to 10 reference images for complex edits, compositions, and visual guidance.

• Natural language editing
  Describe the desired edit in plain text and let the model transform the input images accordingly.

• Pro capabilities, Flash speed
  Same editing capability set as Seedream V5.0 Pro Edit, tuned for faster turnaround.

• One price for every resolution and input count
  1k, 1.5k, and 2k cost the same, and reference images are not billed separately.

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

Parameters

How to Use

1. Upload reference images — Provide one or more images to guide the edit.
2. Write your prompt — Describe what should change and what should stay the same.
3. Choose aspect ratio — Select a supported aspect ratio, or leave it empty to follow the closest supported ratio from the first input image.
4. Choose resolution — 1k, 1.5k, or 2k; the price is the same.
5. Choose output format — Select jpeg or png.
6. Submit — Generate the final edited image.

Pricing

A flat $0.027 per edit, regardless of resolution or the number of reference images.

Best Use Cases

• Single-image editing — Edit one source image with natural-language instructions.
• Multi-reference composition — Use multiple images to guide complex edits and visual combinations.
• Product image editing — Refine product visuals, backgrounds, styles, and presentation.
• High-volume edit pipelines — Apply the same edit direction across large image sets.
• Creative iteration — Test different edit directions quickly using the same reference images.

Pro Tips

• Use clear prompts that describe both what should change and what should remain unchanged.
• Put the main subject in the first reference image and refer to others by position (“the jacket from image 2”).
• Leave aspect_ratio empty when you want the output to follow the closest supported ratio from the first input image.
• Since every resolution costs the same, pick 2k when you need a higher-resolution result.
• Keep reference images clear, relevant, and visually consistent with the desired edit.

Related Models

• Seedream V5.0 Flash — Generate images from text prompts.
• Seedream V5.0 Pro Edit — Higher-quality Seedream 5.0 image editing.

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",
  "images": [
    "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
  ],
  "aspect_ratio": "1:1",
  "resolution": "1k",
  "output_format": "jpeg"
}
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-flash/edit" \
  -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