Bytedance Seedream V5.0 Lite Edit API Documentation

Bytedance Seedream V5.0 Lite Edit API Documentation

Playground

Seedream 5.0 Lite Edit by is a state-of-the-art image editing model preserving facial features, lighting, and color tones from reference images. Features high-fidelity editing with professional quality, superior prompt adherence, and up to 4K resolution. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Seedream V5.0 Lite Edit is lightweight image editing model, enabling creative transformations and style transfers using reference images and text prompts. Upload reference images and describe the desired edit — the model generates stunning results while preserving identity and key features.

Why Choose This?

• Multi-image reference Use multiple reference images for complex edits and compositions.

• Natural language editing Describe your edit in plain text — reference images by Figure number for precise control.

• Style transfer Transform subjects into different aesthetics like cyberpunk, anime, fantasy, and more.

• Lightweight & fast Lite version optimized for speed while maintaining quality.

• Prompt Enhancer Built-in tool to automatically improve your edit descriptions.

• Flexible sizing Specify custom output size, or leave blank to match the reference image.

Parameters

How to Use

1. Upload reference images — add images containing subjects or elements for your edit.
2. Write your prompt — describe the transformation, using “Figure 1”, “Figure 2” to reference specific images.
3. Set size (optional) — specify output dimensions, or leave blank for default.
4. Use Prompt Enhancer (optional) — click to automatically refine your description.
5. Run — submit and download your edited image.

Pricing

Best Use Cases

• Style Transfer — Transform portraits into cyberpunk, anime, fantasy, or artistic styles.
• Character Reimagining — Place subjects in new environments or scenarios.
• Creative Compositing — Combine elements from multiple references.
• Concept Art — Generate stylized versions of existing images.
• Social Media Content — Create eye-catching edits for posts and profiles.

Pro Tips

• Use “Figure 1”, “Figure 2”, etc. in your prompt to reference images in upload order.
• Be specific about the style you want — include lighting, aesthetic, and mood details.
• Clear, front-facing portraits produce the best identity preservation.
• Try the Prompt Enhancer for more detailed and effective descriptions.
• Lite version is great for quick iterations before using the full model.

Notes

• Both prompt and images are required fields.
• Ensure uploaded image URLs are publicly accessible.
• Output size defaults to reference image’s aspect ratio if not specified.

Related Models

• Seedream V5.0 Lite Text-to-Image — Generate images from text prompts.
• Seedream V4 Text-to-Image — Previous generation text-to-image.

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"
  ],
  "output_format": "jpeg"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/bytedance/seedream-v5.0-lite/edit" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "${TASK}" | jq -r '.urls.get // empty')
if [ -z "${RESULT_URL}" ]; then RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"; fi

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "${STATUS}" >&2; exit 1 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters