Luma Photon Modify

Luma Photon Modify

Playground

Luma Photon Modify is a text-to-image generation model that converts text prompts into images for creative and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Edit and transform images with natural language using Luma Photon Modify. Simply describe the changes you want — swap backgrounds, modify elements, or transform scenes — and watch your image transform instantly. Perfect for quick edits, background replacements, and creative modifications.

Why It Looks Great

• Natural language editing: Describe changes in plain English — no complex tools needed.
• Background replacement: Seamlessly swap backgrounds while preserving subjects.
• Scene transformation: Modify environments, lighting, and context effortlessly.
• Subject preservation: Maintains the integrity of your main subject during edits.
• Prompt Enhancer: Built-in tool to refine your editing instructions.
• Ultra-affordable: Professional image editing at just $0.015 per image.

Parameters

How to Use

1. Write your edit instruction — describe what you want to change.
2. Use Prompt Enhancer (optional) — click to refine your instruction.
3. Upload your image — drag and drop or paste a public URL.
4. Run — click the button to apply the edit.
5. Download — preview and save your modified image.

Pricing

Flat rate per image.

Best Use Cases

• Background Replacement — Change backgrounds to any scene or setting.
• Scene Transformation — Move subjects to different environments or contexts.
• Creative Compositing — Place subjects in imaginative or fantastical settings.
• Product Photography — Swap product backgrounds for professional presentations.
• Social Media Content — Quick edits for engaging visual content.

Example Prompts

• “Change the background to large performance stage”
• “Replace the background with a tropical beach at sunset”
• “Put the subject in a futuristic cityscape”
• “Change the setting to a cozy coffee shop interior”
• “Transform the background to a snowy mountain landscape”
• “Place in a professional studio with white backdrop”

Pro Tips for Best Results

• Be specific about the new background or setting you want.
• Photon Modify excels at background replacements and scene changes.
• Include lighting and atmosphere details for more cohesive results.
• Works best when the subject is clearly defined in the original image.
• Use for quick iterations — at $0.015, you can experiment freely.
• Combine with descriptive atmosphere: “dramatic lighting”, “warm tones”, “soft focus”.

Notes

• If using a URL, ensure it is publicly accessible.
• Best results come from images with clear subject-background separation.
• Processing is fast and efficient for rapid workflow integration.
• Ideal for batch processing due to low cost per 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"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/luma/photon-modify" \
  -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