Ideogram AI Ideogram V3 Remove Text API Documentation

Ideogram AI Ideogram V3 Remove Text API Documentation

Playground

Ideogram V3 Layerize Text separates flat graphic images into editable layers, extracting text and background for professional design workflows. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Features

Ideogram V3 Layerize Text separates the text layer from the background in any image, returning the text as a clean transparent PNG ready for editing, replacement, or compositing. Upload an image with text and get back an isolated text layer in seconds.

How to Use

1. Upload your image — provide any image containing text via URL or drag-and-drop.
2. Submit — the model extracts and isolates the text layer with a transparent background.
3. Download your clean text layer PNG ready for compositing or editing.

Pricing

Just $0.09 per image.

Best Use Cases

• Design editing — Extract text from existing designs to reuse, reposition, or restyle it independently.
• Localization & translation — Remove original text from images cleanly before replacing it with translated content.
• Template creation — Strip text from branded assets to create reusable background templates.
• Typography workflows — Isolate text elements for use in compositing, motion graphics, or print layouts.

Notes

• image is the only required field.
• Output is a PNG file with a transparent background containing only the isolated text layer.
• Ensure image URLs are publicly accessible if using a link rather than a direct upload.
• Please ensure your content complies with Ideogram’s usage policies.

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'
{
  "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
}
JSON
)

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