Recraft AI Recraft V4 Create Style API Documentation

Recraft AI Recraft V4 Create Style API Documentation

Playground

Recraft V4 Create Style creates a reusable style ID from reference images, enabling consistent visual style control for image generation, brand assets, design systems, marketing visuals, and creative production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Recraft V4 Create Style creates a reusable visual style from reference images. Upload 1 to 10 images, choose a base style, and control how strictly the generated style should match the references.

Why Choose This?

• Reference-based style creation
  Create a reusable style from uploaded reference images.

• Multi-image style input
  Use 1 to 10 images to define the visual direction more clearly.

• Style match control
  Choose between precise matching and more flexible interpretation.

• Base style selection
  Use any for general style creation or vector_illustration for vector-style references.

• Simple style workflow
  Upload references, choose style settings, and generate a reusable style result.

Parameters

How to Use

1. Upload reference images — Provide 1 to 10 images that represent the style you want to capture.
2. Choose base style — Use any for general style creation or vector_illustration for vector-style output.
3. Set match mode — Use precise for closer style matching or flexible for broader interpretation.
4. Submit — Generate the reusable style result.

Pricing

Pricing is fixed at $0.0055 per request.

images, base_style, and match do not add separate charges.

Best Use Cases

• Brand style creation — Build a reusable style from brand visuals or campaign references.
• Illustration style matching — Capture the look of vector or illustrated reference images.
• Creative consistency — Reuse a generated style across later image generation workflows.
• Visual direction testing — Create style presets from multiple references for design exploration.
• Production workflows — Standardize image style before generating larger creative batches.

Pro Tips

• Use visually consistent reference images for stronger style extraction.
• Provide multiple images when the style is complex or needs better definition.
• Use precise when the output should closely follow the reference style.
• Use flexible when you want the model to generalize the style more broadly.
• Use vector_illustration when the references are clearly vector-style or flat illustration assets.

Notes

• The generated style_id must be used with the matching model version.
• Use a standard Recraft V4 style_id only with recraft-v4-style models.
• Use a Recraft V4 Style Pro style_id only with recraft-v4-style-pro models.
• Do not mix standard and Pro style IDs across model versions.

Related Models

• Recraft V4 Style Text-to-Image — Generate images using a reusable standard Recraft V4 style.
• Recraft V4 Style Text-to-Vector — Generate vector graphics using a reusable standard Recraft V4 style.
• Recraft V4 Style Pro Text-to-Image — Generate images using a reusable Recraft V4 Style Pro style.
• Recraft V4 Style Pro Text-to-Vector — Generate vector graphics using a reusable Recraft V4 Style Pro style.

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'
{
  "images": [
    "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
  ],
  "base_style": "any",
  "match": "precise"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/recraft-ai/recraft-v4/create-style" \
  -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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 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|deleted) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters