Recraft AI Recraft V4 Style Text To Image API Documentation

Recraft AI Recraft V4 Style Text To Image API Documentation

Playground

Recraft V4 Style Text-to-Image generates styled images from text prompts using either a reusable style ID or reference images, enabling consistent visual direction for brand assets, design systems, marketing visuals, social content, and creative production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Recraft V4 Style Text-to-Image generates images from text prompts using either a reusable style_id or temporary style reference images. Use it to create visually consistent image assets with controllable aspect ratio and style matching.

Why Choose This?

• Text-to-image generation
  Generate images directly from natural-language prompts.

• Reusable style support
  Use a style_id created by the matching Create Style model to keep a consistent visual style.

• Reference-image style input
  Provide reference images to create a style for the current request when no style_id is supplied.

• Style match control
  Choose precise for closer style matching or flexible for broader interpretation.

• Multiple aspect ratios
  Generate square, portrait, landscape, and vertical image outputs.

Parameters

How to Use

1. Write your prompt — Describe the subject, scene, composition, and visual direction.
2. Add style input — Provide a matching style_id, or upload reference images to create a temporary style for this request.
3. Choose aspect ratio — Select 1:1, 4:3, 3:4, 16:9, or 9:16.
4. Set style match optional — Use precise for closer matching or flexible for broader style interpretation.
5. Submit — Generate the styled image output.

Pricing

Pricing starts at $0.0385 per request. If style reference images are provided, an additional $0.0055 is added.

aspect_ratio, style_id, and style_match do not add separate charges.

Best Use Cases

• Styled image generation — Generate images with reusable or request-specific style guidance.
• Brand asset creation — Create consistent visuals for campaigns, social media, and marketing materials.
• Reusable style workflows — Use a saved style_id to keep a consistent look across multiple generations.
• Style exploration — Upload reference images to test a style without creating a permanent style first.
• Creative production — Generate polished visuals for design, advertising, and content workflows.

Pro Tips

• Use a matching style_id when you need consistent output across multiple generations.
• Use reference images when you want to create a style for the current request only.
• Use precise when style consistency is more important.
• Use flexible when you want more creative variation.
• Keep prompts focused on the subject, composition, and visual style.
• Use 16:9 for wide layouts and 9:16 for vertical designs.

Notes

• The 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.
• Either images or style_id must be provided. Use style_id for a reusable saved style, or images to create a temporary style for the current request.

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'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "aspect_ratio": "1:1",
  "style_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-style/text-to-image" \
  -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