Wan 2.1 Text To Image API Documentation

Wan 2.1 Text To Image API Documentation

Playground

Wan 2.1 Text-to-Image delivers ultra-realistic photographic images by adapting the Wan 2.1 video model for SOTA visual fidelity. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Wan 2.1 is part of the Wan 2.1 foundation model suite, an advanced AI system developed to redefine video and image generation. This model focuses on text-to-image synthesis — transforming detailed written prompts into vivid, high-resolution visuals with cinematic precision.

🌟 Key Features

• 🎨 SOTA Image Quality Built on Wan 2.1’s next-generation video foundation, this model produces exceptional still-frame quality with realistic lighting, texture, and depth.

• 🧠 Multilingual Understanding Supports both Chinese and English prompts, ensuring accurate and context-rich image generation across languages.

• ⚙️ Fine Control with Parameters Adjustable inputs such as strength, width, and height provide creators with direct control over composition and style.

• 🪄 Powerful Visual Consistency Based on Wan-VAE, enabling coherent detail, color fidelity, and stylistic alignment across resolutions.

• 💰 Lightweight and Efficient High-quality generation at a base cost of just $0.02 per image, ideal for scalable creative workflows.

⚙️ Parameters

💡 Example Prompt

> Envision an ethereal and highly decorative portrait of an androgynous Elven Monarch, seated upon a throne carved from living iridescent wood within a moonlit glade. Intricate Art Nouveau details, luminous textures, soft-focus background, cinematic lighting.

💰 Pricing

🎯 Use Cases

• Concept Art & Illustration — Generate fantasy, sci-fi, or cinematic character art.
• Visual Design & Branding — Create unique imagery for marketing, web, or product visuals.
• Research & Visualization — Produce clear, detailed concept visuals from descriptive text.
• Previsualization — Generate cinematic stills for film, animation, or game design workflows.

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",
  "strength": 0.6,
  "size": "1024*1024",
  "seed": -1,
  "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/wavespeed-ai/wan-2.1/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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(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