Hunyuan Image 3 API Documentation

Hunyuan Image 3 API Documentation

Playground

HunyuanImage-3.0: An AR multimodal model unifying understanding & generation. Its Text-To-Image module rivals closed-source leaders. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Harness the cutting-edge technology of Hunyuan Image 3.0 to transform your written ideas into compelling visual content. This advanced model ensures visuals that not only align with your narrative but also enhance its emotional and conceptual appeal.

What is Hunyuan Image 3.0?

Hunyuan Image 3.0 is a state-of-the-art text-to-image generation model. By simply providing a written prompt, you can create high-quality images that capture the essence of your story, resonate emotionally, and elevate your creative output.

Why it looks great

• Prompt-driven generation: translates text descriptions into rich, detailed visuals.
• Emotional resonance: enhances narrative impact by aligning visuals with tone and mood.
• Flexible sizing: supports custom width and height up to large resolutions.
• Style diversity: accommodates multiple visual aesthetics, from realism to artistic styles.
• Reproducibility: use the seed parameter for consistent, repeatable results.
• Format choice: export in JPEG and PNG for easy integration.

Limits and Performance

• Max resolution per job: up to 2048 × 2048 pixels
• Processing speed: ~5–10 seconds per image (varies by complexity and queue load)
• Input prompt: supports detailed, multi-line descriptions

Pricing

Every image just $0.1!!!

How to Use

1. Write a prompt describing the image you want.
2. Adjust size (width & height).
3. Set a seed for reproducibility.
4. Choose output_format.
5. Submit the job and download the generated image.

Pro tips for best quality

• Be descriptive in your prompt — include mood, lighting, and style.
• Portraits with clear attributes (face, pose, background) yield sharper results.
• Fix the seed if you want consistent outputs across runs.
• Use custom sizes for tailored content (e.g., vertical posters or wide banners).

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",
  "size": "1024*1024",
  "seed": -1
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/hunyuan-image-3" \
  -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