AI Virtual Outfit Tryon API Documentation

AI Virtual Outfit Tryon API Documentation

Playground

AI Virtual Outfit Try-On generates videos of a person wearing uploaded clothing. Upload a portrait and clothing images, add an optional prompt, and get a try-on video. Ready-to-use REST inference API, no coldstarts, affordable pricing.

Features

AI Virtual Outfit Try-On generates realistic videos of you wearing any outfit. Upload a portrait and clothing images — AI composites the look onto your body and animates it into a natural, wearable video. See how any outfit looks on you before buying, without a fitting room.

Why Choose This?

• Realistic virtual try-on video Goes beyond static image try-on — generates an animated video showing the outfit in natural motion on your body.

• Multi-garment support Upload up to 8 clothing images per request to try on complete outfits with multiple pieces.

• Prompt-guided scene control Optionally describe the desired video scene, background, or mood to customize the visual context of the try-on.

• Flexible duration Generate clips from 5 to 15 seconds to capture enough movement to evaluate the outfit.

Parameters

How to Use

1. Upload your portrait — a clear, full-body or upper-body photo works best.
2. Upload clothing images — provide image URLs for each garment you want to try on (up to 8).
3. Write a prompt (optional) — describe the scene, setting, or vibe you want for the video.
4. Set duration — choose between 5 and 15 seconds.
5. Submit — generate, preview, and download your try-on video.

Pricing

Billing Rules

• Rate: $0.039 per second
• Duration range: 5–15 seconds

Best Use Cases

• E-commerce & fashion retail — Let customers virtually try on outfits before purchasing.
• Personal styling — See how multiple garments look together as a complete outfit.
• Social media content — Create fashion try-on videos for Instagram and TikTok.
• Wardrobe planning — Preview new clothing against your actual appearance before buying.

Pro Tips

• Use a clear, well-lit portrait with a neutral background for the most accurate outfit compositing.
• Full-body or upper-body photos give the model more context for realistic garment placement.
• Upload clean, front-facing clothing images on a plain background for the cleanest try-on results.
• Use the prompt to set the scene — for example, “walking in a city street, natural daylight” for a lifestyle feel.

Notes

• Both image and clothes_images are required fields.
• Up to 8 clothing images can be provided per request.
• Ensure all image URLs are publicly accessible if using links rather than direct uploads.
• Please ensure your content complies with WaveSpeed AI’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",
  "clothes_images": [
    "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
  ],
  "duration": 5
}
JSON
)

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