모델 목록으로 돌아가기
라이브 APIQwen Image

Qwen Image 3

qwen-image-3

High-fidelity text-to-image and image-to-image generation with strong typography, layout, and multilingual prompt following.

모델 개요
엔드포인트
/api/v1/images/generations
크레딧 비용
10 credits / image
일반적인 처리 시간
20-60 sec
입력 및 출력
Text, up to 3 images → PNG or JPEG

기능

  • 1K and 2K output
  • Text and image conditioning
  • Prompt expansion
  • Deterministic seeds

요청 파라미터

파라미터유형요구 여부설명
modelstring필수Model identifier. 기본값: qwen-image-3
promptstring필수Generation prompt, up to 800 characters.
image_urlsstring[]선택Up to three public image URLs for image-to-image generation.
aspect_ratiostring선택Output aspect ratio. 기본값: 16:9
resolution1K | 2K선택Output resolution tier. 기본값: 1K
output_formatpng | jpeg선택Generated file format. 기본값: png
seedinteger선택Integer from 0 to 2147483647. 기본값: 1

요청 예시

curl https://qwenapi.org/api/v1/images/generations \
  -H "Authorization: Bearer $QWEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "qwen-image-3",
  "prompt": "Editorial product photo of a translucent blue speaker on a steel desk, soft morning light",
  "aspect_ratio": "16:9",
  "resolution": "1K",
  "output_format": "png"
}'

생성 엔드포인트는 비동기입니다. 동일한 Bearer 키로 GET /api/v1/tasks/를 폴링하세요.