Voltar aos modelos
API ativaQwen 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.

Visão geral do modelo
Endpoint
/api/v1/images/generations
Custo em créditos
10 credits / image
Latência típica
20-60 sec
Entrada e saída
Text, up to 3 images → PNG or JPEG

Recursos

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

Parâmetros da solicitação

ParâmetroTipoRequisitoDescrição
modelstringObrigatórioModel identifier. Padrão: qwen-image-3
promptstringObrigatórioGeneration prompt, up to 800 characters.
image_urlsstring[]OpcionalUp to three public image URLs for image-to-image generation.
aspect_ratiostringOpcionalOutput aspect ratio. Padrão: 16:9
resolution1K | 2KOpcionalOutput resolution tier. Padrão: 1K
output_formatpng | jpegOpcionalGenerated file format. Padrão: png
seedintegerOpcionalInteger from 0 to 2147483647. Padrão: 1

Exemplo de solicitação

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"
}'

O endpoint de geração é assíncrono. Consulte GET /api/v1/tasks/ com a mesma chave Bearer.