Model Information

Display Name: Qwen Image

API Model ID: qwen/qwen-image

Category: Text To Image

Description: Qwen Image is Alibaba's flagship 20B parameter Multimodal Diffusion Transformer for photorealistic image generation and editing. Notable for dramatically reducing the "AI-generated" look in human portraits, with improved skin texture, hair detail, and natural expressions. **Key Features:** - 20B parameter MMDiT architecture - Superior text rendering (Chinese + English) with accurate character placement - Multi-image fusion and semantic editing modes - Identity-preserving edits across people, products and characters - Support for 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3 aspect ratios **Capabilities:** - Text-to-image generation - Image-to-image editing (1-3 input images) - Inline text editing within images - Style preservation across lighting/palette changes - Multi-person identity consistency **Best For:** - Photorealistic portraits and product mockups - Marketing content with embedded text in CN/EN - Iterative design workflows requiring identity preservation - E-commerce product visualization **Technical Specs:** - Architecture: 20B MMDiT (Multimodal Diffusion Transformer) - Max resolution: 1536×1536 (provider-dependent) - Input images for edit: 1-3 - License: Apache 2.0

How to Use This Model

To use Qwen Image via the HInow.ai API, use the model ID: qwen/qwen-image

API Request Example (Chat/Text)

POST https://api.hinow.ai/v1/chat/completions
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

{
  "model": "qwen/qwen-image",
  "messages": [
    {"role": "user", "content": "Your message here"}
  ]
}
              

API Request Example (Image Generation)

POST https://api.hinow.ai/v1/images
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

{
  "model": "qwen/qwen-image",
  "prompt": "Your image description here"
}
              

Pricing

• total: $0.05

Available Parameters

• aspect_ratio: Output aspect ratio. All 9 canonical ratios are accepted; if the upstream provider does not natively support a given ratio, the system maps to the closest one. (Options: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9, 9:21)
• output_format: Output image format. (Options: jpeg, png, webp)
• num_images: Number of images to generate (text-to-image only). (Options: 1, 2, 3, 4)
• seed: Reproducibility seed. -1 for random.

Quick Reference

To use this model, set: "model": "qwen/qwen-image"

Featured: No

Documentation: https://hinow.ai/models/qwen/qwen-image

API Endpoint: https://api.hinow.ai/v1