Novita

qwen-image-txt2img

Qwen/Qwen-image-txt2img
Context

2K

Input

text

Output

image

Tool calling

Not listed

About this model

Qwen-Image-Txt2Img is a 14B-parameter diffusion model specialized in high-quality text-to-image generation with enhanced prompt understanding and stylistic versatility. Part of the Qwen multimodal family, it features advanced composition control, style adaptation, and detail preservation across diverse visual domains.

Compare Image Models

Input modalities

text

Accepted as model input

Providers

Available routing options for this model through OneInfer.

Novita
Available

Image generation

$0.200 / image

Routing

OneInfer optimized

Pricing

Current OneInfer pricing for this model.

UsagePrice
Image generationstandard · 1024*1024$0.200 / image

Performance

Published evaluation results associated with this model.

Image Quality

FID-30K12.8
CLIP Score33.2
Inception Score192.4
Precision87.6
Recall85.3

Prompt Understanding

Attribute Binding89.4
Spatial Reasoning84.7
Complex Prompt Accuracy86.9
Style Adaptation91.2

Domain Specialization

Photorealistic90.8
Artistic Styles92.4
Concept Art88.9
Technical Illustration85.7
Product Visualization87.3

API example

Refer Documentation
curl -X POST https://api.oneinfer.ai/v1/ula/generate-image \
  -H "Authorization: Bearer YOUR_JWT_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
  "provider": "novita",
  "model": "Qwen/Qwen-image-txt2img",
  "messages": [
    {
      "role": "user",
      "content": "A futuristic city skyline at dusk"
    }
  ],
  "number": 1,
  "size": "1024*1024",
  "quality": "standard"
}'