ModelsLab/Qwen
A 20-billion-parameter multimodal diffusion transformer model excelling in complex multilingual text rendering, precise image generation, and advanced editing like style transfer, object manipulation, and pose adjustment with strong semantic and visual fidelity.
API Endpoint URL
Base URL for all API requests to this endpoint.
https://modelslab.com/api/v6/images/img2img
API Authentication
Authentication requires a valid API key included in the request. Generate and manage your API keys from your developer dashboard. Include the key in the key parameter for all API requests.
Integration Examples
Production-ready code samples for API integration
{"model_id": "qwen","prompt": "A backlit acrylic painting of a determined head tilt portrait, featuring a Korean model with neon fantasy, her silhouette glowing against a stark white canvas. Iridescent pastel hues shimmer across her features, blending with vivid colors in a dark, moody atmosphere. minimal brush strokes . The interplay of light and shadow enhances the ethereal glow, giving the piece a dreamlike yet resolute presence, where softness meets strength in a mesmerizing contrast.((1980 jungle themed)The composition employs a double exposure technique, merging the organic floral elements with the human profile in a psychedelic style, with each flower petal and stem defined by delicate lines of light that appear to float and intertwine in the dark space. Digital art with glowing neon elements against black background using precise linework and double exposure techniques.","init_image": "https://assets.modelslab.com/generations/189093a8-a535-4aab-90ee-15ca8bf34e10.jpg","width": "1024","height": "1024","num_inference_steps": "8","strength": "0.5","key": "YOUR_API_KEY"}
SDKs
Official SDKs
Production-ready SDKs and client libraries for all major programming languages
API Parameters
Technical specifications for API request parameters.
| Field Name | Parameter | Technical Description |
|---|---|---|
| model_id | model_id | Model to use for generation |
| prompt | prompt | Enter the prompt for what change you wanted to make in the given image |
| Reference Image | init_image | Please upload the reference image you want to edit. |
| width | width | width of the image |
| height | height | Height of the Image |
| num_inference_steps | num_inference_steps | The number of denoising steps. Values 8. |
| strength | strength | Strength mean how closely it resemble the init image 1 mean closer to referance image 0.1 mean more freedom and creaytivity we leave to AI |