Enhanced virtual try-on model that supports both single garments and top+bottom outfit combinations, delivering higher-quality results with automatic clothing type detection.
API Key authentication. Format: Bearer YOUR_API_KEY.
Note: This is an asynchronous model with typical processing time of 15-60 seconds. Generated images are valid for 30 days only - please save promptly. V1 supports single garment try-on. V1.5 (Recommended) additionally supports 'top+bottom' combination try-on with higher quality output. This model does NOT support: prompt, negative_prompt, n, aspect_ratio, resolution, image_fidelity, image_reference, or model_name parameters (model_name is automatically injected by system).
Human image for virtual try-on (URL or Base64 encoded, do not include 'data:' prefix for Base64). Supported formats: .jpg, .jpeg, .png. Maximum size: 10MB. Minimum dimensions: 300x300px. Recommend clear frontal or side view full-body photos
1"https://example.com/person.jpg"
Clothing reference image (URL or Base64 encoded, do not include 'data:' prefix for Base64). Supports product photos or white-background clothing images. V1 supports: single top, single bottom, dress. V1.5 supports: single garments OR 'top+bottom' combination (merged into one white-background image). Supported formats: .jpg, .jpeg, .png. Maximum size: 10MB. Minimum dimensions: 300x300px
1"https://example.com/tshirt.jpg"