The latest and highest-quality multi-image composition model, delivering superior subject fusion, scene replacement, and style transfer with up to 4 subject images.
API Key authentication. Format: Bearer YOUR_API_KEY.
Note: All parameters are optional, but at least one of prompt, subject_image_list, scene_image, or style_image should be provided. This model does NOT support: negative_prompt, resolution, image, image_reference, image_fidelity, or human_fidelity parameters.
Image description text, supports Chinese and English. Optional but recommended for better results
1 - 2500"Family gathering in an elegant dining room"
List of subject reference images. Each element must contain a 'subject_image' field with image URL or Base64 data. Minimum 1 image, maximum 4 images
1 - 4 elements[
{
"subject_image": "https://example.com/person1.jpg"
},
{
"subject_image": "https://example.com/person2.jpg"
},
{
"subject_image": "https://example.com/person3.jpg"
}
]Scene reference image (Base64 encoded or URL). Used for scene replacement. Supported formats: .jpg, .jpeg, .png. Maximum size: 10MB
1"https://example.com/dining-room.jpg"
Style reference image (Base64 encoded or URL). Used for style transfer. Supported formats: .jpg, .jpeg, .png. Maximum size: 10MB
1"https://example.com/elegant-style.jpg"
Image aspect ratio
16:9, 9:16, 1:1, 4:3, 3:4, 3:2, 2:3, 21:9 "3:2"
Number of images to generate per request
1 <= x <= 91