Kuaishou’s first-generation AI image model using a diffusion transformer architecture, capable of generating 1K-resolution images with strong prompt adherence and realistic detail.
API Key authentication. Format: Bearer YOUR_API_KEY.
Image description text, supports Chinese and English
1 - 2500"Transform into a watercolor painting style"
Reference image (Base64 encoded or URL). Supported formats: .jpg, .jpeg, .png. Maximum size: 10MB
1"https://example.com/reference.jpg"
Image facial reference strength. Higher values mean stronger reference. Range: 0.0-1.0
0 <= x <= 10.7
Image aspect ratio
16:9, 9:16, 1:1, 4:3, 3:4, 3:2, 2:3, 21:9 "16:9"
Image resolution. I2I only supports 1K
1k "1k"
Number of images to generate per request
1 <= x <= 91