MiniMax Image-01 I2I
[Core Function] MiniMax Image-01 I2I is an image-to-image editing and variation model. [Strengths] It excels at generating new images based on a text prompt while structurally referencing one or more input images. [Best For] Highly recommended for: style transfer, generating variations of existing artwork, and structurally guided image creation. [Limitations] Do NOT use this model if you want to generate video or if you do not have a reference image. [Routing] Use this model when the user provides a reference image and a text prompt to generate a new image.
Authorizations
API Key authentication. Format: Bearer YOUR_API_KEY.
Body
Image description text, supports Chinese and English
1 - 1500"A girl in futuristic style"
Reference image URLs for image-to-image generation. Supports public HTTPS URLs or Base64 Data URLs
1 - 10 elementsImage URL or Base64 Data URL (data:image/jpeg;base64,...). Image requirements: JPG/JPEG/PNG format, <10MB, best with single front-facing portrait photo
Image aspect ratio. If both aspect_ratio and width/height are provided, aspect_ratio takes priority
1:1, 16:9, 4:3, 3:2, 2:3, 3:4, 9:16, 21:9 "1:1"
Image width in pixels (must be used with height). Must be divisible by 8. If aspect_ratio is provided, width/height will be ignored
512 <= x <= 20481024
Image height in pixels (must be used with width). Must be divisible by 8. If aspect_ratio is provided, width/height will be ignored
512 <= x <= 20481024
Random seed for reproducible results. Use the same seed with same parameters to generate identical images
x >= 042
Number of images to generate per request
1 <= x <= 91
Enable automatic prompt optimization to improve generation quality
false