Tongyi Wanxiang Wan2 Image-to-Image
Image Generation - Wan2
Wan2 Image-to-Image
Use Tongyi Wanxiang Wan2 image-to-image model (wan2.5-i2i-preview) for image editing and multi-image fusion
POST
Tongyi Wanxiang Wan2 Image-to-Image
Edit and fuse images using Alibaba Cloud’s Tongyi Wanxiang Wan2.5 model. Key Features:Documentation Index
Fetch the complete documentation index at: https://docs.sinancode.com/llms.txt
Use this file to discover all available pages before exploring further.
- Subject Consistency - Image editing based on subject consistency
- Multi-Image Fusion - Support multiple image inputs for creative fusion
- One-Sentence Editing - Complete complex edits through simple text instructions
- Native Chinese - Describe editing requirements directly in Chinese
Authorizations
Please use your API Token for authentication
Body
application/json
Task parameters
Input image URL list (required, 1-3 images) Supports public URLs (HTTP/HTTPS) or Base64 encoding
Required array length:
1 - 3 elementsPositive prompt (required, max 2000 characters)
Required string length:
1 - 2000Negative prompt (optional, max 500 characters)
Maximum string length:
500Random seed (optional, range 0-2147483647)
Required range:
0 <= x <= 2147483647Output resolution (optional, default 12801280) Total pixels [768768, 1280*1280], aspect ratio [1:4, 4:1]
Response
OK
Task ID
Example:
"01234567-89ab-cdef-0123-456789abcdef"