Wan2.7 Image
Generate or edit images with Wan2.7 Image. Supports text-to-image, image editing, and sequential image generation.
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
Model ID. wan2.7-image-pro text-to-image supports 4K output; wan2.7-image generates faster.
wan2.7-image-pro, wan2.7-image "wan2.7-image-pro"
Image description. Chinese and English are supported. Maximum 5000 characters.
"A flower shop with delicate windows, a beautiful wooden door, and flowers on display"
Input image for editing — URL (HTTP/HTTPS) or Base64 data URI(data:{MIME};base64,{data})。
Supported formats: JPEG, JPG, PNG (no alpha channel), BMP, WEBP. Max 20 MB, width/height 240–8000 px, aspect ratio 1:8–8:1. Up to 9 images.
"https://example.com/input.jpg"
Number of images to generate.
- Sequential mode off (
enable_sequential: "false):1–4, default1." - Sequential mode on (
enable_sequential: "true):1–12, default"12. The actual count is decided by the model.
1 <= x <= 121
Output resolution. Two formats are supported (do not mix them):
- Presets:
1K(1024×1024),2K(2048×2048, default),4K(4096×4096, only wan2.7-image-pro text-to-image). - Custom pixels:
{width}x{height}— text-to-image total pixels 768×768–4096×4096; other modes up to 2048×2048, aspect ratio 1:8–8:1.
"2K"
Enable sequential image output. When true, n is the maximum count and the model decides the actual number.
Enable thinking mode to improve reasoning and image quality. Only takes effect when there is no image input and sequential mode is off.
Whether to add a watermark to the bottom-right corner of the generated image.
Random seed, range [0, 2147483647]. The same seed yields similar results but does not guarantee an exact match.
0 <= x <= 2147483647Return an image URL or Base64 encoding.
url, b64_json "url"