跳到主要内容
Alibaba检查中

Wan 2.5 Preview / Image to Image

wan-2-5-preview-image-to-image

图生图输出: 图像输入: 文本 + 图像
正在加载价格…
官方原价 · 未验证

模型能力

Edit images with text instructions.

Image editing · 1–4 images

输入参数

仅列出此模型接受的字段。必填字段必须提供。

字段类型必填默认值可选值与约束
prompt
string必填—

Positive prompt describing the desired image editing operation.

≤ 2000 chars

imageUrls
string[]必填—

Input images (1-3)

≤ 3 items · HTTPS image URL or media:<uuid>

negativePrompt
string可选—

Negative prompt describing unwanted content.

≤ 500 chars

size
string可选—

Output image resolution.Output image resolution. If size is not specified, the system will generate an image with a total pixel size of 1280×1280 by default, and maintain the aspect ratio (approximate value) according to the following rules: For single-image input: the aspect ratio is consistent with the input image. For multi-image input: the aspect ratio is consistent with the last input image.

可选值: "1280*1280", "1024*1024", "800*1200", "1200*800", "960*1280", "1280*960", "720*1280", "1280*720", "1344*576"

n
integer必填1

Number of images to generate (1-4), directly affects pricing.

1–4

promptExtend
boolean可选true

Enable intelligent prompt extension.

seed
integer可选—

Random seed for reproducible generation.

-1–2147483647

限制与行为

  • 仅支持异步:先提交任务,再轮询结果。
  • prompt: ≤ 2000 chars
  • imageUrls: ≤ 3 items
  • negativePrompt: ≤ 500 chars
  • n: 1–4
  • seed: -1–2147483647
  • 媒体输入接受公开 HTTPS URL,或 POST /api/v1/media 返回的 media:<uuid> 引用。