The Wan Image to Image node generates an image from one or two input images and a text prompt. It transforms your input images based on the description you provide, creating a new image that maintains the aspect ratio of your original input. The output image is fixed at 1.6 megapixels regardless of the input size.

## Inputs

| Parameter | Description | Data Type | Required | Range |
| --- | --- | --- | --- | --- |
| `model` | Model to use (default: "wan2.5-i2i-preview"). | COMBO | Yes | "wan2.5-i2i-preview" |
| `image` | Single-image editing or multi-image fusion, maximum 2 images. | IMAGE | Yes | - |
| `prompt` | Prompt describing the elements and visual features. Supports English and Chinese (default: empty). | STRING | Yes | - |
| `negative_prompt` | Negative prompt describing what to avoid (default: empty). | STRING | No | - |
| `seed` | Seed to use for generation (default: 0). | INT | No | 0 to 2147483647 |
| `watermark` | Whether to add an AI-generated watermark to the result (default: false). | BOOLEAN | No | - |

**Note:** This node accepts exactly 1 or 2 input images. If you provide more than 2 images or no images at all, the node will return an error.

## Outputs

| Output Name | Description | Data Type |
| --- | --- | --- |
| `image` | The generated image based on the input images and text prompts. | IMAGE |

> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanImageToImageApi/en.md)

---
**Source fingerprint (SHA-256):** `c9afd38e3df8c080f489c4b569ea647eab5718fa78d95c65e294706344bb8067`