TRStart creating
Menu

Wan v2.6 Image to Image

Wan 2.6 image-to-image model.

Input

Fields marked * are required. Review the price before generating.

Text prompt describing the desired image. Supports Chinese and English. Max 2000 characters. Example: 'Generate an image using the style of image 1 and background of image 2'.

Reference images for editing (1-3 images required). Order matters: reference as 'image 1', 'image 2', 'image 3' in prompt. Resolution: 384-5000px each dimension. Max size: 10MB each. Formats: JPEG, JPG, PNG (no alpha), BMP, WEBP.

Uploading a file needs an account. Create accountJPEG, PNG, WebP · up to 25 MB

Tips and requirements

Output image size. Use presets like 'square_hd', 'landscape_16_9', 'portrait_9_16', or specify exact dimensions with ImageSize(width=1280, height=720). Total pixels must be between 768*768 and 1280*1280.

Number of images to generate (1-4). Directly affects billing cost.

Additional settings

Content to avoid in the generated image. Max 500 characters.

Enable LLM prompt optimization. Significantly improves results for simple prompts but adds 3-4 seconds processing time.

Random seed for reproducibility (0-2147483647). Same seed produces more consistent results.

Price$0.05 / image

You sign up first. Your settings are kept.

API code for this input

Complete the required fields and fix input errors to see API code.

How to use Wan v2.6 Image to Image

Getting started

Assign a clear role to each reference, such as subject, background or visual style.

Review your result

Compare subject identity, lighting compatibility and compositing edges with the references.

Inputs and settings

Provide image_urls and prompt. Official guidance supports 1–3 references; refer to their order as image 1, image 2 and image 3.

Start num_images at 1; Raywake allows up to 4. Decide whether enable_prompt_expansion should rewrite the instruction and keep seed fixed for comparisons.

We use analytics cookies. Privacy policy