Unifically LogoUnificAlly
Model logo

Wan 2.6 Image API

Text to ImageImage to Image

AI image generation with style transfer and editing using 1-4 reference images.

Click or drag & dropPNG, JPG, WEBP, GIF · Max 100MB
Prompt Extend
Smart prompt rewriting (default on)
Output

Your generated image will appear here

Features

What Wan 2.6 Image API offers

Text-to-image plus image-guided editing and style work
Up to four reference images (optional)
Negative prompts up to the documented length limit
Prompt extend (smart rewriting), default on in the playground
Seven aspect ratio presets
Optional seed for reproducibility

Use cases

Built for

Primary

Catalog refreshes: restyle shots with a small set of references

#2

Concept art: combine references while steering with the main prompt

#3

Creative QA: fix seeds and negatives to lock a look across iterations

#4

Editorial: match brand color and lighting from reference stills

FAQ

About Wan 2.6 Image API

Between zero and four images. With no images you get plain text-to-image; with images you steer edits or style transfer style runs.

No. It covers generation from text alone and workflows that use references for editing or style alignment.

Negatives list content to suppress; prompt extend rewrites the main prompt for clarity. They work together: exclusions stay explicit while the positive prompt can be expanded.