Private AI

Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Search
 
 
 
 
All conversations

Create

Chat
Studio

Explore

Models
Pricing
AI Apps
Blog

Library

Gallery
Workspace
Usage & billing
API
Suggestions and bugs
Use cases

|

Terms

|

Privacy

|

Refunds
Usage & billing
Teams
Referrals
Presets
Settings
FAQPress & mediaBrand assetsBenchmarksNano RPCEarn crypto
  1. Models
  2. Image

WAN 2.6 Image Edit

Try Model

WAN 2.6 Image Edit is Alibaba's image-to-image editing model for making prompt-driven changes to existing images. Upload reference images, describe your edit in natural language, and get updated images while preserving the overall structure and identity of the original. Great for changing clothing, colors, materials, backgrounds, adding/removing objects, or applying style adjustments.

Added Dec 22, 2025

Details

Approx. Price
$0.035 per image
Model type
image-to-image

Settings

Generation controls available for this model.

Images Per Run

Up to 3

Output images

Input Images

Up to 3

Reference/edit images accepted • Route max 30 MB

Output Sizes

Auto

Number of Images

Default

1

Prompt Expansion

Toggle

Default

No

Enable AI-powered prompt enhancement.

Resolution

Default

auto

Options (1)

auto (Matches uploaded image)

Seed

Number

Default

-1

Control reproducibility (-1 for random).

Benchmarks

No public benchmark scores for this model yet.

Examples

Loading examples…

Related image models

Compare WAN 2.6 Image Edit with similar models from the same provider or model family.

Qwen Edit Uncensored

qwen-edit-uncensored

Uncensored Qwen image editing. Edit an image or combine up to three references with a text instruction. Supports native 1K output, flexible aspect ratios, and PNG, JPEG or WebP format. Requires an input image; edit prompts can contain up to 1,500 characters.

Qwen Image 2.1 Edit

wavespeed-ai/qwen-image-2.1/edit

Edit from up to ten reference images with natural-language instructions, strong subject preservation, flexible framing, and native output up to 2K.

Qwen Image 2.1 Edit LoRA

wavespeed-ai/qwen-image-2.1/edit-lora

Edit from up to ten references while applying up to three custom LoRAs for precise identity, product, or style control at up to 2K.

WAN 2.7 Image

wan2.7-image

WAN 2.7 image model for text-to-image and multi-image editing. Supports prompt-driven generation, up to 9 reference images, and up to 2K output.

WAN 2.7 Image Pro

wan2.7-image-pro

Higher-end WAN 2.7 image model for text-to-image and multi-image editing workflows. Supports up to 9 reference images, 4K text-to-image output, and 2K edit output.

Qwen Image Max Edit

qwen-image-max-edit

Qwen Image Max Edit applies prompt-driven edits to 1-6 reference images, preserving structure while supporting Chinese and English prompts.