Qwen Image Edit TL5

Qwen-Image-Edit is Alibaba's open-weight image-to-image editing model, built on the 20B-parameter Qwen-Image diffusion transformer. It takes an input image and a text instruction and produces a revised image, combining Qwen2.5-VL for semantic understanding with a VAE encoder for appearance control. The model supports localized edits such as adding, removing, or changing objects while preserving unaffected regions, as well as broader transformations including style transfer, object rotation, and character variations. A standout capability is editing text already embedded in images: it can add, replace, or delete English and Chinese words while aiming to retain their font, size, and styling. Applications include revising posters and ads, updating signage, adapting illustrations, and iterating on product visuals. Released under Apache 2.0.

INPUT

Image to Image

Seed

Width

Height

Sampling Parameters

Sampling Steps

Output Quality

True Classifier-Free-Guidance (CFG) Scale

Progress Images


Progress

Console Output

Image Preview

Disclaimer: The content generated with this demonstration platform ("playground") is generated with AI. AI can make mistakes. The services of AKI.IO are offered exclusively for business and professional use. Creating a company account is required for commercial use. The content provided on this playground platform is for informational and educational purposes only, and its use is at your own risk. We do not assume any liability for the accuracy, completeness, or usefulness of the information provided. Viewer discretion is advised as the content may contain explicit material. This playground platform is intended for research and demonstration purposes only and should not be used as a substitute for professional advice. By using or accessing this platform, you agree to these terms and conditions.