Introduction
Qwen-Image-Edit is an image editing version of Qwen-Image. It is further trained based on the 20B model and supports precise text editing and dual semantic/appearance editing capabilities.
Qwen-Image-Edit is an image editing version of Qwen-Image. It is further trained based on the 20B Qwen-Image model and successfully extends Qwen-Image's unique text rendering capabilities to editing tasks, achieving precise text editing. Furthermore, Qwen-Image-Edit feeds the input image simultaneously into the Qwen2.5-VL (for visual semantic control) and the VAE Encoder (for visual appearance control), achieving dual semantic and appearance editing capabilities.
Features include:
- Precise Text Editing: Qwen-Image-Edit supports bilingual (Chinese and English) text editing, allowing you to directly add, delete, and modify text within an image while preserving the original text size, font, and style.
- Dual Semantic/Appearance Editing: Qwen-Image-Edit supports not only low-level visual appearance editing (such as style transfer, addition, deletion, and modification), but also advanced visual semantic editing (such as IP creation and object rotation).
- Strong cross-benchmark performance: Evaluations on multiple public benchmarks show that Qwen-Image-Edit achieves SOTA in editing tasks, making it a strong base model for image generation.
https://huggingface.co/Qwen/Qwen-Image
https://github.com/QwenLM/Qwen-Image
Recommended machineďźLarge-Pro
Workflow Overview
How to use this workflow
Step 1: Load Image
Step 2 : Input the Prompt
Step 3 : Get Image
