Skip to main content
Qwen-Image-Edit is the image editing version of Qwen-Image. It is further trained based on the 20B Qwen-Image model, successfully extending Qwen-Image’s unique text rendering capabilities to editing tasks, enabling precise text editing. In addition, Qwen-Image-Edit feeds the input image into both Qwen2.5-VL (for visual semantic control) and the VAE Encoder (for visual appearance control), thus achieving dual semantic and appearance editing capabilities. Model Features Features include:
  • Precise Text Editing: Qwen-Image-Edit supports bilingual (Chinese and English) text editing, allowing direct addition, deletion, and modification of text in images 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, modification, etc.) but also high-level visual semantic editing (such as IP creation, object rotation, etc.).
  • Strong Cross-Benchmark Performance: Evaluations on multiple public benchmarks show that Qwen-Image-Edit achieves SOTA in editing tasks, making it a powerful foundational model for image generation.
Official Links:

​
ComfyOrg Qwen-Image-Edit Live Stream

​
Qwen-Image-Edit ComfyUI Native Workflow Example

Make sure your ComfyUI is updated.Workflows in this guide can be found in the Workflow Templates. If you can’t find them in the template, your ComfyUI may be outdated.If nodes are missing when loading a workflow, possible reasons:
  1. You are not using the latest ComfyUI version (Nightly version)
  2. Some nodes failed to import at startup

​
Qwen Image Edit

Edit images with precise bilingual text editing and dual semantic/appearance editing capabilities using Qwen-Image-Edit’s 20B MMDiT model. Qwen-Image-Edit workflow preview

Run on Comfy Cloud

Run this workflow on Cloud GPUs with zero setup

Download Workflow

Download JSON or search “Qwen Image Edit” in Template Library
Input materials Upload this file to the matching LoadImage node:

image_qwen_image_edit_input_image.png

LoadImage node 78 · image_qwen_image_edit_input_image.png
image_qwen_image_edit_input_image.png
Example output
Input imageQwen-Image-Edit example output

​
1. Workflow File

​
2. Model Download

All models can be found at Comfy-Org/Qwen-Image_ComfyUI or Comfy-Org/Qwen-Image-Edit_ComfyUI Diffusion model LoRA Text encoder VAE Model Storage Location

​
3. Follow the Steps to Complete the Workflow

Steps Diagram
  1. Model Loading
    • Ensure the Load Diffusion Model node loads qwen_image_edit_fp8_e4m3fn.safetensors
    • Ensure the Load CLIP node loads qwen_2.5_vl_7b_fp8_scaled.safetensors
    • Ensure the Load VAE node loads qwen_image_vae.safetensors
  2. Image Loading
    • Ensure the Load Image node uploads the image to be edited
  3. Prompt Setting
    • Set the prompt in the CLIP Text Encoder node
  4. The Scale Image to Total Pixels node will scale your input image to a total of one million pixels,
    • Mainly to avoid quality loss in output images caused by oversized input images such as 2048x2048
    • If you are familiar with your input image size, you can bypass this node using Ctrl+B
  5. If you want to use the 4-step Lighting LoRA to speed up image generation, you can select the LoraLoaderModelOnly node and press Ctrl+B to enable it
  6. For the steps and cfg settings of the Ksampler node, we’ve added a note below the node where you can test the optimal parameter settings
  7. Click the Queue button, or use the shortcut Ctrl(cmd) + Enter to run the workflow