Workflow Overview
This is a dual editing workflow for Qwen Edit 2511 and Flux Klein 9B; however, both model groups are self-contained. You can safely delete the entire group of whichever model you don't use without breaking the workflow. The remaining model group will work independently without any additional changes needed.
Additionally, the workflow can function as a standard text-to-image workflow.
Why a dual workflow?
Flux Klein is my preferred editing model and I use it all the time; however, I like to have the Qwen model as a backup when Klein struggles with certain edits, and vice versa.
Some personal notes:
Qwen Edit has better character consistency, but it loses skin details; Flux Klein can sometimes affect character consistency, but it preserves details better.
Two variants are provided in the zip file:
A standard edit workflow (EditStandard.json)
The same workflow as the first one, but with the extra feature of saving images with metadata compatible with CivitAI (EditCivitAI.json)
Main features
Standard text-to-image generation
Edit images guided by a text prompt, using up to three reference source images
Isolate and mask specific objects or subjects via SAM3 segmentation or hand-drawn masks (or both) to avoid pixel drifting
Camera angle control (especially useful with Qwen + multi-angle LoRA)
Basic pose transfer
Example use cases
Virtual try-on / outfit transfer

Object / subject removal

Background / scene change

Character swap / face swap

Inpainting

Multi-angle view

Pose change

Character sheet

Scene composition

Image fixing

Image style change

Detailed instructions are contained in the workflow itself:
Red nodes are instructions and useful notes.
Yellow nodes are configurable elements you can adjust to your needs.

Description
First version release
FAQ
Comments (7)
Interesting, but I'm not sure if I got the concept right.. this is meant to use either Klein or QIE, not a mix of both? Meaning, it doesn't edit with qie and then sends the image to Klein to fix the skin? It doesn't work like that?
Correct, you use one model or the other, depending on your needs.
I changed the title of the post to more accurately describe what the workflow does.
Does this workflow address pixelshift when Qwen resizes the initial image?
If you use the mask editing feature, yes
Nice Workflow thnk :)
Thanks ;)













