This is a very simple ComfyUI beginner friendly QWEN Image Edit Plus (2511) workflow that will work with with very simple text editing instructions in natural language to edit your desired image. This is an updated and extended version of my older QWEN Image Edit Workflow that you can find in my CivitAI Profile. You need a Hugging Face account to download your necessary QWEN Image files (Details are mentioned below). Make sure you install GGUF addon for ComfyUI using ComfyUI manager and place the correct files in correct places. Also check out my other workflows for SD 1.5 + SDXL 1.0, HiDream, WAN 2.1, WAN 2.2, MagicWAN v2, Z-Image Turbo, Chroma, AuraFlow, Ovis Image, Flux & others.
How to use this -
#1. Just select your desired QWEN Image models first
#2. now select your image(s) on "Upload Image(s) for Editing" (You can select upto 3 images, select atleast one)
#3. on next step enter your image editing instructions
#4. then select how many images you want (Change the number besides the "Run" button)
#5. after this select image sampling methods, CFG, steps etc. settings
#5. finally press the run button to generate. That's it..
** You can also customize output image dimensions on "(( Optional )) Fix Output Image Size" section of the workflow (Read the notes on that section of the workflow)
## QWEN Image Edit Models
=========================================================================================================================
### Download Links for QWEN Image Edit Plus (2511) Checkpoint
https://huggingface.co/unsloth/Qwen-Image-Edit-2511-GGUF/resolve/main/qwen-image-edit-2511-Q2_K.gguf
### Download Links for QWEN Image Encoders
### Download Links for QWEN Image VAE
https://huggingface.co/QuantStack/Qwen-Image-Edit-GGUF/resolve/main/VAE/Qwen_Image-VAE.safetensors
=========================================================================================================================
### This workflow also uses the following QWEN Image LORA from CivitAI -
Qwen Lightning 8-Step Lora v2
https://civarchive.com/models/2046883/qwen-lightning-8-step-loras-re-ranked
Description
FAQ
Comments (2)
While it's nice you summarized the settings and included the original source images, without information on which quantitized version you used or the random seed, it's useless. The default workflow used Q2_K. and the garbage it spewed out with all your stated settings looks nothing like your output - hell it doesn't look like anything at all. Have uploaded the image.
CFG 1.2, Sampler euler and 12 steps... I used an AMD 8 GB VRAM GPU on Linux.. if you have a better GPU use higher Q model or full model.. also check your CUDA (for Nvidia) or ROCm (for AMD Radeon) packages..