This is a very simple ComfyUI beginner friendly QWEN Image Edit workflow that will work with with very simple text editing instructions in natural language to build a consistent character dataset from your desired reference image so that you can build a character LORA later. It does not have any lengthy process that you may have been seen for other consistent character dataset builder you may have seen using SDXL or Flux. QWEN Image Edit is very good on it's own to conserve and reuse character details from reference image to provide output ( challenging part is to figure out your precise sampler and scheduler ). 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 and Flux.
How to use this -
#1. Just select your desired QWEN Image models first
#2. now select your input character reference image and set the character's first and last name
#3. on next step enter your image editing instructions - Batch character prompts like "Make this person" followed by other details. Also add common negative filters or use the existing one provided.
#4. after this select image sampling methods, CFG, steps etc. settings (this part is tricky, if you want you can just have the values as it is)
#5. finally press the run button to generate. That's it..
** I have given two reference images (1 SFW and 1 NSFW, both with their character builder prompts you can try out or modify, 60 for each) for you already in the zip file containing this workflow along with a text file with links to any downloads you may need to do for my other workflows
Enjoy!
## QWEN Image Edit Models
=========================================================================================================================
### Download Links for QWEN Image Edit Checkpoint
https://huggingface.co/QuantStack/Qwen-Image-Edit-GGUF/resolve/main/Qwen_Image_Edit-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 LORAs from CivitAI -
Qwen Lightning LoRA
https://civarchive.com/models/1854805?modelVersionId=2099128
Reality Simulator
https://civarchive.com/models/1886273?modelVersionId=2135085
Description
FAQ
Comments (5)
It is slowing down in random nodes. Do you have any particular settings for optimization?
Check these things - #1. Maybe see if I or you accidentally added any unused nodes and remove them #2. Close unused processes #3. Add any RAM cleaning node #4. Try smaller Image dimensions #5. Use basic samplers and schedulers (euler, simple for example) or try another combo - each hardware loves different setups (most trickiest part)
Also check the Flux Kontext version of this workflow on my profile. I very recently uploaded that version.
Where are these stored? I tried to edit the path in ComfyUI Image Saver node but it was greyed out/locked. Otherwise, super resource. TY!
Stored inside a subfolder under ComfyUI folder, depending on your system it may be named output or Text2Img or something similar or if you have explicitly set another path to store images outside of ComfyUI look for the subfolder inside that folder. You can change the file name with "File Name Prefix" input inside the workflow, because I wanted to ensure the both the text file and image(s) have the matching name and timestamp I redirected the file name creations to other input fields. ( A little correction this one does not save the .txt file with timestamp, my other newer workflows do that )