This is a very simple ComfyUI beginner friendly WAN VACE Cleaner & Tweaker workflow that will work with a single WAN VACE GGUF model to cleanup and tweak your existing image (this is good for text, logo, watermark, artifacts etc. object removal, where regular inpainting & outpainting workflows are good for adding or editing stuffs. With some modifications of this workflow you can use it to remove objects from videos too. If you need other other methods of inpainting / outpaint / editing you can find them in my CivitAI profile too ). You need a Hugging Face account to download your necessary WAN VACE model 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, SD 3.5, HiDream, QWEN Image and Flux.
How to use this -
#1. Just select your desired WAN VACE GGUF model first and then load
#2. then load your masked image on "Load Masked Image" (if you want to use it with ComfyUI's Mask Editor you can load your original image for masking here too)
#3. now can adjust output resolution settings (defaults are good for portraits)
#4. after this you can go to "Cleanup Parameter" write your positive and negative prompts for output. (defaults are good for most cases)
#5. finally press the run button to generate. That's it..
** You can also load your original unmasked image to view and compare it with cleaned & tweaked output on an optional viewing pane.
Enjoy!
### To use this workflow you need to log into huggingface and download necessary files from there (I also included a text file on the archive that has the workflow file, in which you will find even more links for essential downloads for my other workflows) -
# Download Link for WAN VACE Checkpoint
https://huggingface.co/QuantStack/Wan2.1_14B_VACE-GGUF/resolve/main/Wan2.1_14B_VACE-Q3_K_S.gguf
# Download Link for WAN Encoder
# Download Link for WAN VAE