Over view
This is a simple workflow designed to closely reproduce the inpainting features available in WebUI. And specifically designed for use with my model, Utopian Inpainting.
Update: Changed sam2 to sam3
Old update: Added Openpose, Detail daemon, fill mask area, basic Adetailer, and more.
I realized the pure SDXL models is good as a refiner. After testing several options, Epic Realism delivered good performance with both high-resolution and low-resolution images.
Set the sampler 2 configuration to "dpmpp_2m_sde" "karras" and try adjusting the "refiner ratio" to around "0.6 to 0.8"
-Basic feauture-
Inpainting with refiner model
Inpainting full image and crop image select
Pre-resize image with scale by % and long_side resize select
Basic K-sampler and Lanpaint support
Manual mask and sam2 Auto masking select
Optional Vae and Clip selector
Postprocess Mask detailer (testing)
Upcoming Update plan: Outpainting Support, More Accurate Auto masking.
-How to use-
Resources you need:
Inpainting Model: Utopian pony inpainting or Any SDXL Inpainting model
Refiner Model: Your favorite models
Optional Clip: Illustrious_base_clip_L and Illustrious_Base_CLIP_G
Settings:
[Optional loader]
Select if you want to use Clip or VAE instead.
[Inpaint mode]
-Normal
Normal Inpainting.
-Refiner
Inpainting with refiner.
-Lanpaint
Use Lanpaint, The output results are different from Ksampler. It is difficult to say which is better.
[Resize method]
-percentage
Pre-resize image with scaled %.
-Long side
Pre-resize the image based on the long edge.
[Inpaint area]
full
Inpaint with pre-resized image size.
-crop
Crop pre-resized image according to mask.
crop target size
Scales the size of the crop from the image.
Cropped_image = Original_img * Pre-resize * crop_target_sizecrop mask extend
How much of the image to crop from the mask.
[Mask method]
-Manual
Right-click on the load image and select "Open in mask editor" to manually draw a mask.
-Auto
A mask is generated automatically; use the mask prompt to define the area you want to mask.
[Postprocess]
-After Detailer
Enhance the Inpainted image by running a mild inpainting pass after finished.
-with refiner
Also use refiner model when Detailer. (With refiner doesn’t perform well at the moment)
Detailer denoise
recommended 0.3 ~ 0.5Detailer zoom
Set how much of the surrounding area is included when cropping.
The higher the value, the more area around the mask will be cropped.
Description
test
FAQ
Comments (5)
Huh, this looks a lot more complex than what I assumed is required for such a straight forward model, but I will try this workflow, thanks!
Webui looks simple, but it actually does a lot of things. Even with this complex, not all webui functions have been ported yet.
That's certainly true, I have been experimenting with different inpainting methods on comfyui for a long time now and I noticed even when using theocratically similar method such as using the fooocus inpaint patch vs using webui forge, the effect is not as good as how webui/fooocus implemented it. Shame that the creators of those UIs have bigger things to worry about and we never get any update.
@habibing Finally got around to try this workflow, when I run the workflow it very soon stops from an "Output will be ignored" error, it seems like the two save image(i replaced with preview image) nodes are missing image input from your workflow.
"Output will be ignored" is a normal response when there is an unused mode, and is not an error that will stop the generation. If the settings are correct, generation will start after that log. If it stops, please check whether you are using a refiner mode without selecting a refiner model, or whether you have enabled clips or vae without loading them.
Or there may be a setting on the comfyui side that stops generation even with minor errors. In the next version, I will improve it to mute unused save image nodes.