ComfyUI: Yolo World, Inpainting, Outpainting (Workflow Tutorial)

This tutorial focuses on Yolo World segmentation and advanced inpainting and outpainting techniques in Comfy UI. It has 7 workflows, including Yolo World instance segmentation, color grading, image processing, object/subject removal using LaMa / MAT, inpaint plus refinement, and outpainting.

------------------------

For error: "cannot import name 'packaging' from 'pkg_resources'"

The solution: Ensure that Python 3.12 or lower is installed with a comfy UI portable. Then go inside ComfyUI_windows_portable\python_embeded folder and run this command.

A comfy update installs setuptools-70.0.0, you need to downgrade for it to work.

------------------------

Inference Install (Comfy UI Portable Instructions):
Go to python_embedded folder. Right click and open terminal.

Command to Install Inference:
python -m pip install inference==0.9.13
python -m pip install inference-gpu==0.9.13

Command to Uninstall Inference:
python -m pip uninstall inference
python -m pip uninstall inference-gpu

Command to Upgrade Inference to Latest Version (non compatible with Yolo World)
python -m pip install --upgrade inference
python -m pip install --upgrade inference-gpu

------------------------

TimeStamps:

0:00 Intro.
01:01 Requirements.
03:21 Yolo World Installation.
04:32 Models, Files Download.
05:09 Yolo World, Efficient SAM.
12:50 Image Processing, Color Grading.
19:09 Fooocus Inpaint Patch.
21:56 Inpaint & Refinement.
24:17 Subject, Object Removal.
31:58 Combine Workflow.
33:17 Outpainting.

[controlaltai]

For error: "cannot import name 'packaging' from 'pkg_resources'"

The solution: Ensure that Python 3.12 or lower is installed with a comfy UI portable. Then go inside folder and run this command.

python.exe -m pip install setuptools==65.5.1

A comfy update installs setuptools-70.0.0, you need to downgrade for it to work.

[moonson]

I've seen your video before, but I though it was bit too long back then. This week when I really encountered inpaint problems, I checked your video and found it is really really helpful.

Detailed enough to help me improve inpaint and it works well. Thank you! Many subtle elements really need us to learn from you step by step. just go on, the time would be worthy.

[goodieshoes]

Amazing tutorial. I need a couple of viewings to take it all in because there is soo much usefull information!

[AIEFX]

Crazy. Time for me to put my Confy UI cape back on. Great video!!!

[runebinder]

Excellent video, want to try and use ComfyUI as much as I can but Inpaint and Outpaint has been better for me in other UI. Hopefully this will help. I've also only just realised you can zoom in and out of the canvas in Mask Editor due to watching you do it when you were fixing the edge of the mask after adding the polar bear lol.

[oliviertorres]

Results are amazing. But the learning curve to understand (and not only copy/paste) all these workflows seems a very long journey... Nevertheless, I subscribe immediately 😵‍💫

[webu]

The good news is that the ComfyUI Yolo World plugin is great. The bad news is that the author of this plugin has made many plugins and never maintains them.

[brgresearch]

Brilliant explanations. Thanks for making this video, it is so useful, and you have a great mastery of the subject.

[jeffg]

Thanks for the comment the other day. I had deleted my post already before I saw it so unfortunately the tip wasn't left for others (because of my deletion).
The tip (leaving for others here) was to delete the specific custom node folder if you have problems loading an addon - in certain cases anyways.
I had an idea for NN model decoders.
The idea is simple. It's to pass in a portion of the image that's pre-rendered and that you want unchanged in the final image.
So, the decoder would basically do it's magic right after the noise is generated.
So, right on top of the noise, the decoder overlays the image you want included (transparent in most cases).
It can have some functionality in the NN decoder for shading your image clips - both lighting applied to it as well as shadows.
This might even need a new adapter "Type" - but I just haven't gotten deep enough into it yet (sorry if you're reading this as I keep correcting it, it's like 4:48 am... - it's pretty bad writing...)
If you all have direct contacts with those at stability ai, you might reach out and suggest something regarding including pre-renders directly into noise at the beginning of the denoise process.

[АлексейКузнецов-жз]

Huge thanxs for the video! At last i have good inpaint and outpaint workflows

[LuckRenewal]

i really love your videos, you really explain it very well!

[croxyg]

If you have a missing .jit file error, go to SkalskiP's huggingface and find the jit files there. Place in your custom nodes > efficient sam yolo world folder.

[Artishtic]

Thank you for the object removal section

[Kikoking-yb]

At the Beginning Thank you
The question is now which inpaint methode is better? To use Vae encode then Refine with Preview Bridge
or
to work directly with VAE Enfode&Inpaint conditioning without any refinment . I want to know how to get the best results
:) Appreciate

[opstudio]

Holy crap this was good... I love being able to just boop people out of pictures now lol

[geraldwiesinger]

Wow, awesome results. Which resolution are the images? Would this work on 4k images as well or would it be necessary to downscale or crop the inpaint region first?

[swipesomething]

3:37 After I installed the node, I had errors "cannot import name packaging from pkg_resources", I updated the inference and inference-gpu packages and it was working, so if anybody has the same errors try to update the inference and inference-gpu

[emizemani]

Amazing work! Just one question, in the combined workflow, how do you add a mask manually? Because the moment I queue prompt the mask disappears from the preview bridge. Am I doing something wrong?

[dexter]

Hi, really useful and interesting video! I have one small problem and maybe you can help me. At 33:25 minute mark your KSampler has a seed input circle, mine doesn't and i tried to use the KSampler(WAS) node that has a seed input circle but my Seed node from rgthree doesn't want to connect with the WAS KSampler node... any help please?

[subashchandra]

The issue with this is when you are trying to inpaint pictures that are large, it cannot inpaint accurately at all. Were you able to figure out how to downscale just the masked region such that its max_width is 768 or 1024 so that it is able to inpaint effectively?