How to Inpaint in Stable Diffusion A1111, A Detailed Guide with Inpainting Techniques to level up!

#aiart, #stablediffusiontutorial, #generativeart
This tutorial will cover how to inpaint in stable diffusion A1111 and some inpainting techniques, using tools like Photopea, img2img inpaint, inpaint sketch, and LORAs. Along the way, I will give you some tips and tricks for how to quickly and consistently obtain great inpainting results. As always, feel free to leave a comment down below and who knows, you might see it in my future videos. Please leave a like and subscribe if you found my videos helpful. Cheers!

Chapters:
00:00 Intro
00:50 Summary / Outline
01:37 Installing Photopea Extension
02:15 Inpaint technique #1 – Overlay object in Photopea and inpaint over it in img2img.
03:11 How to inpaint by overlaying an object on top of the original image with Photopea
04:25 Inpainting the overlay object within Img2Img – Inpaint
06:05 How to pick the right denoising strength
08:20 Inpaint technique #2 – Use Inpaint Sketch to draw/generate a new object
09:19 XY plot of Denoising Strength vs. Sampling Steps
09:56 Latent upscaling with low denoising strength to fix minor image issues
10:40 Inpainting technique #3 – Inpainting a new object using a LORA
11:12 How to download and use a LORA
12:02 How to add the activation keyword to a LORA
12:45 How to add a preview image to a LORA
13:20 Inpainting with a LORA
15:33 How to clean up the background
17:27 Latent upscaling with low denoising to fix minor issues

My Other Inpainting Tutorials:

Useful links:
Photopea github page for use when installing from URL in A1111:

Real Mechanical Parts LoRA (reelmechv1.2)

***If you enjoy my videos, consider supporting me on Ko-fi***

[Trinketorium]

If you get the civtai extension via the a1111 extension tab you can just click update and it will scan your lira folder and add images and keywords for you

[hyperdeloutz]

WOW!! Never knew LORAs could be organized in such a way. Learnt so much and thank you for this inpainting tutorial.

[maddyvoldy]

Am using sd since many months, yet I didn't know a lot of stuff explained in this video. Thanks a lot. Learnt something today. Really appreciate this knowledge share

[rexs]

Really appreciate this tutorial! Reinforcing these skills in a step-by-step way has made it much easier for me to emulate in my own image generation!

[fishpickles]

Super great tips in this video, thanks!

[mulda]

Great videos, thank you! One of the hardest things to do is to fix arms. It would be great to see a video about this.

[ronaldp]

Great video all the useful information layed out an elegant manner.

[godpunisher]

Your videos are easier to understand. I like every video you publish.

[yss]

hey dude, you are really good youtuber and I really enjoy your videos. I have one quick question, where can I get the repository or like a file selection with all the models you are using? or if you can’t provide that, can you please share your opinion on which model would be best for generating realistic and very detailed photos, sometimes NWSF. Thanks a lot!

[ISIMUSI]

Very interesting video, I didn't know this tool. Since you are open to new requests, I would like to propose one that interests me..
I am becoming used to using Automatic1111 on the renderings I produce to add some details here and there.. being high-res images I use the Tile/blur(controlnet) + Tiled combo Diffusion&TiledVae to work directly on it and do further upscaling.
When there are people in the images, they very often come out wrong. Is there any way to use the Inpaint module directly in high resolutions without making crops?

[kennethgosch]

Great Video! I stumbled across this Aitana Lopez thing. I found it relatively easy to recreate pictures with the same face quality using juggernaut. But they have pictures where she is in a pool for example and this certainly doesn’t look AI generated to me. Could you explain how they are pulling this off? Greetings from Norway

[nemonomen]

Haven’t heard of Photopea before, but people probably pronounce it that way because they think it’s a smash up of “photo” and “utopia” but that would be wrong since the spelling is off.

[billyn]

If i may ask, is it possible to make 2 poses from controlnet, generate them separately and inpaint them in 1 image?

[EDashMan]

Is it possible to do this on an image of myself? Please do a tutorial

[CoconutPete]

still confused about whole picture vs. masked only... seems like I've seen tutorials that recommend the opposite. Will need more practice lol

[LEWINEMUSIC]

Hey, i practice every day. But I dont find a way to add realistic normal glasses. Its anoying, I get everything but not realistic results.

[ynirhfd]

Hey nice artwork! Just want to ask that are you interested in our new ai generation product? Maybe I can send you beta version to you~

[CoconutPete]

photopea remove background doesn't work with A1111 anymore