Видео

You are so right with your video.... It is so sad.

2 rising possibilities in my opinion: 1 - It's a occidental point of view. In China I am quite sure they will not debate about it, everything is free of copy, so AI generated content will rise while occidental countries will regulate? It will not happen 2 - If I'm wrong about N+1, there will be for sure web 3 solutions via a blockchain protocoles (such as DeFi solutions) and so no one will be able to regulate 😁😁😁

open source forever 😊

Platforms fight over users, who gets the monopoly. The time for funding will come later when they invent things that prevent people from moving from one platform to another - such as the transfer of their own historical data. Hopefully, the competition for the development of features will continue for a long time and no one will have a monopoly on the platforms, on the other hand, the coming of standards and enabling the transfer of data is desirable.

Great video, greetings from Greece

Agree

Let it go underground! We'll do it anyways

thx

Ich schau beinahe alles Videos auf deinem Kanal. Für mich tatsächlich einer der informativsten KI Channels hier.

Legend :D

Superb presentation! Thank you!

😳 What? Hackerman™ without his Limahl hair? 😉

Can't wait to try this. I've been struggling with hands, especially nails. Have you had any success with animation using DW?

Why I cant acces adjusment curve?

Genius thank you fantastic tutorial and tips ☀️

What is the purpose of the clip skip? Is that only for certain models?

(16:40) First, he meant "ALT+F4". Second, you can "ALT+TAB" to swap to the alert popup. Also, BooruDatasetTagManager has hotkeys you can set yourself (under "settings" => "hotkeys"). The default hotkey for hiding the preview window is "CTRL+P". (25:30) He forgot to mention that you can't set "max resolution" to 768x768 if your input images are less than that--say 512x512. A lot of times we'll create LoRAs specifically for use in image-to-image. That means we want those LoRAs to output at a low resolution so that it is quick and then you can "upscale" in img2img using the low-res as a base. You can also use 128x128 for pixel art.

I could hear you explaning thing to me for days, thank you for the informative video!

Why is this video incomplete? I dont have any ComfyUI folder. Isnt this a tutorial? Dislike

Hello @OlivioSarikas I have installed Kohya on a Mac Studio M1 Ultra. Although I received the following warning: "WARNING: Could not automatically configure Accelerate. Please manually configure Accelerate using the option in the menu or with: accelerate config," the interface is working. However, when I try to use DreamBooth, I'm getting several errors. I tried different configurations on Accelerate, but unfortunately, nothing worked. Have you managed to successfully train using a Mac? Any advice would be greatly appreciated. Thanks a lot!

Nice video, but I didn't get how downloading a file into the comfyUI folder then actually has an effect. Could someone explain? :) LG

I think they go for the option that makes the most money 😂

why my text box node shows missing? I have downloaded the chibi node as it says

Whenever I use negative embeddings this error always show's up "runtimeerror: expected scalar type half but found float"

If you get this working in A1111, PLEASE show us this again!

Looking for help, I have downloaded loras to the lora model folder, I have removed the @Rem from the command line in editor but after reloading and clicking on Loras the box says that there is nothing here and to add loras to the following directory C:\Forge\webui_forge_cu121_torch21\webui\models\Lora. Any help would be greatly appreciated.

Where to dowbload a1111? This is not really helpful…

thanks u

where to get the saicanny model?

Thank you Olivio! I've tried multiple outdated tutorials how to do stuff with DreamBooth and I wasn not able to make it work. Your tutorial was the easiest and I was able to train my own model and play with it a bit. Thank you o>

Thank you so much for this. I can't find, like we can see at 3:45, ComfyUI_Comfyroll_CustomNodes , maybe it was replaced for Comfyroll Studio?

You always have community love, no matter what's wrong... Thanks for bring great things to us.

Great video! Thank you!

sora is still very lame at movements. very much not realistic.

is it still working?

Take the time you need. Get my best wishes.

I installed comfyui and story diffusion and ollama, but none of them starts

Stay strong Olivio

Very sorry to hear you’re going through so much. We appreciate you and everything you do, Olivio . You’re a great guy.

I dont have an ESRGAN folder

boo! lying by omission, boo this man!

Do not hesitate to take some breaks with RUclips, we can wait a few days for some AI news ! ;-) Stay strong, greetings from France !

Thank you bro, that was great!

That was incredible, really liked the music video!

fantastic video - I learned so much, thank you

Love your content man, keep your head up

I had a problem downloading the plugin and trying to get it to load without errors. However, I tracked it down to the file name length that needs to exceed 260 characters, In Windows, there is a parameter in the Register file that allows you to increase the file name length. And then it worked fine. You might have to clear out the ComfyUI folder that Krita created in downloading. The installer will point out that the ComfyUI folder exists but there is nothing in it.

Bro, take care! We love you.

Efficiency Node is broken currently idk why? Failed to install.