RIP Midjourney! FREE & UNCENSORED SDXL 1.0 is TAKING OVER!

Say goodbye to Midjourney and hello to the future of free open-source AI image generation: SDXL 1.0! This new, uncensored model is taking the AI world by storm, offering unparalleled image quality for FREE. So in this video, I'll show you how to download the model and use it on your own computer locally for free!

What do you think of SDXL 1.0? Let me know in the comments!
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
SOCIAL MEDIA LINKS!
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
►► My PC & Favorite Gear:
Recording Gear:
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
Special thanks to Royal Emperor:
- Totoro
- TNSEE

Thank you so much for your support on Patreon! You are truly a glory to behold! Your generosity is immense, and it means the world to me. Thank you for helping me keep the lights on and the content flowing. Thank you very much!

#stablediffusion #sdxl #imagegeneration #texttoimage
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
WATCH MY MOST POPULAR VIDEOS:
RECOMMENDED WATCHING - All LLM & ChatGPT Video:

RECOMMENDED WATCHING - My "Tutorial" Playlist:

Disclosure: Bear in mind that some of the links in this post are affiliate links and if you go through them to make a purchase I will earn a commission. Keep in mind that I link these companies and their products because of their quality and not because of the commission I receive from your purchases. The decision is yours, and whether or not you decide to buy something is completely up to you.

[Aitrepreneur]

HELLO HUMANS! Thank you for watching & do NOT forget to LIKE and SUBSCRIBE For More Ai Updates. Thx <3
"K" - Your Ai Overlord

[vheypreexa]

Pro Tip: The styles don't have to be applied to your prompt. If they're selected in that section, it will apply it to your prompt in the background. Easy way to switch, add together, or combine different prompts quickly.

[WorriorXD]

I just used it for the first time to make a German Sheppard wearing shades and it looks so dope I'm now using it as a wallpaper🤩

[Macatho]

Guys. One tip, for those that havent thought about it.
The difference in time required to load the models is about factor 10-15 if you have the model on a mechanical drive. It takes around 5-7 seconds to load a model on a new SSD and around 100 seconds to load it from a mechanical drive.

[goldkat]

You can easily change the default size from 512px to 1024px.
1. Open ui-config.json with notepad
2. Strg+F "512"
3. Change value to "txt2img/Width/value": 1024,
4. Strg+F "512"
5. Change value to "txt2img/Height/value": 1024,
6. Save
Now you dont have to change the resolution everytime you start a1111

[elias]

Really looking forward to the next generation of user created models using SDXL. I just can't wait!

[Thozi]

K is back! (as much as he probably hates it). Felt very much like the good ol' times - K explaining A1111 is like a Koi in the water <3

[thanksfernuthin]

Awesome! I saw their release announcement yesterday and hoped you'd cover it right away. It would have taken me a ton of time to figure out how to actually use it!

[carecoable]

12:21 My man went and uploaded this thinking we wouldn't notice the uncensored one at the bottom.

It's amazing how fast progress is being done with these new technologies. First I hear about the new wave tracing Nvidia does and now this, what a time to be alive.

[rs]

Now I can put my 4090 to work ! Thanks for the video, great content !

[MRboss]

I really hope auto1111 updates the UI for SDXL use. Like a toggle for SDXL that changed the look. The demo plugin for SDXL 0.9 has a ok UI so I hope they will build on that

[DominoUB]

based on the documentation from SAI the refiner is supposed to be used in latent space, not as img2img. I don't know if this is possible to do on A1111 but it is on comfyUI.

[Jordan_C_Wilde]

God damn i get excited when i hear "runs locally". If the next sentence is "on 10 GB GPUs" i might need tissues.

[ephemeral]

Thanks you for continuing to teach and keeping us up to date!

[wo]

Think of the offset lora in terms of what it does as a useful tool. Not simply in terms of prettier or not. By default the average brightness of all the pixels of a generated stablediffusion image sum to a mid value, even when you specify something very dark or very bright in the promp. But if you want truly dark or bright scenes that dont average to grey, or even logos or drawings with a few thin black lines over a white canvas, you need the offset lora, otherwise it will make lines thicker or add more lines than needed

[MameruArune]

Tried sdxl 1.0 from clipboard, prompted a photographic style art by the beach, one result says NSFW and is blurred, want but can't remove the blur, pretty sure that nsfw only shows the back of the skin of the girl. Am i missing something?

[bitfreezer]

Hello, Thank you so much. I really like your videos, you are good at explaining and come to the point fast! After watching your videos I always share your excitement for the newest AI stuff. I hope you can make a new video on how to train a own Lora model for SDXL or is it still the same way as with older models?

[banzai]

Awesome AI Overlord! It’s time to create again

[hubnwuj]

Yesterday, i checked your videos about this content. Great as always!

[gameswithoutfrontears]

Awesome. Thanks for this vid. Looking forward to installing this great new model.