This A1111 Trick is NEXT LEVEL

complex compositions Every image shown is a static figure bust facing to the camera with a semi abstract background. 🤦

..... this is the pipeline....

Best video, so funny. Hacker Man...

Sorry, it doesn´t work. I´m missing the models, Olivio was talking about. They are not installed. Has anyone a link where I can download them manually or any other helpful advice? Thanks!!

Thanks for this Olivio, by far the best process i've tried so far.

So im new to A1111 and followed all this steps and it takes like 40 minutes or more for 1 image. is that normal? i have a 5800x3d and 7900 xt, 32 gb ram.

I love your new personality much better than the old one ... not saying that there was anything wrong with the old one :)
Thank you for this video!

Man, this is nothing new. One of the first things I did in Automatic1111 was exactly this. I was semi-familiar with the software, I might add. What else "IMG to IMG" would mean? This was a waste of time, I really expected something revolutionary. You started off being so enthusiastic about something that turned out to be a basic feature of the software.

The upscaler is not visible here in the UI, what might be the case? I have put the model into the models/RealESRGAN. Still, it just doesn't get listed.

GREAT !

Have you ever tested out the various loopback methods in Img2Img they are great and can be used to take a very specific style of image and slowly change it to a different style keeping the same general composition. Never see many videos on loopback either

It almost generates the same face each time?

Why the mushroom girl on the opening image doesn't wear sunglasses?

so this video basically is a nothing-burger. "Use a good starting image and use i2i with the most basic settings to convert it from digital art to a photo"...
Yeah... That's something that you get taught in the very first beginner tutorial.

Also this info is useless without actually explaining what each of your settings does. If a newbie sees it, sure they can copy the result. But did they gain any knowledge that would let them make their own art better? No. They just got your preset, and that's it.
This video is just a lazy cash grab.

Also midjourney works nice with generating two face in one photo, vary region one face of that photo and do a side of that same photo. Making a training source for who knows what😂

Any help on how to incorporate the downloaded upscaler in Invoke AI?

Did you install Nvidia Game Ready Driver or Studio Driver?

The hyperbole is next level. The secondary images do not look significantly better than the base images. Some of them look worse.

Wow, an extremely intelligent and practical tip. It can be said that achieving this level of artistry and detail involves numerous steps in SD (moreover comfyui need to be involved, going through many detailed steps, refiner). To make it easier, why don't we take use of MJ's creative brain (activate high-style mode) and quickly redraw? Then use SD, we can turn every digital masterpiece into reality🎉🎉Q

I love stable diffusion more than MJ

My god it blew my mind. I upscale on daily basis and definitely need to try this. I'm not able to follow and try everything about AIs. It's just too much incoming too fast 😂

Could you do all of that in one worflow in Comfy?

Just like in economics, imagine a scenario: "When everyone can obtain gold, what is the cost of gold? Zero." If you can create art without being an artist and make music without being a musician, what is the cost of art and music? Zero. We are all heading straight towards a massive iceberg, and we, as human beings, are on board the Titanic. Undoubtedly.

Olivio, thank you for your work! All your video is awesome!
Do you have any plans to make a new outpainting video in SD, similar to photoshop techniques without the prompt to quik clean the image from artifacts and increase the size of the image?

Damn I like your hairstyle and your "mwah" flying kiss lol. Very nice trick thank you for sharing.

The tips are awesome! 🎉 but the delivery is kinda corny

you've taken me to the next level I might have to try with source images from the Wurstchen demo

Hi Olivio - What would be the best way to do the reverse of this? Which model and prompt do you think would work best to take an ordinary photo of someone and turn it in to a magical creation? Thanks.

This one was a bit more awkward to watch than usual… 🤷‍♂️

Model swapping or using multi-platform rendering really isn't anything new or profound.. but this is still good to know for users that are new to this. The amount of "Hype" is a bit much for such a little trick that is old. Not liking this kind of video honestly.

I had some problems using img2img and SDXL, getting errors all the time.
I'll try this option.

Any chance of getting just one decent video about illustrations, rather than photorealism. At least one fucking proper video where there would be a truly well realized upscaling for the illustrations, so that it would enhance the details, not ruin them?

imagine that you can upscale her to kind of unlimited resolution, and you can even zoom in or zoom out and see microbs on her makro skin cells, that ai recreate online 😮 and if its a video in this eternal resolution and you can render any old movie with new actors and environment in this eternal ai resolution😮 and all this is in VR 3d model of whole earth. and universe 😂 and you have only one body in it and feel pain and you can die😂

I have been trying to find a way to create photos of my relatives who have died. It is almost impossible to create a LORA or checkpoint to draw them because there are not enough quality images to train on. I have tried Roop but that doesn't seem to work. If you could do a tutorial on this, I would appreciate it greatly. Thank you.

This is amazing and something I've been thinking about as a long time MJ-subscriber and quite fresh SD-explorer. Please be this this personality with the wig in every future video 😄

Top content creator. Cheers.

What VAE are you using? Auto? Thanks.

MidJourney is to expensive so can't do this.

make it 16k 😮 my 8k sony tv from 2021 doing that kind of upscales you showing. i suppose😂

can you order to ai to make exact face model and other transformations on few pictures? kind of can you render a movie or cartoon and watch it in different style, cast etc?

Good video!
DPM++ SDE Karras doesn't need that many steps. 10 is usually enough for SDE, anything higher won't change much. But I recommend DPM++ 2M SDE Karras which is a new sampler and is a mix of SDE and 2M. It's much faster for high res images, and you can set it at ~30 steps and it's still faster than the older samplers in my experience.

Nice i idea, i will give it a try😊 , ( you have too much tabs in your browser 😅 )

Nice tip. Working beautifully! It's quite crazy, the feeling is like you are getting the original photograph, from which the Midjourney art was painted :)

I'm a simple man. I see Hackerman, I press like button.

You look great today! :D
Thank you for the video and keep up the good work!

Do you use ComfyUI?