Funny how all AI websites have anual plans, the landscape changes so fast than in weeks or months you might just have a better open source alternative.
That’s the thing about ai products in services it’s in waves of development and then open source developers get on their tails but then they Provide new Services and Loop
Krea certainly uses the same SD upscaler. Two SD-based choices for you: `fewjative/ultimate-sd-upscale` and `batouresearch/high-resolution-controlnet-tile` on Replicate AI.
I don't get the point of upscaling if it alters the image as substantially as this does. What I want is an AI upscaler that produces an image that looks indistinguishable from the original when downscaled.
I thought you have the choice - with a slider to choose from 'no creativity' to 'full creativity,' during the upscale. But if you just want a simple AI-powered upscale, and nothing else, then suggest you use TOPAZ AI or perhaps UPSKAYL. I have Topaz, and It will give you a no-nonsense fast upscale, without changing the original image at all. But I am so going to give this Open Art one a go too, as I like seeing what it can do to improve the image...
Just 10 seconds in for single images of a video, and you're in for a visual rollercoaster - objects leap and morph unpredictably, making every moment an unexpected thrill.
Its not an upscaler at all. Its just another Image generator. If you look at all the images that its upscaling. It's just a regenerates the image from the first image. Its just a Image to Image generator. Every image generated is different to the original. So if you have an image that wants to be upscaled, and it needs to be a perfect 1:1 image, this will not do that at all. It will just generate another image of what you have, and things will be different from the original. Dont get me wrong, it's really amazing, I love it myself. But I use Topaz Photo AI. and it upscales and does not change the image.
It is an upscaler - it upscales the image dramatically, and you then choose if you want to add more detail or 'creativity' to the upscale. But you don't have to.
Thanks a lot for all your videos, Matt! Just a note according to Magnific: it only takes 5 credits for a 2x upscale of a standard e.g. midjourney image size (round about 2000 px > magnified to 4000 px), so my monthly 2,500 credits in the basic subscription go a long way with 500 simple 2x upscales. And if I combine it with the cost free upscayl app for the final bigger upscales, it is a perfect combination for a lot of use cases, and I often prefer the Magnific upscales to the midjourney ones. And special thanks for introducing Upscayl in one of your last videos :*
Hey Matt! Check this out Theres this thing, Air LLM If i understood it correctly, it seems to allow 70b models yo run on 4gb hardware Here is a long wall of text by perplexity Understanding AirLLM and Its Significance AirLLM is a groundbreaking technique that facilitates running a 70-billion-parameter large language model (LLM) on a single 4GB GPU, overcoming traditional hardware limitations. Traditionally, such large models would require more powerful and expensive hardware, restricting accessibility. **What is AirLLM?** AirLLM stands for a method allowing large language models to operate on smaller, less powerful GPUs. It employs two main techniques: 1. **Layer-wise Inference:** Breaks down the model into individual layers, loading only the necessary layers into memory during inference, reducing the overall memory footprint. 2. **Flash Attention:** An optimization within layer-wise inference, focusing on loading and executing only one layer at a time, further minimizing memory requirements. **Why is AirLLM Significant?** The significance lies in democratizing the use of large language models, making it accessible for personal projects, educational purposes, and small businesses. Practical implications include the ability to run advanced AI models, like chatbots, on smaller hardware, fostering innovation in various fields. **Running 70B LLM on a 4GB GPU with AirLLM Technique** **What it is:** AirLLM is a groundbreaking technique enabling the operation of a 70-billion-parameter large language model (LLM) on a single 4GB GPU, overcoming traditional hardware limitations. **How it works:** The technique employs layer-wise inference, dividing the model into layers and loading only the necessary parts into memory, drastically reducing memory requirements. **Key Features:** - **Layer-wise Inference:** Splits the model into layers, significantly cutting down on GPU memory usage. - **Flash Attention:** Optimizes single-layer execution, further reducing memory needs per layer. **Benefits:** Allows for efficient and effective inference on a 4GB GPU without compromising model performance, bypassing the need for high-end GPUs or excessive RAM. **Applications:** Ideal for scenarios where hardware resources are limited, such as personal projects or low-budget research. This technique represents a significant leap in making advanced AI models more accessible, enabling users with modest hardware to leverage the power of large LLMs for various applications.
@@aouyiuif you add detail is from imagination at the end, that detail was lost by lowres/small image so its the same with ai, it adds detail from its predictions
It's reality touch it put on all objects increases its “real” look and more difficult to distinguish between an actual photo and AI generated, which is one of the biggest tests for me on how good a model is. Well done!
I thought there was something cool here. It's basically a basic thing I do by hand. It's not a one-button solution, but it's completely buttonless and under my control.
To be fair, I think the gems on the crown were implied in the original; they were just not very detailed. the upscale added and improved those. I think things like T-shirt logos, you could prob get similar results by doing a vector tracing of the original in an app like Adobe Illustrator. And that would take just a few seconds. I think the Camelon was an improvement, and the Apple/Classroom was clearly a much better image, and no details were added that were not implied in the original? I am not sure the Pig one was an improvement, but it didn't make it any worse either I guess.
i wonder if it would be possible to have upscalers improve their consistency by having them trained both to produce a bigger image, but also to keep the bigger image looking similar to the smaller image when downscaled to the same size; or even downscale both to something like half or a quarter of the size of the original to give some room for creativity.
It worries me that I'm seeing fewer and fewer examples of what these new image generators and upscalers can do when it comes to people. Hands. Fingers. Eyes. I worry that we've gotten so concerned with what people are going to do to Taylor Swift's saintly image that the guardrails are being brought up around human images in general. Somebody please prove me wrong.
8:01 - That's not perfect since Open Art AI changed the O into a G and that's not good, it ruined the text, but regardless it's pretty amazing how it made it look real like a photo in comparison to the SD 3.0 original image
Nah. I’m good. Open source is the way. This kind of stuff needs to be available for everyone for free. There are a lot of creative people with ideas that can’t pay for stuff like this.
@@absolutefreedom8035 sponsors? Donators? Investors? Idk. 🤷 hopefully in the future we can do this kind of things on our own pc’s/laptops with mid/low specs or a device that is specifically designed for this kind of stuff.
I really hate the fact this is being marketed as an "upscaler". At 7:03 you can clearly see the result isn't being upscaled but instead regenerated, the lighting, color and shape of the apple has completely changed and mind the fact that the text in the background has too.
начало тут 10:46 если устроят условия , можно смотреть ролик целиком. start at 10:46 if you're happy with the conditions, you can watch the whole clip.
thank you for that, I was trying to find an other option besides Magnific, I liked the price and got a few credits for free to test it proper, unfortunately the tools I was looking for (upscale) is not available with free credits, but I'll definitely pay and test this one. Magnific is really good, but the price is not worthy.
Doesn't Krea have the creative upscale? Also note, the Krea free version is very limited to the paid plans. (But are much less expensive than Magnific)
So... it seems like its generating an entirely new image with a higher resolution. Not adding details and upscaling. Pretty much the same as using controlnet in img2img.
Ill say it before and ill say it again, way to totally tank your reputation, Magnific ai! When the ai space is rapidly growing and ai companies are constantly outdoing thenselves, $30/month is a complete scam when you can just wait like 3 weeks and have open source completely free creative upscale.
Subscribed to basic plan and tried creative upscale, but after wasting hours after trying I find that the image upload process is endlessly running. It seems the website is not functioning properly and the helpline is not even replying to my SOS mail. Thinking about asking for a refund.
Where the hell has the upscaling option gone on open art? I've just generated four images and they look terrible and I cannot find it anywhere. If they have removed it then I'm cancelling my membership.
Matt can you speak about commercial use with Open Art though? It says on their website attribution in required. How's one to do that on a tshirt design? Kinda makes it a deal breaker for me
I went on Openart but I am not even allowed to test the upscaler without upgrading to a premium account (that means paying !)... Sorry Open art, but I don't pay for something I personally did not test before
bruh only 5 images a day, i'm sorry but thats just fucking useless. The rollercoaster of emotions this vid took me through, first i rolled my eyes at mgnific killer thingy cause i thought t was another clickbait like many channels have done, then i saw the crown photo i was like "holy shit, these fuckers actually did it, this might be a magnific killer" and then the smile got wipped off my face at 5 images a day. oh boy, i use dalle and sd for work and i'm not that sold on this cause i'd rather stick to my usual process as this doesnt optimize much for me but even as a hobbyist i wouldnt even consider getting this. 5images a day is too darn little, mahn the upscaler thing is an incredible piece of creative tech but it still has along way to go b4 its properly usable for most people
Yes, the price is better than magnific, but it's only a steal because they're sponsoring the video. $12 for 150 images? WAY too expensive! We all know that you won't get what you need with one generation. each job would require at least 5 generations to get something decent, so for $12 you'll get 30 jobs done.
Hello, I have watched many of your videos and I always wish you could speak in your normal voice, also you never seem to have anything negative to say about AI.
Ummm can I just say something here, and other techies of the same age chime in... so things move fast in tech, been in IT now 40 years... its a rollercoaster. But this time, with AI tech... Its moving too fast, people can't apply it cos by the time they come up with a use case somebody makes that idea obsolete. Its not sustainable for industry at this speed of advance.
Funny how all AI websites have anual plans, the landscape changes so fast than in weeks or months you might just have a better open source alternative.
A fool and his money are soon to be departed.
Yeah, and they usually offer a discount if you pay the whole year.
@@bazookaman1353 The new gold rush before money becomes more or less obsolete haha
That’s the thing about ai products in services it’s in waves of development and then open source developers get on their tails but then they Provide new Services and Loop
Exactly what i thought
Buying yearly subscription when things move that fast in AI it should be 90% off lol
with how fast things change i dont see myself subscribing annually to anything.
Plus global recession, they just don´t see it.
Fr, just wait till next year or so and it will probably be cheaper or maybe good free alternatives
@@The_Questionaut There's already a good free alternative Krea AI
Stability AI should give us an open source upscaler like that :)
You can already do that with img2img in eg auto1111. Low cfg, low denoise, followed by the upscaler.
@@helge666 i mean something more sophisticated like Krea
@@BillMillsd upscaler is already advanced, it's just a bit difficult to master
Krea certainly uses the same SD upscaler. Two SD-based choices for you: `fewjative/ultimate-sd-upscale` and `batouresearch/high-resolution-controlnet-tile` on Replicate AI.
Wow really free unlimited but how plz how to use it tell me name of it and tutorials of it??
I don't get the point of upscaling if it alters the image as substantially as this does. What I want is an AI upscaler that produces an image that looks indistinguishable from the original when downscaled.
I thought you have the choice - with a slider to choose from 'no creativity' to 'full creativity,' during the upscale. But if you just want a simple AI-powered upscale, and nothing else, then suggest you use TOPAZ AI or perhaps UPSKAYL. I have Topaz, and It will give you a no-nonsense fast upscale, without changing the original image at all. But I am so going to give this Open Art one a go too, as I like seeing what it can do to improve the image...
@@RJMCTV Topaz definitely changes the image, leaves a lot of artifacts.
Just 10 seconds in for single images of a video, and you're in for a visual rollercoaster - objects leap and morph unpredictably, making every moment an unexpected thrill.
The chameleon doesn't have a little extra eyeball... the upscale gave it a nostril!
It's crazy how I can check your channel almost every day, and there is something new and exciting!!
Its not an upscaler at all. Its just another Image generator. If you look at all the images that its upscaling. It's just a regenerates the image from the first image. Its just a Image to Image generator. Every image generated is different to the original. So if you have an image that wants to be upscaled, and it needs to be a perfect 1:1 image, this will not do that at all. It will just generate another image of what you have, and things will be different from the original. Dont get me wrong, it's really amazing, I love it myself. But I use Topaz Photo AI. and it upscales and does not change the image.
It is an upscaler - it upscales the image dramatically, and you then choose if you want to add more detail or 'creativity' to the upscale. But you don't have to.
Thanks a lot for all your videos, Matt! Just a note according to Magnific: it only takes 5 credits for a 2x upscale of a standard e.g. midjourney image size (round about 2000 px > magnified to 4000 px), so my monthly 2,500 credits in the basic subscription go a long way with 500 simple 2x upscales. And if I combine it with the cost free upscayl app for the final bigger upscales, it is a perfect combination for a lot of use cases, and I often prefer the Magnific upscales to the midjourney ones. And special thanks for introducing Upscayl in one of your last videos :*
Love it!
I upscale photos before printing with great results. I use open source free Upscayl and add my own models
yeah I have that too, plus if you have your models in a folder called models' then you can change the upscale model Upscayl uses.
Hey Matt! Check this out
Theres this thing, Air LLM
If i understood it correctly, it seems to allow 70b models yo run on 4gb hardware
Here is a long wall of text by perplexity
Understanding AirLLM and Its Significance
AirLLM is a groundbreaking technique that facilitates running a 70-billion-parameter large language model (LLM) on a single 4GB GPU, overcoming traditional hardware limitations.
Traditionally, such large models would require more powerful and expensive hardware, restricting accessibility.
**What is AirLLM?**
AirLLM stands for a method allowing large language models to operate on smaller, less powerful GPUs. It employs two main techniques:
1. **Layer-wise Inference:** Breaks down the model into individual layers, loading only the necessary layers into memory during inference, reducing the overall memory footprint.
2. **Flash Attention:** An optimization within layer-wise inference, focusing on loading and executing only one layer at a time, further minimizing memory requirements.
**Why is AirLLM Significant?**
The significance lies in democratizing the use of large language models, making it accessible for personal projects, educational purposes, and small businesses. Practical implications include the ability to run advanced AI models, like chatbots, on smaller hardware, fostering innovation in various fields.
**Running 70B LLM on a 4GB GPU with AirLLM Technique**
**What it is:**
AirLLM is a groundbreaking technique enabling the operation of a 70-billion-parameter large language model (LLM) on a single 4GB GPU, overcoming traditional hardware limitations.
**How it works:**
The technique employs layer-wise inference, dividing the model into layers and loading only the necessary parts into memory, drastically reducing memory requirements.
**Key Features:**
- **Layer-wise Inference:** Splits the model into layers, significantly cutting down on GPU memory usage.
- **Flash Attention:** Optimizes single-layer execution, further reducing memory needs per layer.
**Benefits:**
Allows for efficient and effective inference on a 4GB GPU without compromising model performance, bypassing the need for high-end GPUs or excessive RAM.
**Applications:**
Ideal for scenarios where hardware resources are limited, such as personal projects or low-budget research.
This technique represents a significant leap in making advanced AI models more accessible, enabling users with modest hardware to leverage the power of large LLMs for various applications.
wtf... ?
this is not upscaling… this is stylizing
creative 😂
Re-stylizing. Who wants "upscale" of a persons photo where the upscaler changes the face of the person?
@@digidope you can't magically add missing details, you can only allucinate them, there is still a slider to lower the creativity anyway
@@sherpya Why not? you can do so yourself in photoshop, so why can't AI?
@@aouyiuif you add detail is from imagination at the end, that detail was lost by lowres/small image so its the same with ai, it adds detail from its predictions
It's reality touch it put on all objects increases its “real” look and more difficult to distinguish between an actual photo and AI generated, which is one of the biggest tests for me on how good a model is. Well done!
I thought there was something cool here. It's basically a basic thing I do by hand. It's not a one-button solution, but it's completely buttonless and under my control.
I’m looking forward to a local upscale that provides almost the same result.
SD upscale in Stable Diffusion was released in 2022. It "creative "upscales as high as your VRAM allows.
This isn't local?
Who else checks Matt every couple of hours for cool AI news like these 😂
This is more like inpainting than upscaling; adding a bunch of details that weren't even implied in the original image.
To be fair, I think the gems on the crown were implied in the original; they were just not very detailed. the upscale added and improved those. I think things like T-shirt logos, you could prob get similar results by doing a vector tracing of the original in an app like Adobe Illustrator. And that would take just a few seconds. I think the Camelon was an improvement, and the Apple/Classroom was clearly a much better image, and no details were added that were not implied in the original? I am not sure the Pig one was an improvement, but it didn't make it any worse either I guess.
I would also add that Leonardo has some pretty cool upscaling options, although said upscales are modest. Thanks for the video!
Will it also be an upscaler model one can use locally/offline?
Absolutely excellent info as always. Congrats on a quarter million!
Nice reveal of the new tool looks very slick can't wait to try it out on my cat photos.
9:44 It looks like a real cameleon nose, not an eyeball
i wonder if it would be possible to have upscalers improve their consistency by having them trained both to produce a bigger image, but also to keep the bigger image looking similar to the smaller image when downscaled to the same size; or even downscale both to something like half or a quarter of the size of the original to give some room for creativity.
2:40 It's not 3D "render", it's "rendering" ...paint vs a painting = render vs a rendering.
render is not a noun.
It’s a good day when Matt uploads
Nice ! Thank you Matt. 😁😄😊
Released??? Where can I try SD3? I'm on the waiting list.
I just hope I can run it on 12gb vram
@@deeptobhattacharyya3249 I am so sorry for you.
He means "announced". The waiting list and the images on Twitter are the only things available right now.
@@deeptobhattacharyya3249 *cries in 8gb*
I gave it a picture of myself nude. and a big warning came up saying, 'no AI system on earth has the compute power to make that look good'
6:30. This is really sweet. The lemon was meh.
It worries me that I'm seeing fewer and fewer examples of what these new image generators and upscalers can do when it comes to people. Hands. Fingers. Eyes. I worry that we've gotten so concerned with what people are going to do to Taylor Swift's saintly image that the guardrails are being brought up around human images in general. Somebody please prove me wrong.
When will we see this and SD3 on Clipdrop?!??!?
This upscaler thing is way over my head but looks cool!
Denoising strength = Creativity Slider 😊
Yep. It's funny how they re-branded denoising :D
It did introduce an error though. Go big or go home apple. The G in big has a super comma
8:01 - That's not perfect since Open Art AI changed the O into a G and that's not good, it ruined the text, but regardless it's pretty amazing how it made it look real like a photo in comparison to the SD 3.0 original image
Great video. Test it on ps1 screenshots.
Good idea.
Nah. I’m good. Open source is the way. This kind of stuff needs to be available for everyone for free. There are a lot of creative people with ideas that can’t pay for stuff like this.
@@absolutefreedom8035 sponsors? Donators? Investors? Idk. 🤷 hopefully in the future we can do this kind of things on our own pc’s/laptops with mid/low specs or a device that is specifically designed for this kind of stuff.
Loving the content! Keep it up!!
Lets hope Open Art provides early access to Sora just like they did with Dalle 2
you're confusing OpenArt and OpenAI
Their AI really makes average photos shine.
What happened with upscalers, they don't sem to be progressing much, hardly hear anything anymore about them.
I really hate the fact this is being marketed as an "upscaler". At 7:03 you can clearly see the result isn't being upscaled but instead regenerated, the lighting, color and shape of the apple has completely changed and mind the fact that the text in the background has too.
an upscaler and a creative upscaler are not the same.
Kinda cool, but shouldn't they offer an open-source option if they're calling themselves OpenArt? Or are they open in an OpenAI way ? (i.e. closed)
7:53 the O in "OR" is messed up
Theres also a weird line after G in BIG
Push for open source upscaling✊
Leonardo AI upscales pretty good as well.
начало тут 10:46 если устроят условия , можно смотреть ролик целиком.
start at 10:46 if you're happy with the conditions, you can watch the whole clip.
thank you for that, I was trying to find an other option besides Magnific, I liked the price and got a few credits for free to test it proper, unfortunately the tools I was looking for (upscale) is not available with free credits, but I'll definitely pay and test this one. Magnific is really good, but the price is not worthy.
07:56 "take about perfection", the text was clearly messed up...
08:56 "the pig feet look awesome", it has two extra feet...
Doesn't Krea have the creative upscale? Also note, the Krea free version is very limited to the paid plans. (But are much less expensive than Magnific)
Great video, thanks
That image enhance of Yeshua is really good
Yahshua YAH- YAHWEH SHUA- Salvation. Yahshua Yahweh is salvation. Not Yes SHUA- Yes is not ELOHIM name.
krea ai also has a creative upscaler
His hairline is not receding, I saw his giga pixel video earlier and noticed that his hair looks the same
The astronaut pig reminded me of Muppets. Piiiiigsss innnn spaaaace!
dude! they wont even let you try it once for free. I mean seriously.
Still has some issues upscaling hand digits and the flag of the astronaut on the pig...... I'm still not quite convinced....
So... it seems like its generating an entirely new image with a higher resolution. Not adding details and upscaling. Pretty much the same as using controlnet in img2img.
I really hope newer models get better at upscaling than SDXL so we can avoid using these payed services.
suno v3 is out now for pro and premium members
Fix your camera on the wall, when you touch the table you make it wobble and so the image wabbles too...
Ill say it before and ill say it again, way to totally tank your reputation, Magnific ai! When the ai space is rapidly growing and ai companies are constantly outdoing thenselves, $30/month is a complete scam when you can just wait like 3 weeks and have open source completely free creative upscale.
It rate limited me for 24 hrs after 5 upscales. I paid $12 for THIS?
Subscribed to basic plan and tried creative upscale, but after wasting hours after trying I find that the image upload process is endlessly running. It seems the website is not functioning properly and the helpline is not even replying to my SOS mail. Thinking about asking for a refund.
Where the hell has the upscaling option gone on open art? I've just generated four images and they look terrible and I cannot find it anywhere. If they have removed it then I'm cancelling my membership.
Hi Matt! I didn't know about openart, thank you for the enlightenment. Hope one can train LoRA there, if so, that's what I'm looking for 💪🏻
It sucks for two things, 1-it's not free and 2-it doesn't allow nsfw
It actually does for many models and upgraded subscriptions
No link in description, Matt?
You're usually pretty good for that.
Fixed it! That’s my bad. openart.ai/home?gad_source=1&gclid=EAIaIQobChMIrf_zvdHChAMVWmdHAR3SFwGzEAAYASAAEgICMPD_BwE
@@MattVidPro Thanks muchly, bro.
Matt can you speak about commercial use with Open Art though? It says on their website attribution in required. How's one to do that on a tshirt design? Kinda makes it a deal breaker for me
Another "Open" company that only offers closed source software. Lame.
This is great news!
Will you do a Suno v3 video?
Yes!
I went on Openart but I am not even allowed to test the upscaler without upgrading to a premium account (that means paying !)... Sorry Open art, but I don't pay for something I personally did not test before
bruh only 5 images a day, i'm sorry but thats just fucking useless. The rollercoaster of emotions this vid took me through, first i rolled my eyes at mgnific killer thingy cause i thought t was another clickbait like many channels have done, then i saw the crown photo i was like "holy shit, these fuckers actually did it, this might be a magnific killer" and then the smile got wipped off my face at 5 images a day. oh boy, i use dalle and sd for work and i'm not that sold on this cause i'd rather stick to my usual process as this doesnt optimize much for me but even as a hobbyist i wouldnt even consider getting this. 5images a day is too darn little, mahn the upscaler thing is an incredible piece of creative tech but it still has along way to go b4 its properly usable for most people
Yeah... it's crazy that they only let you use 1,500 of the credits on upscaling out of the 5000 you paid for... this isn't a magnific killer.
@@tybost it is a magnific killer, because it is better and cheaper, however its still expensive
@@zrakonthekrakon494The 5 upscales a day restriction is rather annoying... hopefully they get rid of it and it will be a little more digestible.
Thanks John Oliver
Love your vids
I started playing around with Pinokio and Stable Diffusion on my PC. Are there open source image upscalers we can install locally?
@@absolutefreedom8035lap configuration??, GPU or cpu which one is most recommended for these tools..
Upscayl
SARCASM ON: 1:37 I think its a bit racist to swap an asian face to a caucasian face and call it upscale 🤣
Local Stable Diffusion does creative upscales. This tool is for people who don't run SD.
The upscaler botched the text in the apple image.
Open Art ❤️
Midjourney's paid plan isnt worth it anymore.
Most people don't pay for Midjourney just for upscaling, it's everything else it can do. And clearly it's still the best at many things.
Matt camera could do with some stability
i can’t even use sd3….
Don't mislead with the thumbnail!
Is there any good uspcaler for VHS footage?
👋
Is this new upscaler the one that comes packaged with a ClipDrop subscription?
ClipDrop.. you might have to wait in a queue for a l o n g time.... but ClipDrop does a lot of other stuff too.
taking so far over 2 min to make one image...
This is the correct way to do sponsorships. Thanks for the respect Matt.
Always!
Umm 1:37 up-scaled Asian person = white person? I hope that transformation was due to the prompt and not a bias in the model 😅
Yes, the price is better than magnific, but it's only a steal because they're sponsoring the video. $12 for 150 images? WAY too expensive! We all know that you won't get what you need with one generation. each job would require at least 5 generations to get something decent, so for $12 you'll get 30 jobs done.
Magnific set a horrendous precedent for the whole industry, fortunately they will all be beset by open source in a few months
Hello, I have watched many of your videos and I always wish you could speak in your normal voice, also you never seem to have anything negative to say about AI.
we can find paid upscalers its no big deal show us a free one that will be a big deal
1:36 An Asian Girl Became Non-Asian 😐
nowadays upscale is changing to redraw.
THat's not upscaling! That's reimagined high quality image 2 image ai. I've yet to see a proper upscaler
Ummm can I just say something here, and other techies of the same age chime in... so things move fast in tech, been in IT now 40 years... its a rollercoaster. But this time, with AI tech... Its moving too fast, people can't apply it cos by the time they come up with a use case somebody makes that idea obsolete. Its not sustainable for industry at this speed of advance.
Not really useful for restoration. I rather would use KreaAI or hopefully SUPIR soon
You cant upscale free people so dont bother
5 a day.... lol