More on Lifestyle
Peter Steven Ho
3 years ago
Thank You for 21 Fantastic Years, iPod
Apple's latest revelation may shock iPod fans and former owners.
Apple discontinued the iPod touch on May 11, 2022. After 21 years, Apple killed the last surviving iPod, a device Steve Jobs believed would revolutionize the music industry.
Jobs was used to making bold predictions, but few expected Apple's digital music player to change the music industry. It did.
This chaos created new business opportunities. Spotify, YouTube, and Amazon are products of that chaotic era.
As the digital landscape changes, so do consumers, and the iPod has lost favor. I'm sure Apple realizes the importance of removing an icon. The iPod was Apple like the Mac and iPhone. I think it's bold to retire such a key Apple cornerstone. What would Jobs do?
iPod evolution across the ages
Here's an iPod family tree for all you enthusiasts.
iPod vintage (Oct 2001 to Sep 2014, 6 generations)
The original iPod had six significant upgrades since 2001. Apple announced an 80 GB ($249) and 160 GB ($349) iPod classic in 2007.
Apple updated the 80 GB model with a 120 GB device in September 2008. Apple upgraded the 120 GB model with a 160 GB variant a year later (2009). This was the last iteration, and Apple discontinued the classic in September 2014.
iPod nano (Jan 2004 to Sep 2005, 2 generations)
Apple debuted a smaller, brightly-colored iPod in 2004. The first model featured 4 GB, enough for 1,000 songs.
Apple produced a new 4 GB or 6 GB iPod mini in February 2005 and discontinued it in September when they released a better-looking iPod nano.
iTouch nano (Sep 2005 to July 2017, 7 generations)
I loved the iPod nano. It was tiny and elegant with enough tech to please most music aficionados, unless you carry around your complete music collection.
Apple owed much of the iPod nano's small form and success to solid-state flash memory. Flash memory doesn't need power because it has no moving parts. This makes the iPod nano more durable than the iPod classic and mini, which employ hard drives.
Apple manufactured seven generations of the iPod nano, improving its design, display screen, memory, battery, and software, but abandoned it in July 2017 due to dwindling demand.
Shuffle iPod (Jan 2005 to Jul 2017, 4 generations)
The iPod shuffle was entry-level. It was a simple, lightweight, tiny music player. The iPod shuffle was perfect for lengthy bike trips, runs, and hikes.
Apple sold 10 million iPod shuffles in the first year and kept making them for 12 years, through four significant modifications.
iOS device (Sep 2007 to May 2022, 7 generations)
The iPod touch's bigger touchscreen interface made it a curious addition to the iPod family. The iPod touch resembled an iPhone more than the other iPods, making them hard to tell apart.
Many were dissatisfied that Apple removed functionality from the iPod touch to avoid making it too similar to the iPhone. Seven design improvements over 15 years brought the iPod touch closer to the iPhone, but not completely.
The iPod touch uses the same iOS operating system as the iPhone, giving it access to many apps, including handheld games.
The iPod touch's long production run is due to the next generation of music-loving gamers.
What made the iPod cool
iPod revolutionized music listening. It was the first device to store and play MP3 music, allowing you to carry over 1,000 songs anywhere.
The iPod changed consumer electronics with its scroll wheel and touchscreen. Jobs valued form and function equally. He showed people that a product must look good to inspire an emotional response and ignite passion.
The elegant, tiny iPod was a tremendous sensation when it arrived for $399 in October 2001. Even at this price, it became a must-have for teens to CEOs.
It's hard to identify any technology that changed how music was downloaded and played like the iPod. Apple iPod and iTunes had 63% of the paid music download market in the fourth quarter of 2012.
The demise of the iPod was inevitable
Apple discontinuing the iPod touch after 21 years is sad. This ends a 00s music icon.
Jobs was a genius at anticipating market needs and opportunities, and Apple launched the iPod at the correct time.
Few consumer electronics items have had such a lasting impact on music lovers and the music industry as the iPod.
Smartphones and social media have contributed to the iPod's decline. Instead of moving to the music, the new generation of consumers is focused on social media. They're no longer passive content consumers; they're active content creators seeking likes and followers. Here, the smartphone has replaced the iPod.
It's hard not to feel a feeling of loss, another part of my adolescence now forgotten by the following generation.
So, if you’re lucky enough to have a working iPod, hang on to that relic and enjoy the music and the nostalgia.
Joanna Henderson
2 years ago
An Average Day in the Life of a 25-Year-Old -A Rich Man's At-Home Unemployed Girlfriend
And morning water bottle struggles.
Welcome to my TikTok, where I share my stay-at-home life! I'll show you my usual day from morning to night.
I rise early to prepare my guy iced coffee. I make matcha, my favorite drink. I also fill our water bottles, which takes time and effort, so I record and describe the procedure. As you see me perform the unthinkable by putting a water bottle in a soda machine, you'll see my magnificent but unowned condo. My lover has everything, including:
In the living room, a sizable velvet alabaster divan. I was unable to use the words white or sofa in place of alabaster or a divan since they are insufficiently elegant and do not adequately convey how opulent the item is. The price tag on the divan was another huge feature; I'm sure my lover wouldn't purchase any furniture for less than $20k because it would be beneath him.
A plush Swiss coffee-colored Tabriz carpet. Once more, white is a color associated with the underclass; for us, the wealthy, it's alabaster or swiss coffee. Sorry, my boyfriend is wealthy; I'm truly in the same situation. And yet, I’m the one whos freeloading off of him, not you haha!
Soft translucent powder is the hue of the vinyl wallcoverings. I merely made up the name of that hue, but I have to maintain the online character I've established. There is no room for adopting language typical of peasant people; I must reiterate that I am wealthy while they are not.
I rest after filling our water bottles. I'm really fatigued from chores. My boyfriend is skeptical about hiring a housekeeper and cook. Does he assume I'm a servant or maid? I can't be overly demanding or throw a tantrum since he may replace me with a younger version. Leonardo Di Caprio's fault!
After the break, I bring my lover a water bottle. He's off to work with my best wishes. After cleaning the shower, I text my BF saying I broke a nail. He charged $675 for a crystal-topped shellac manicure. Lucky me!
After this morning's crazy choirs, especially the water bottle one, I'm famished. I dress quickly and go to the neighborhood organic-vegan-gluten-free-sugar-free-plasma-free-GMO-free-HBO-free breakfast place. Most folks can't afford $17.99 for a caffeine-free-mushroom-plus-mud-and-electrolytes morning beverage. It goes nicely with my matcha. Eggs Benedict cost $68. English muffins are off-limits. I can't make myself obese. My partner said he'd swap me for a 19-year-old Eastern European if I keep eating bacon.
I leave no tip since tipping is too much pressure and math for me, so I go shopping.
My shopping adventures have gotten monotonous. 47 designer bags and 114 bag covers Birkins need their own luggage. My babies! I've never caught my BF with a baby. I have sleeping medications and a turkey baster. Tatiana is much younger and thinner than me, so I can't lose him to her. The goal is to become a stay-at-home wife shortly. A turkey baster is essential.
After spending $955 on La Mer lotions and getting a crystal manicure, I nap. Before my boyfriend's return, I can nap for 5 hours.
I wake up around 4 pm — it’s time to prepare dinner. Yes, I said “prepare for dinner,” not “prepare dinner.” I have crystals on my nails! Do you really think I would cook? No way.
My husband's arrival still requires much work. I clean the kitchen, get cutlery and napkins. I order UberEats while my BF is 30-45 minutes away.
Wagyu steaks with Matsutake mushroom soup today. I pick desserts for my lover but not myself. Eastern European threat?
When my BF gets home from work, we eat. I don't believe in tipping UberEats drivers. If he wants to appreciate life's finer things, he should locate a rich woman.
After eating, we plan our getaway. I requested Aruba's fanciest hotel for winter and expect a butler. We're bickering over who gets the butler. We may need two.
Day's end, I'm exhausted. Stay-at-home girlfriends put in a lot of time and work. Work and duties are never-ending.
Before bed, I shower and use a liquid gold mask in my 27-step makeup procedure. It's a French luxury brand, not La Mer.
Here's my day.
Note: I like satire and absurd trends. Stay-at-home-girlfriend TikTok videos have become popular recently.
I don't shame or support such agreements; I'm just an observer. Thanks for reading.
Josh Chesler
3 years ago
10 Sneaker Terms Every Beginner Should Know
So you want to get into sneakers? Buying a few sneakers and figuring it out seems simple. Then you miss out on the weekend's instant-sellout releases, so you head to eBay, Twitter, or your local sneaker group to see what's available, since you're probably not ready to pay Flight Club prices just yet.
That's when you're bombarded with new nicknames, abbreviations, and general sneaker slang. It would take months to explain every word and sneaker, so here's a starter kit of ten simple terms to get you started. (Yeah, mostly Jordan. Does anyone really start with Kith or Nike SB?)
10. Colorways
Colorways are a common term in fashion, design, and other visual fields. It's just the product's color scheme. In the case of sneakers, the colorway is often as important as the actual model. Are this year's "Chicago" Air Jordan 1s more durable than last year's "Black/Gum" colorway? Because of their colorway and rarity, the Chicagos are worth roughly three pairs of the Black/Gum kicks.
Pro Tip: A colorway with a well-known nickname is almost always worth more than one without, and the same goes for collaborations.
9. Beaters
A “beater” is a well-worn, likely older model of shoe that has significant wear and tear on it. Rarely sold with the original box or extra laces, beaters rarely sell for much. Unlike most “worn” sneakers, beaters are used for rainy days and the gym. It's exactly what it sounds like, a box full of beaters, and they're a good place to start if you're looking for some cheap old kicks.
Pro Tip: Know which shoes clean up nicely. The shape of lower top sneakers with wider profiles, like SB Dunk Lows and Air Jordan 3s, tends to hold better over time than their higher and narrower cousins.
8. Retro
In the world of Jordan Brand, a “Retro” release is simply a release (or re-release) of a colorway after the shoe model's initial release. For example, the original Air Jordan 7 was released in 1992, but the Bordeaux colorway was re-released in 2011 and recently (2015). An Air Jordan model is released every year, and while half of them are unpopular and unlikely to be Retroed soon, any of them could be re-released whenever Nike and Jordan felt like it.
Pro Tip: Now that the Air Jordan line has been around for so long, the model that tends to be heavily retroed in a year is whichever shoe came out 23 (Michael Jordan’s number during the prime of his career) years ago. The Air Jordan 6 (1991) got new colorways last year, the Air Jordan 7 this year, and more Air Jordan 8s will be released later this year and early next year (1993).
7. PP/Inv
In spite of the fact that eBay takes roughly 10% of the final price, many sneaker buyers and sellers prefer to work directly with PayPal. Selling sneakers for $100 via PayPal invoice or $100 via PayPal friends/family is common on social media. Because no one wants their eBay account suspended for promoting PayPal deals, many eBay sellers will simply state “Message me for a better price.”
Pro Tip: PayPal invoices protect buyers well, but gifting or using Google Wallet does not. Unless you're certain the seller is legitimate, only use invoiced goods/services payments.
6. Yeezy
Kanye West and his sneakers are known as Yeezys. The rapper's first two Yeezys were made by Nike before switching to Adidas. Everything Yeezy-related will be significantly more expensive (and therefore have significantly more fakes made). Not only is the Nike Air Yeezy 2 “Red October” one of the most sought-after sneakers, but the Yeezy influence can be seen everywhere.
Pro Tip: If you're going to buy Yeezys, make sure you buy them from a reputable retailer or reseller. With so many fakes out there, it's not worth spending a grand on something you're not 100% sure is real.
5. GR/Limited
Regardless of how visually repulsive, uncomfortable, and/or impractical a sneaker is, if it’s rare enough, people will still want it. GR stands for General Release, which means they're usually available at retail. Reselling a “Limited Edition” release is costly. Supply and demand, but in this case, the limited supply drives up demand. If you want to get some of the colorways made for rappers, NBA players (Player Exclusive or PE models), and other celebrities, be prepared to pay a premium.
Pro Tip: Limited edition sneakers, like the annual Doernbecher Freestyle sneakers Nike creates with kids from Portland's Doernbecher Children's Hospital, will always be more expensive and limited. Or, you can use automated sneaker-buying software.
4. Grails
A “grail” is a pair of sneakers that someone desires above all others. To obtain their personal grails, people are willing to pay significantly more than the retail price. There doesn't have to be any rhyme or reason why someone chose a specific pair as their grails.
Pro Tip: For those who don't have them, the OG "Bred" or "Royal" Air Jordan 1s, the "Concord" Air Jordan 11s, etc., are all grails.
3. Bred
Anything released in “Bred” (black and red) will sell out quickly. Most resale Air Jordans (and other sneakers) come in the Bred colorway, which is a fan favorite. Bred is a good choice for a first colorway, especially on a solid sneaker silhouette.
Pro Tip: Apart from satisfying the world's hypebeasts, Bred sneakers will probably match a lot of your closet.
2. DS
DS = Deadstock = New. That's it. If something has been worn or tried on, it is no longer DS. Very Near Deadstock (VNDS) Pass As Deadstock It's a cute way of saying your sneakers have been worn but are still in good shape. In the sneaker world, “worn” means they are no longer new, but not too old or beat up.
Pro Tip: Ask for photos of any marks or defects to see what you’re getting before you buy used shoes, also find out if they come with the original box and extra laces, because that can be a sign that they’re in better shape.
1. Fake/Unauthorized
The words “Unauthorized,” “Replica,” “B-grades,” and “Super Perfect” all mean the shoes are fake. It means they aren't made by the actual company, no matter how close or how good the quality. If that's what you want, go ahead and get them. Do not wear them if you do not want the rest of the sneaker world to mock them.
Pro Tip: If you’re not sure if shoes are real or not, do a “Legit Check” on Twitter or Facebook. You'll get dozens of responses in no time.
You might also like
Nojus Tumenas
3 years ago
NASA: Strange Betelgeuse Explosion Just Took Place
Orion's red supergiant Betelgeuse erupted. This is astronomers' most magnificent occurrence.
Betelgeuse, a supergiant star in Orion, garnered attention in 2019 for its peculiar appearance. It continued to dim in 2020.
The star was previously thought to explode as a supernova. Studying the event has revealed what happened to Betelgeuse since it happened.
Astronomers saw that the star released a large amount of material, causing it to lose a section of its surface.
They have never seen anything like this and are unsure what caused the star to release so much material.
According to Harvard-Smithsonian Center for Astrophysics astrophysicist Andrea Dupre, astronomers' data reveals an unexplained mystery.
They say it's a new technique to examine star evolution. The James Webb telescope revealed the star's surface features.
Corona flares are stellar mass ejections. These eruptions change the Sun's outer atmosphere.
This could affect power grids and satellite communications if it hits Earth.
Betelgeuse's flare ejected four times more material than the Sun's corona flare.
Astronomers have monitored star rhythms for 50 years. They've seen its dimming and brightening cycle start, stop, and repeat.
Monitoring Betelgeuse's pulse revealed the eruption's power.
Dupre believes the star's convection cells are still amplifying the blast's effects, comparing it to an imbalanced washing machine tub.
The star's outer layer has returned to normal, Hubble data shows. The photosphere slowly rebuilds its springy surface.
Dupre noted the star's unusual behavior. For instance, it’s causing its interior to bounce.
This suggests that the mass ejections that caused the star's surface to lose mass were two separate processes.
Researchers hope to better understand star mass ejection with the James Webb Space Telescope.
Dmitrii Eliuseev
2 years ago
Creating Images on Your Local PC Using Stable Diffusion AI
Deep learning-based generative art is being researched. As usual, self-learning is better. Some models, like OpenAI's DALL-E 2, require registration and can only be used online, but others can be used locally, which is usually more enjoyable for curious users. I'll demonstrate the Stable Diffusion model's operation on a standard PC.
Let’s get started.
What It Does
Stable Diffusion uses numerous components:
A generative model trained to produce images is called a diffusion model. The model is incrementally improving the starting data, which is only random noise. The model has an image, and while it is being trained, the reversed process is being used to add noise to the image. Being able to reverse this procedure and create images from noise is where the true magic is (more details and samples can be found in the paper).
An internal compressed representation of a latent diffusion model, which may be altered to produce the desired images, is used (more details can be found in the paper). The capacity to fine-tune the generation process is essential because producing pictures at random is not very attractive (as we can see, for instance, in Generative Adversarial Networks).
A neural network model called CLIP (Contrastive Language-Image Pre-training) is used to translate natural language prompts into vector representations. This model, which was trained on 400,000,000 image-text pairs, enables the transformation of a text prompt into a latent space for the diffusion model in the scenario of stable diffusion (more details in that paper).
This figure shows all data flow:
The weights file size for Stable Diffusion model v1 is 4 GB and v2 is 5 GB, making the model quite huge. The v1 model was trained on 256x256 and 512x512 LAION-5B pictures on a 4,000 GPU cluster using over 150.000 NVIDIA A100 GPU hours. The open-source pre-trained model is helpful for us. And we will.
Install
Before utilizing the Python sources for Stable Diffusion v1 on GitHub, we must install Miniconda (assuming Git and Python are already installed):
wget https://repo.anaconda.com/miniconda/Miniconda3-py39_4.12.0-Linux-x86_64.sh
chmod +x Miniconda3-py39_4.12.0-Linux-x86_64.sh
./Miniconda3-py39_4.12.0-Linux-x86_64.sh
conda update -n base -c defaults condaInstall the source and prepare the environment:
git clone https://github.com/CompVis/stable-diffusion
cd stable-diffusion
conda env create -f environment.yaml
conda activate ldm
pip3 install transformers --upgradeDownload the pre-trained model weights next. HiggingFace has the newest checkpoint sd-v14.ckpt (a download is free but registration is required). Put the file in the project folder and have fun:
python3 scripts/txt2img.py --prompt "hello world" --plms --ckpt sd-v1-4.ckpt --skip_grid --n_samples 1Almost. The installation is complete for happy users of current GPUs with 12 GB or more VRAM. RuntimeError: CUDA out of memory will occur otherwise. Two solutions exist.
Running the optimized version
Try optimizing first. After cloning the repository and enabling the environment (as previously), we can run the command:
python3 optimizedSD/optimized_txt2img.py --prompt "hello world" --ckpt sd-v1-4.ckpt --skip_grid --n_samples 1Stable Diffusion worked on my visual card with 8 GB RAM (alas, I did not behave well enough to get NVIDIA A100 for Christmas, so 8 GB GPU is the maximum I have;).
Running Stable Diffusion without GPU
If the GPU does not have enough RAM or is not CUDA-compatible, running the code on a CPU will be 20x slower but better than nothing. This unauthorized CPU-only branch from GitHub is easiest to obtain. We may easily edit the source code to use the latest version. It's strange that a pull request for that was made six months ago and still hasn't been approved, as the changes are simple. Readers can finish in 5 minutes:
Replace if attr.device!= torch.device(cuda) with if attr.device!= torch.device(cuda) and torch.cuda.is available at line 20 of ldm/models/diffusion/ddim.py ().
Replace if attr.device!= torch.device(cuda) with if attr.device!= torch.device(cuda) and torch.cuda.is available in line 20 of ldm/models/diffusion/plms.py ().
Replace device=cuda in lines 38, 55, 83, and 142 of ldm/modules/encoders/modules.py with device=cuda if torch.cuda.is available(), otherwise cpu.
Replace model.cuda() in scripts/txt2img.py line 28 and scripts/img2img.py line 43 with if torch.cuda.is available(): model.cuda ().
Run the script again.
Testing
Test the model. Text-to-image is the first choice. Test the command line example again:
python3 scripts/txt2img.py --prompt "hello world" --plms --ckpt sd-v1-4.ckpt --skip_grid --n_samples 1The slow generation takes 10 seconds on a GPU and 10 minutes on a CPU. Final image:
Hello world is dull and abstract. Try a brush-wielding hamster. Why? Because we can, and it's not as insane as Napoleon's cat. Another image:
Generating an image from a text prompt and another image is interesting. I made this picture in two minutes using the image editor (sorry, drawing wasn't my strong suit):
I can create an image from this drawing:
python3 scripts/img2img.py --prompt "A bird is sitting on a tree branch" --ckpt sd-v1-4.ckpt --init-img bird.png --strength 0.8It was far better than my initial drawing:
I hope readers understand and experiment.
Stable Diffusion UI
Developers love the command line, but regular users may struggle. Stable Diffusion UI projects simplify image generation and installation. Simple usage:
Unpack the ZIP after downloading it from https://github.com/cmdr2/stable-diffusion-ui/releases. Linux and Windows are compatible with Stable Diffusion UI (sorry for Mac users, but those machines are not well-suitable for heavy machine learning tasks anyway;).
Start the script.
Done. The web browser UI makes configuring various Stable Diffusion features (upscaling, filtering, etc.) easy:
V2.1 of Stable Diffusion
I noticed the notification about releasing version 2.1 while writing this essay, and it was intriguing to test it. First, compare version 2 to version 1:
alternative text encoding. The Contrastive LanguageImage Pre-training (CLIP) deep learning model, which was trained on a significant number of text-image pairs, is used in Stable Diffusion 1. The open-source CLIP implementation used in Stable Diffusion 2 is called OpenCLIP. It is difficult to determine whether there have been any technical advancements or if legal concerns were the main focus. However, because the training datasets for the two text encoders were different, the output results from V1 and V2 will differ for the identical text prompts.
a new depth model that may be used to the output of image-to-image generation.
a revolutionary upscaling technique that can quadruple the resolution of an image.
Generally higher resolution Stable Diffusion 2 has the ability to produce both 512x512 and 768x768 pictures.
The Hugging Face website offers a free online demo of Stable Diffusion 2.1 for code testing. The process is the same as for version 1.4. Download a fresh version and activate the environment:
conda deactivate
conda env remove -n ldm # Use this if version 1 was previously installed
git clone https://github.com/Stability-AI/stablediffusion
cd stablediffusion
conda env create -f environment.yaml
conda activate ldmHugging Face offers a new weights ckpt file.
The Out of memory error prevented me from running this version on my 8 GB GPU. Version 2.1 fails on CPUs with the slow conv2d cpu not implemented for Half error (according to this GitHub issue, the CPU support for this algorithm and data type will not be added). The model can be modified from half to full precision (float16 instead of float32), however it doesn't make sense since v1 runs up to 10 minutes on the CPU and v2.1 should be much slower. The online demo results are visible. The same hamster painting with a brush prompt yielded this result:
It looks different from v1, but it functions and has a higher resolution.
The superresolution.py script can run the 4x Stable Diffusion upscaler locally (the x4-upscaler-ema.ckpt weights file should be in the same folder):
python3 scripts/gradio/superresolution.py configs/stable-diffusion/x4-upscaling.yaml x4-upscaler-ema.ckptThis code allows the web browser UI to select the image to upscale:
The copy-paste strategy may explain why the upscaler needs a text prompt (and the Hugging Face code snippet does not have any text input as well). I got a GPU out of memory error again, although CUDA can be disabled like v1. However, processing an image for more than two hours is unlikely:
Stable Diffusion Limitations
When we use the model, it's fun to see what it can and can't do. Generative models produce abstract visuals but not photorealistic ones. This fundamentally limits The generative neural network was trained on text and image pairs, but humans have a lot of background knowledge about the world. The neural network model knows nothing. If someone asks me to draw a Chinese text, I can draw something that looks like Chinese but is actually gibberish because I never learnt it. Generative AI does too! Humans can learn new languages, but the Stable Diffusion AI model includes only language and image decoder brain components. For instance, the Stable Diffusion model will pull NO WAR banner-bearers like this:
V1:
V2.1:
The shot shows text, although the model never learned to read or write. The model's string tokenizer automatically converts letters to lowercase before generating the image, so typing NO WAR banner or no war banner is the same.
I can also ask the model to draw a gorgeous woman:
V1:
V2.1:
The first image is gorgeous but physically incorrect. A second one is better, although it has an Uncanny valley feel. BTW, v2 has a lifehack to add a negative prompt and define what we don't want on the image. Readers might try adding horrible anatomy to the gorgeous woman request.
If we ask for a cartoon attractive woman, the results are nice, but accuracy doesn't matter:
V1:
V2.1:
Another example: I ordered a model to sketch a mouse, which looks beautiful but has too many legs, ears, and fingers:
V1:
V2.1: improved but not perfect.
V1 produces a fun cartoon flying mouse if I want something more abstract:
I tried multiple times with V2.1 but only received this:
The image is OK, but the first version is closer to the request.
Stable Diffusion struggles to draw letters, fingers, etc. However, abstract images yield interesting outcomes. A rural landscape with a modern metropolis in the background turned out well:
V1:
V2.1:
Generative models help make paintings too (at least, abstract ones). I searched Google Image Search for modern art painting to see works by real artists, and this was the first image:
I typed "abstract oil painting of people dancing" and got this:
V1:
V2.1:
It's a different style, but I don't think the AI-generated graphics are worse than the human-drawn ones.
The AI model cannot think like humans. It thinks nothing. A stable diffusion model is a billion-parameter matrix trained on millions of text-image pairs. I input "robot is creating a picture with a pen" to create an image for this post. Humans understand requests immediately. I tried Stable Diffusion multiple times and got this:
This great artwork has a pen, robot, and sketch, however it was not asked. Maybe it was because the tokenizer deleted is and a words from a statement, but I tried other requests such robot painting picture with pen without success. It's harder to prompt a model than a person.
I hope Stable Diffusion's general effects are evident. Despite its limitations, it can produce beautiful photographs in some settings. Readers who want to use Stable Diffusion results should be warned. Source code examination demonstrates that Stable Diffusion images feature a concealed watermark (text StableDiffusionV1 and SDV2) encoded using the invisible-watermark Python package. It's not a secret, because the official Stable Diffusion repository's test watermark.py file contains a decoding snippet. The put watermark line in the txt2img.py source code can be removed if desired. I didn't discover this watermark on photographs made by the online Hugging Face demo. Maybe I did something incorrectly (but maybe they are just not using the txt2img script on their backend at all).
Conclusion
The Stable Diffusion model was fascinating. As I mentioned before, trying something yourself is always better than taking someone else's word, so I encourage readers to do the same (including this article as well;).
Is Generative AI a game-changer? My humble experience tells me:
I think that place has a lot of potential. For designers and artists, generative AI can be a truly useful and innovative tool. Unfortunately, it can also pose a threat to some of them since if users can enter a text field to obtain a picture or a website logo in a matter of clicks, why would they pay more to a different party? Is it possible right now? unquestionably not yet. Images still have a very poor quality and are erroneous in minute details. And after viewing the image of the stunning woman above, models and fashion photographers may also unwind because it is highly unlikely that AI will replace them in the upcoming years.
Today, generative AI is still in its infancy. Even 768x768 images are considered to be of a high resolution when using neural networks, which are computationally highly expensive. There isn't an AI model that can generate high-resolution photographs natively without upscaling or other methods, at least not as of the time this article was written, but it will happen eventually.
It is still a challenge to accurately represent knowledge in neural networks (information like how many legs a cat has or the year Napoleon was born). Consequently, AI models struggle to create photorealistic photos, at least where little details are important (on the other side, when I searched Google for modern art paintings, the results are often even worse;).
When compared to the carefully chosen images from official web pages or YouTube reviews, the average output quality of a Stable Diffusion generation process is actually less attractive because to its high degree of randomness. When using the same technique on their own, consumers will theoretically only view those images as 1% of the results.
Anyway, it's exciting to witness this area's advancement, especially because the project is open source. Google's Imagen and DALL-E 2 can also produce remarkable findings. It will be interesting to see how they progress.
Jonathan Vanian
3 years ago
What is Terra? Your guide to the hot cryptocurrency
With cryptocurrencies like Bitcoin, Ether, and Dogecoin gyrating in value over the past few months, many people are looking at so-called stablecoins like Terra to invest in because of their more predictable prices.
Terraform Labs, which oversees the Terra cryptocurrency project, has benefited from its rising popularity. The company said recently that investors like Arrington Capital, Lightspeed Venture Partners, and Pantera Capital have pledged $150 million to help it incubate various crypto projects that are connected to Terra.
Terraform Labs and its partners have built apps that operate on the company’s blockchain technology that helps keep a permanent and shared record of the firm’s crypto-related financial transactions.
Here’s what you need to know about Terra and the company behind it.
What is Terra?
Terra is a blockchain project developed by Terraform Labs that powers the startup’s cryptocurrencies and financial apps. These cryptocurrencies include the Terra U.S. Dollar, or UST, that is pegged to the U.S. dollar through an algorithm.
Terra is a stablecoin that is intended to reduce the volatility endemic to cryptocurrencies like Bitcoin. Some stablecoins, like Tether, are pegged to more conventional currencies, like the U.S. dollar, through cash and cash equivalents as opposed to an algorithm and associated reserve token.
To mint new UST tokens, a percentage of another digital token and reserve asset, Luna, is “burned.” If the demand for UST rises with more people using the currency, more Luna will be automatically burned and diverted to a community pool. That balancing act is supposed to help stabilize the price, to a degree.
“Luna directly benefits from the economic growth of the Terra economy, and it suffers from contractions of the Terra coin,” Terraform Labs CEO Do Kwon said.
Each time someone buys something—like an ice cream—using UST, that transaction generates a fee, similar to a credit card transaction. That fee is then distributed to people who own Luna tokens, similar to a stock dividend.
Who leads Terra?
The South Korean firm Terraform Labs was founded in 2018 by Daniel Shin and Kwon, who is now the company’s CEO. Kwon is a 29-year-old former Microsoft employee; Shin now heads the Chai online payment service, a Terra partner. Kwon said many Koreans have used the Chai service to buy goods like movie tickets using Terra cryptocurrency.
Terraform Labs does not make money from transactions using its crypto and instead relies on outside funding to operate, Kwon said. It has raised $57 million in funding from investors like HashKey Digital Asset Group, Divergence Digital Currency Fund, and Huobi Capital, according to deal-tracking service PitchBook. The amount raised is in addition to the latest $150 million funding commitment announced on July 16.
What are Terra’s plans?
Terraform Labs plans to use Terra’s blockchain and its associated cryptocurrencies—including one pegged to the Korean won—to create a digital financial system independent of major banks and fintech-app makers. So far, its main source of growth has been in Korea, where people have bought goods at stores, like coffee, using the Chai payment app that’s built on Terra’s blockchain. Kwon said the company’s associated Mirror trading app is experiencing growth in China and Thailand.
Meanwhile, Kwon said Terraform Labs would use its latest $150 million in funding to invest in groups that build financial apps on Terra’s blockchain. He likened the scouting and investing in other groups as akin to a “Y Combinator demo day type of situation,” a reference to the popular startup pitch event organized by early-stage investor Y Combinator.
The combination of all these Terra-specific financial apps shows that Terraform Labs is “almost creating a kind of bank,” said Ryan Watkins, a senior research analyst at cryptocurrency consultancy Messari.
In addition to cryptocurrencies, Terraform Labs has a number of other projects including the Anchor app, a high-yield savings account for holders of the group’s digital coins. Meanwhile, people can use the firm’s associated Mirror app to create synthetic financial assets that mimic more conventional ones, like “tokenized” representations of corporate stocks. These synthetic assets are supposed to be helpful to people like “a small retail trader in Thailand” who can more easily buy shares and “get some exposure to the upside” of stocks that they otherwise wouldn’t have been able to obtain, Kwon said. But some critics have said the U.S. Securities and Exchange Commission may eventually crack down on synthetic stocks, which are currently unregulated.
What do critics say?
Terra still has a long way to go to catch up to bigger cryptocurrency projects like Ethereum.
Most financial transactions involving Terra-related cryptocurrencies have originated in Korea, where its founders are based. Although Terra is becoming more popular in Korea thanks to rising interest in its partner Chai, it’s too early to say whether Terra-related currencies will gain traction in other countries.
Terra’s blockchain runs on a “limited number of nodes,” said Messari’s Watkins, referring to the computers that help keep the system running. That helps reduce latency that may otherwise slow processing of financial transactions, he said.
But the tradeoff is that Terra is less “decentralized” than other blockchain platforms like Ethereum, which is powered by thousands of interconnected computing nodes worldwide. That could make Terra less appealing to some blockchain purists.