His story will inspire you.

“Google search went down for a few hours in 2002; Jeff Dean handled all the queries by hand and checked quality doubled.”- Jeff Dean Facts.

One of many Jeff Dean jokes, but you get the idea.

Google's top six engineers met in a war room in mid-2000. Google's crawling system, which indexed the Web, stopped working. Users could still enter queries, but results were five months old.

Google just signed a deal with Yahoo to power a ten-times-larger search engine. Tension rose. It was crucial. If they failed, the Yahoo agreement would likely fall through, risking bankruptcy for the firm. Their efforts could be lost.

A rangy, tall, energetic thirty-one-year-old man named Jeff dean was among those six brilliant engineers in the makeshift room. He had just left D. E. C. a couple of months ago and started his career in a relatively new firm Google, which was about to change the world. He rolled his chair over his colleague Sanjay and sat right next to him, cajoling his code like a movie director. The history started from there.

When you think of people who shaped the World Wide Web, you probably picture founders and CEOs like Larry Page and Sergey Brin, Marc Andreesen, Tim Berners-Lee, Bill Gates, and Mark Zuckerberg. They’re undoubtedly the brightest people on earth.

Under these giants, legions of anonymous coders work at keyboards to create the systems and products we use. These computer workers are irreplaceable.

Let's get to know him better.

It's possible you've never heard of Jeff Dean. He's American. Dean created many behind-the-scenes Google products. Jeff, co-founder and head of Google's deep learning research engineering team, is a popular technology, innovation, and AI keynote speaker.

While earning an MS and Ph.D. in computer science at the University of Washington, he was a teaching assistant, instructor, and research assistant. Dean joined the Compaq Computer Corporation Western Research Laboratory research team after graduating.

Jeff co-created ProfileMe and the Continuous Profiling Infrastructure for Digital at Compaq. He co-designed and implemented Swift, one of the fastest Java implementations. He was a senior technical staff member at mySimon Inc., retrieving and caching electronic commerce content.

Dean, a top young computer scientist, joined Google in mid-1999. He was always trying to maximize a computer's potential as a child.

An expert

His high school program for processing massive epidemiological data was 26 times faster than professionals'. Epi Info, in 13 languages, is used by the CDC. He worked on compilers as a computer science Ph.D. These apps make source code computer-readable.

Dean never wanted to work on compilers forever. He left Academia for Google, which had less than 20 employees. Dean helped found Google News and AdSense, which transformed the internet economy. He then addressed Google's biggest issue, scaling.

Growing Google faced a huge computing challenge. They developed PageRank in the late 1990s to return the most relevant search results. Google's popularity slowed machine deployment.

Dean solved problems, his specialty. He and fellow great programmer Sanjay Ghemawat created the Google File System, which distributed large data over thousands of cheap machines.

These two also created MapReduce, which let programmers handle massive data quantities on parallel machines. They could also add calculations to the search algorithm. A 2004 research article explained MapReduce, which became an industry sensation.

Several revolutionary inventions

Dean's other initiatives were also game-changers. BigTable, a petabyte-capable distributed data storage system, was based on Google File. The first global database, Spanner, stores data on millions of servers in dozens of data centers worldwide.

It underpins Gmail and AdWords. Google Translate co-founder Jeff Dean is surprising. He contributes heavily to Google News. Dean is Senior Fellow of Google Research and Health and leads Google AI.

Recognitions

The National Academy of Engineering elected Dean in 2009. He received the 2009 Association for Computing Machinery fellowship and the 2016 American Academy of Arts and Science fellowship. He received the 2007 ACM-SIGOPS Mark Weiser Award and the 2012 ACM-Infosys Foundation Award. Lists could continue.

A sneaky question may arrive in your mind: How much does this big brain earn? Well, most believe he is one of the highest-paid employees at Google. According to a survey, he is paid $3 million a year.

He makes espresso and chats with a small group of Googlers most mornings. Dean steams milk, another grinds, and another brews espresso. They discuss families and technology while making coffee. He thinks this little collaboration and idea-sharing keeps Google going.

“Some of us have been working together for more than 15 years,” Dean said. “We estimate that we’ve collectively made more than 20,000 cappuccinos together.”

We all know great developers and software engineers. It may inspire many.

A friend told me of an incident she found particularly irritating: a retailer where she is a frequent client, with an account and loyalty card, asked for the item's receipt.

We all know that stores collect every bit of data they can on us, including our socio-demographic profile, address, shopping habits, and everything we've ever bought, so why would they need a fading receipt? Who knows? That their consumers try to pass off other goods? It's easy to verify past transactions to see when the item was purchased.

That's it. Why require receipts? Companies send us incentives, discounts, and other marketing, yet when we need something, we have to prove we're not cheating.

Why require us to preserve data and documents when our governments and governmental institutions already have them? Why do I need to carry documents like my driver's license if the authorities can check if I have one and what state it's in once I prove my identity?

We shouldn't be required to give someone data or documents they already have. The days of waiting up with our paperwork for a stern official to inform us something is missing are over.

How can retailers still ask if you have a receipt if we've made our slow, bureaucratic, and all-powerful government sensible? Then what? The shop may not accept your return (which has a two-year window, longer than most purchase tickets last) or they may just let you replace the item.

Isn't this an anachronism in the age of CRMs, customer files that know what we ate for breakfast, and loyalty programs? If government and bureaucracies have learnt to use its own files and make life easier for the consumer, why do retailers ask for a receipt?

They're adding friction to the system. They know we can obtain a refund, use our warranty, or get our money back. But if I ask for ludicrous criteria, like keeping the purchase receipt in your wallet (wallet? another anachronism, if I leave the house with only my smartphone! ), it will dissuade some individuals and tip the scales in their favor when it comes to limiting returns. Some manager will take credit for lowering returns and collect her annual bonus. Having the wrong metrics is common in management.

To slow things down, asking for a receipt is like asking us to perform a handstand and leap 20 times on one foot. You have my information, use it to send me everything, and know everything I've bought, yet when I need a two-way service, you refuse to utilize it and require that I keep it and prove it.

Refuse as customers. If retailers want our business, they should treat us well, not just when we spend money. If I come to return a product, claim its use or warranty, or be taught how to use it, I am the same person you treated wonderfully when I bought it. Remember that, and act accordingly.

A store should use my information for everything, not just what it wants. Keep my info, but don't sell me anything.

Trigger warning — Andrew Tate is running a genius marketing campaign

Andrew Tate is a 2022 internet celebrity.

Kickboxing world champion became rich playboy with controversial views on gender roles.

Andrew's get-rich-quick scheme isn't new. His social media popularity is impressive.

He’s currently running one of the most genius marketing campaigns in history.

He pulls society's pendulum away from diversity and inclusion and toward diversion and exclusion. He's unstoppable.

Here’s everything you need to know about Andrew Tate. And how he’s playing chess while the world plays checkers.

Cobra Tate is the name he goes by.

American-born, English-raised entrepreneur Andrew Tate lives in Romania.

Romania? Says Andrew,

“I prefer a country in which corruption is available to everyone.”

Andrew was a professional kickboxer with the ring moniker Cobra before starting Hustlers University.

Before that, he liked chess and worshipped his father.

Emory Andrew Tate III is named after his grandmaster chess player father.

Emory was the first black-American chess champion. He was military, martial arts-trained, and multilingual. A superhuman.

He lived in his car to make ends meet.

Andrew and Tristan relocated to England with their mother when their parents split.

It was there that Andrew began his climb toward becoming one of the internet’s greatest villains.

Andrew fell in love with kickboxing.

Andrew spent his 20s as a professional kickboxer and reality TV star, featuring on Big Brother UK and The Ultimate Traveller.

These 3 incidents, along with a chip on his shoulder, foreshadowed Andrews' social media breakthrough.

• Chess

• Combat sports

• Reality television

A dangerous trio.

Andrew started making money online after quitting kickboxing in 2017 due to an eye issue.

Andrew didn't suddenly become popular.

Andrew's web work started going viral in 2022.

Due to his contentious views on patriarchy and gender norms, he's labeled the King of Toxic Masculinity. His most contentious views (trigger warning):

• “Women are intrinsically lazy.”

• “Female promiscuity is disgusting.”

• “Women shouldn’t drive cars or fly planes.”

• “A lot of the world’s problems would be solved if women had their body count tattooed on their foreheads.”

Andrew's two main beliefs are:

1. “These are my personal opinions based on my experiences.”

2. “I believe men are better at some things and women are better at some things. We are not equal.”

Andrew intentionally offends.

Andrew's thoughts began circulating online in 2022.

In July 2022, he was one of the most Googled humans, surpassing:

• Joe Biden

• Donald Trump

• Kim Kardashian

Andrews' rise is a mystery since no one can censure or suppress him. This is largely because Andrew nor his team post his clips.

But more on that later.

Andrew's path to wealth.

Andrew Tate is a self-made millionaire. His morality is uncertain.

Andrew and Tristan needed money soon after retiring from kickboxing.

“I owed some money to some dangerous people. I had $70K and needed $100K to stay alive.”

Andrews lost $20K on roulette at a local casino.

Andrew had one week to make $50,000, so he started planning. Andrew locked himself in a chamber like Thomas Edison to solve an energy dilemma.

He listed his assets.

• Physical strength (but couldn’t fight)

• a BMW (worth around $20K)

• Intelligence (but no outlet)

A lightbulb.

He had an epiphany after viewing a webcam ad. He sought aid from women, ironically. His 5 international girlfriends are assets.

Then, a lightbulb.

Andrew and Tristan messaged and flew 7 women to a posh restaurant. Selling desperation masked as opportunity, Andrew pitched his master plan:

A webcam business — with a 50/50 revenue split.

5 women left.

2 stayed.

Andrew Tate, a broke kickboxer, became Top G, Cobra Tate.

The business model was simple — yet sad.

Andrew's girlfriends moved in with him and spoke online for 15+ hours a day. Andrew handled ads and equipment as the women posed.

Andrew eventually took over their keyboards, believing he knew what men wanted more than women.

Andrew detailed on the Full Send Podcast how he emotionally manipulated men for millions. They sold houses, automobiles, and life savings to fuel their companionship addiction.

When asked if he felt bad, Andrew said,

“F*ck no.“

Andrew and Tristan wiped off debts, hired workers, and diversified.

Tristan supervised OnlyFans models.

Andrew bought Romanian casinos and MMA league RXF (Real Xtreme Fighting).

Pandemic struck suddenly.

Andrew couldn't run his 2 businesses without a plan. Another easy moneymaker.

He banked on Hustlers University.

The actual cause of Andrew's ubiquity.

On a Your Mom’s House episode Andrew's 4 main revenue sources:

1. Hustler’s University

2. Owning casinos in Romania

3. Owning 10% of the Romanian MMA league “RXF”

4. “The War Room” — a society of rich and powerful men

When the pandemic hit, 3/4 became inoperable.

So he expanded Hustlers University.

But what is Hustler’s University?

Andrew says Hustlers University teaches 18 wealth-building tactics online. Examples:

• Real estate

• Copywriting

• Amazon FBA

• Dropshipping

• Flipping Cryptos

How to swiftly become wealthy.

Lessons are imprecise, rudimentary, and macro-focused, say reviews. Invest wisely, etc. Everything is free online.

You pay for community. One unique income stream.

The only money-making mechanism that keeps the course from being a scam.

The truth is, many of Andrew’s students are actually making money. Maybe not from the free YouTube knowledge Andrew and his professors teach in the course, but through Hustler’s University’s affiliate program.

Affiliates earn 10% commission for each new student = $5.

Students can earn $10 for each new referral in the first two months.

Andrew earns $50 per membership per month.

This affiliate program isn’t anything special — in fact, it’s on the lower end of affiliate payouts. Normally, it wouldn’t be very lucrative.

But it has one secret weapon— Andrew and his viral opinions.

Andrew is viral. Andrew went on a media tour in January 2022 after appearing on Your Mom's House.

• The Full Send Podcast

• The Fresh & Fit Podcast

• “BFFs” by Barstool Sports

And many, many more…

He chatted with Twitch streamers. Hustlers University wanted more controversy (and clips).

Here’s the strategy behind Hustler’s University that has (allegedly) earned students upwards of $10K per month:

1. Make a social media profile with Andrew Tates' name and photo.

2. Post any of the online videos of Andrews that have gone viral.

3. Include a referral link in your bio.

Effectively simple.

Andrew's controversy attracts additional students. More student clips circulate as more join. Andrew's students earn more and promote the product as he goes viral.

A brilliant plan that's functioning.

At the beginning of his media tour, Hustler’s University had 5,000 students. 6 months in, and he now has over 100,000.

One income stream generates $5 million every month.

Andrew's approach is not new.

But it is different.

In the early 2010s, Tai Lopez dominated the internet.

His viral video showed his house.

“Here in my garage. Just bought this new Lamborghini.”

Tais' marketing focused on intellect, not strength, power, and wealth to attract women.

How reading quicker leads to financial freedom in 67 steps.

Years later, it was revealed that Tai Lopez rented the mansion and Lamborghini as a marketing ploy to build social proof. Meanwhile, he was living in his friend’s trailer.

Faked success is an old tactic.

Andrew is doing something similar. But with one major distinction.

Andrew outsources his virality — making him nearly impossible to cancel.

In 2022, authorities searched Andrews' estate over human trafficking suspicions. Investigation continues despite withdrawn charges.

Andrew's divisive nature would normally get him fired. Andrew's enterprises and celebrity don't rely on social media.

He doesn't promote or pay for ads. Instead, he encourages his students and anyone wishing to get rich quick to advertise his work.

Because everything goes through his affiliate program. Old saying:

“All publicity is good publicity.”

Final thoughts: it’s ok to feel triggered.

Tate is divisive.

His emotionally charged words are human nature. Andrews created the controversy.

It's non-personal.

His opinions are those of one person. Not world nor generational opinion.

Briefly:

• It's easy to understand why Andrews' face is ubiquitous. Money.

• The world wide web is a chessboard. Misdirection is part of it.

• It’s not personal, it’s business.

• Controversy sells

Sometimes understanding the ‘why’, can help you deal with the ‘what.’

After a crazy second half of 2021 and significant trade volumes into 2022, the market for NFT artworks like Bored Ape Yacht Club, CryptoPunks, and Pudgy Penguins has begun a sharp collapse as market downturns hit token values.

DappRadar data shows NFT monthly sales have fallen below $1 billion since June 2021. OpenSea, the world's largest NFT exchange, has seen sales volume decline 75% since May and is trading like July 2021.

Prices of popular non-fungible tokens have also decreased. Bored Ape Yacht Club (BAYC) has witnessed volume and sales drop 63% and 15%, respectively, in the past month.

BeInCrypto analysis shows market decline. May 2022 cryptocurrency marketplace volume was $4 billion, according to a news platform. This is a sharp drop from April's $7.18 billion.

OpenSea, a big marketplace, contributed $2.6 billion, while LooksRare, Magic Eden, and Solanart also contributed.

NFT markets are digital platforms for buying and selling tokens, similar stock trading platforms. Although some of the world's largest exchanges offer NFT wallets, most users store their NFTs on their favorite marketplaces.

In January 2022, overall NFT sales volume was $16.57 billion, with LooksRare contributing $11.1 billion. May 2022's volume was $12.57 less than January, a 75% drop, and June's is expected to be considerably smaller.

A World Based on Utility

Despite declines in NFT trading volumes, not all investors are negative on NFTs. Although there are uncertainties about the sustainability of NFT-based art collections, there are fewer reservations about utility-based tokens and their significance in technology's future.

In June, business CEO Christof Straub said NFTs may help artists monetize unreleased content, resuscitate catalogs, establish deeper fan connections, and make processes more efficient through technology.

We all know NFTs can't be JPEGs. Straub noted that NFT music rights can offer more equitable rewards to musicians.

Music NFTs are here to stay if they have real value, solve real problems, are trusted and lawful, and have fair and sustainable business models.

NFTs can transform numerous industries, including music. Market opinion is shifting towards tokens with more utility than the social media artworks we're used to seeing.

While the major NFT names remain dominant in terms of volume, new utility-based initiatives are emerging as top 20 collections.

Otherdeed, Sorare, and NBA Top Shot are NFT-based games that rank above Bored Ape Yacht Club and Cryptopunks.

Users can switch video NFTs of basketball players in NBA Top Shot. Similar efforts are emerging in the non-fungible landscape.

Sorare shows how NFTs can support a new way of playing fantasy football, where participants buy and swap trading cards to create a 5-player team that wins rewards based on real-life performances.

Sorare raised 579.7 million in one of Europe's largest Series B financing deals in September 2021. Recently, the platform revealed plans to expand into Major League Baseball.

Strong growth indications suggest a promising future for NFTs. The value of art-based collections like BAYC and CryptoPunks may be questioned as markets become diluted by new limited collections, but the potential for NFTs to become intrinsically linked to tangible utility like online gaming, music and art, and even corporate reward schemes shows the industry has a bright future.

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 conda

Install 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 --upgrade

Download 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 1

Almost. 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 1

Stable 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 1

The 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 0.8

It 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 ldm

Hugging 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.ckpt

This 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.

This is arguably the best three-minute demonstration I've ever seen of anything. Derek Sivers turns a shaky video of a lone dancing guy at a music festival into a leadership lesson.

A leader must have the courage to stand alone and appear silly. But what he's doing is so straightforward that it's almost instructive. This is critical. You must be simple to follow!

Now comes the first follower, who plays an important role: he publicly demonstrates how to follow. The leader embraces him as an equal, so it's no longer about the leader — it's about them, plural. He's inviting his friends to join him. It takes courage to be the first follower! You stand out and dare to be mocked. Being a first follower is a style of leadership that is underappreciated. The first follower elevates a lone nut to the position of leader. If the first follower is the spark that starts the fire, the leader is the flint.

This link was sent to me by @ottmark, who noted its resemblance to Kurt Vonnegut's three categories of specialists required for revolution.

The rarest of these specialists, he claims, is an actual genius – a person capable generating seemingly wonderful ideas that are not widely known. "A genius working alone is generally dismissed as a crazy," he claims.

The second type of specialist is much easier to find: a highly intellectual person in good standing in his or her community who understands and admires the genius's new ideas and can attest that the genius is not insane. "A person like him working alone can only crave loudly for changes, but fail to say what their shapes should be," Slazinger argues.

Jeff Veen reduced the three personalities to "the inventor, the investor, and the evangelist" on Twitter.