Quick, easy and tasty (and dollops of parenting around food).

My wife and mom are both great mothers. They're super-efficient planners. They soak and ferment food. My 104-year-old grandfather loved fermented foods.

When I'm hungry and need something fast, I waffle to the pantry. Like most people, I like to improvise. I wish I knew these 11 hacks sooner.

1. The world's best pasta sauce only has 3 ingredients.

You watch recipe videos with prepped ingredients. In reality, prepping and washing take time. The food's taste isn't guaranteed. The raw truth at a sublime level is not talked about often.

Sometimes a radical recipe comes along that's so easy and tasty, you're dumbfounded. The Classic Italian Cook Book has a pasta recipe.

One 28-ounce can of whole, peeled tomatoes, one medium peeled onion, and 5 tablespoons of butter. And salt to taste.

Combine everything in a single pot and simmer for 45 minutes, uncovered. Stir occasionally. Toss the onion halves after 45 minutes and pour the sauce over pasta. Finish!

This simple recipe fights our deepest fears.

Salt to taste! Customized to perfection, no frills.

2. Reheating rice with ice. Magical.

Most of the world eats rice. I was raised in south India. My grandfather farmed rice in the Cauvery river delta.

The problem with rice With growing kids, you can't cook just enough. Leftovers are a norm. Microwaves help most people. Ice cubes are the frosting.

Before reheating rice in the microwave, add an ice cube. The ice will steam the rice, making it fluffy and delicious again.

3. Pineapple leaf 

if it comes off easy, it is ripe enough to cut. No rethinking.

My daughter loves pineapples like her dad. One daddy task is cutting them. Sharing immediate results is therapeutic.

Timing the cut has been the most annoying part over the years. The pineapple leaf tip reveals the fruitiness inside. Always loved it.

4. Magic knife words (rolling and curling)

Cutting hand: Roll the blade's back, not its tip, to cut.

Other hand: If you can’t see your finger tips, you can’t cut them. So curl your fingers.

I dislike that schools don't teach financial literacy or cutting skills.

My wife and I used scissors differently for 25 years. We both used the thumb. My index finger, her middle. We googled the difference when I noticed it and laughed. She's right.

This video teaches knifing skills:

5. Best advice about heat

If it's done in the pan, it's overdone on the plate.

This simple advice stands out when we worry about ingredients and proportions.

6. The truth about pasta water

Pasta water should be sea-salty.

Properly seasoning food separates good from great. Salt depends is a good line.

Want delicious pasta? Well, then kind of a lot, to be perfectly honest.

7. Clean as you go

Clean blender as you go by blending water and dish soap.

I find clean as you go easier than clean afterwords. This easy tip is gold.

8. Clean as you go (bis)

Microwave a bowl of water, vinegar, and a toothpick for 5 minutes.

2 cups water, 2 tablespoons vinegar, and a toothpick to prevent overflow.

5-minute microwave. Let the steam work for another 2 minutes. Sponge-off dirt and food. Simple.

9 and 10. Tools,tools, tools

Immersion blender and pressure cooker save time and money.

Narrative: I experienced fatherly pride. My middle-schooler loves science. We discussed boiling. I spoke. Water doesn't need 100°C to boil. She looked confused. 100 degrees assume something. The world around the water is a normal room. Changing water pressure affects its boiling point. This saves energy. Pressure cooker magic.

I captivated her. She's into science and sustainable living.

Whistling is a subliminal form of self-expression when done right. Pressure cookers remind me of simple pleasures.

Your handiness depends on your home tools. Immersion blenders are great for pre- and post-cooking. It eliminates chopping and washing. Second to the dishwasher, in my opinion.

11. One pepper is plenty

A story I share with my daughters.

Once, everyone thought about spice (not spicy). More valuable than silk. One of the three mighty oceans was named after a source country. Columbus sailed the wrong way and found America. The explorer called the natives after reaching his spice destination.

It was pre-internet days. His Google wasn't working.

My younger daughter listens in awe. Strong roots. Image cast. She can contextualize one of the ocean names.

I struggle with spices in daily life. Combinations are mind-boggling. I have more spices than Columbus. Flavor explosion has repercussions. You must closely follow the recipe without guarantees. Best aha. Double down on one spice and move on. If you like it, it's great.

I naturally gravitate towards cumin soups, fennel dishes, mint rice, oregano pasta, basil thai curry and cardamom pudding.

Variety enhances life. Each of my dishes is unique.

To each their own comfort food and nostalgic memories.

Happy living!

I’m a permaculture farmer. I want to create food-producing ecosystems. My hope is a world with easy access to a cuisine that nourishes consumers, supports producers, and leaves the Earth joyously habitable.

Permaculturists, natural farmers, plantsmen, and foodies share this ambition. I believe this group of green thumbs, stock-folk, and food champions is falling to tribalism, forgetting that rescuing the globe requires saving all of its inhabitants, even those who adore cheap burgers and Coke. We're digging foxholes and turning folks who disagree with us or don't understand into monsters.

Take Dr. Daphne Miller's comments at the end of her Slow Money Journal interview:

“Americans are going to fall into two camps when all is said and done: People who buy cheap goods, regardless of quality, versus people who are willing and able to pay for things that are made with integrity. We are seeing the limits of the “buying cheap crap” approach.”

This is one of the most judgmental things I've read outside the Bible. Consequences:

• People who purchase inexpensive things (food) are ignorant buffoons who prefer to choose fair trade coffee over fuel as long as the price is correct.

• It all depends on your WILL to buy quality or cheaply. Both those who are WILLING and those who ARE NOT exist. And able, too.

• People who are unwilling and unable are purchasing garbage. You're giving your kids bad food. Both the Earth and you are being destroyed by your actions. Your camp is the wrong one. You’re garbage! Disgrace to you.

Dr. Miller didn't say it, but words are worthless until interpreted. This interpretation depends on the interpreter's economic, racial, political, religious, family, and personal history. Complementary language insults another. Imagine how that Brown/Harvard M.D.'s comment sounds to a low-income household with no savings.

Dr. Miller's comment reflects the echo chamber into which nearly all clean food advocates speak. It asks easy questions and accepts non-solutions like raising food prices and eating less meat. People like me have cultivated an insular world unencumbered by challenges beyond the margins. We may disagree about technical details in rotationally-grazing livestock, but we short circuit when asked how our system could supply half the global beef demand. Most people have never seriously considered this question. We're so loved and affirmed that challenging ourselves doesn't seem necessary. Were generals insisting we don't need to study the terrain because God is on our side?

“Yes, the $8/lb ground beef is produced the way it should be. Yes, it’s good for my body. Yes it’s good for the Earth. But it’s eight freaking dollars, and my kid needs braces and protein. Bye Felicia, we’re going to McDonald’s.”

-Bobby Q. Homemaker

Funny clean foodies. People don't pay enough for food; they should value it more. Turn the concept of buying food with integrity into a wedge and drive it into the heart of America, dividing the willing and unwilling.

We go apeshit if you call our products high-end.

I've heard all sorts of gaslighting to defend a $10/lb pork chop as accessible (things I’ve definitely said in the past):

• At Whole Foods, it costs more.

• The steak at the supermarket is overly affordable.

• Pay me immediately or the doctor gets paid later.

I spoke with Timbercreek Market and Local Food Hub in front of 60 people. We were asked about local food availability.

They came to me last, after my co-panelists gave the same responses I would have given two years before.

I grumbled, "Our food is inaccessible." Nope. It's beyond the wallets of nearly everyone, and it's the biggest problem with sustainable food systems. We're criminally unserious about being leaders in sustainability until we propose solutions beyond economic relativism, wishful thinking, and insisting that vulnerable, distracted people do all the heavy lifting of finding a way to afford our food. And until we talk about solutions, all this preserve the world? False.

The room fell silent as if I'd revealed a terrible secret. Long, thunderous applause followed my other remarks. But I’m probably not getting invited back to any VNRLI events.

I make pricey cuisine. It’s high-end. I have customers who really have to stretch to get it, and they let me know it. They're forgoing other creature comforts to help me make a living and keep the Earth of my grandmothers alive, and they're doing it as an act of love. They believe in us and our work.

I remember it when I'm up to my shoulders in frigid water, when my vehicle stinks of four types of shit, when I come home covered in blood and mud, when I'm hauling water in 100-degree heat, when I'm herding pigs in a rainstorm and dodging lightning bolts to close the chickens. I'm reminded I'm not alone. Their enthusiasm is worth more than money; it helps me make a life and a living. I won't label that gift less than it is to make my meal seem more accessible.

Not everyone can sacrifice.

Let's not pretend we want to go back to peasant fare, despite our nostalgia. Industrial food has leveled what rich and poor eat. How food is cooked will be the largest difference between what you and a billionaire eat. Rich and poor have access to chicken, pork, and beef. You might be shocked how recently that wasn't the case. This abundance, particularly of animal protein, has helped vulnerable individuals.

Industrial food causes environmental damage, chronic disease, and distribution inequities. Clean food promotes non-industrial, artisan farming. This creates a higher-quality, more expensive product than the competition; we respond with aggressive marketing and the "people need to value food more" shtick geared at consumers who can spend the extra money.

The guy who is NOT able is rendered invisible by clean food's elitist marketing, which is bizarre given a.) clean food insists it's trying to save the world, yet b.) MOST PEOPLE IN THE WORLD ARE THAT GUY. No one can help him except feel-good charities. That's crazy.

Also wrong: a foodie telling a kid he can't eat a 99-cent fast food hamburger because it lacks integrity. Telling him how easy it is to save his ducketts and maybe have a grass-fed house burger at the end of the month as a reward, but in the meantime get your protein from canned beans you can't bake because you don't have a stove and, even if you did, your mom works two jobs and moonlights as an Uber driver so she doesn't have time to heat that shitup anyway.

A wealthy person's attitude toward the poor is indecent. It's 18th-century Versailles.

Human rights include access to nutritious food without social or environmental costs. As a food-forest-loving permaculture farmer, I no longer balk at the concept of cultured beef and hydroponics. My food is out of reach for many people, but access to decent food shouldn't be. Cultures and hydroponics could scale to meet the clean food affordability gap without externalities. If technology can deliver great, affordable beef without environmental negative effects, I can't reject it because it's new, unusual, or might endanger my business.

Why is your farm needed if cultured beef and hydroponics can feed the world? Permaculture food forests with trees, perennial plants, and animals are crucial to economically successful environmental protection. No matter how advanced technology gets, we still need clean air, water, soil, greenspace, and food.

Clean Food cultivated in/on live soil, minimally processed, and eaten close to harvest is part of the answer, not THE solution. Clean food advocates must recognize the conflicts at the intersection of environmental, social, and economic sustainability, the disproportionate effects of those conflicts on the poor and lower-middle classes, and the immorality and impracticality of insisting vulnerable people address those conflicts on their own and judging them if they don't.

Our clients, relatives, friends, and communities need an honest assessment of our role in a sustainable future. If we're serious about preserving the world, we owe honesty to non-customers. We owe our goal and sanity to honesty. Future health and happiness of the world left to the average person's pocketbook and long-term moral considerations is a dismal proposition with few parallels.

Let's make soil and grow food. Let the lab folks do their thing. We're all interdependent.

Jobs' secret emails became public due to a litigation with Samsung.

Steve Jobs sent Phil Schiller an email at the end of 2010. Top 100 A was the codename for Apple's annual Top 100 executive meetings. The 2011 one was scheduled.

Everything about this gathering is secret, even attendance. The location is hidden, and attendees can't even drive themselves. Instead, buses transport them to a 2-3 day retreat.

Due to a litigation with Samsung, this Top 100 meeting's agenda was made public in 2014. This was a critical milestone in Apple's history, not a Top 100 meeting. Apple had many obstacles in the 2010s to remain a technological leader. Apple made more money with non-PC goods than with its best-selling Macintosh series. This was the last Top 100 gathering Steve Jobs would attend before passing, and he wanted to make sure his messages carried on before handing over his firm to Tim Cook.

In this post, we'll discuss lessons from Jobs' meeting agenda. Two sorts of entrepreneurs can use these tips:

1. Those who manage a team in a business and must ensure that everyone is working toward the same goals, upholding the same principles, and being inspired by the same future.

2. Those who are sole proprietors or independent contractors and who must maintain strict self-discipline in order to stay innovative in their industry and adhere to their own growth strategy.

Here's Steve Jobs's email outlining the annual meeting agenda. It's an 11-part summary of the company's shape and strategy.

Steve Jobs outlines Apple's 2011 strategy, 10/24/10

1. Correct your data

Business leaders must comprehend their company's metrics. Jobs either mentions critical information he already knows or demands slides showing the numbers he wants. These numbers fall under 2 categories:

Metrics for growth and strategy

• As we will see, this was a crucial statistic for Apple since it signaled the beginning of the Post PC era and required them to make significant strategic changes in order to stay ahead of the curve. Post PC products now account for 66% of our revenues.

• Within six months, iPad outsold Mac, another sign of the Post-PC age. As we will see, Jobs thought the iPad would be the next big thing, and item number four on the agenda is one of the most thorough references to the iPad.

• Geographical analysis: Here, Jobs emphasizes China, where the corporation has a slower start than anticipated. China was dominating Apple's sales growth with 16% of revenue one year after this meeting.

Metrics for people & culture

• The individuals that make up a firm are more significant to its success than its headcount or average age. That holds true regardless of size, from a 5-person startup to a Fortune 500 firm. Jobs was aware of this, which is why his suggested agenda begins by emphasizing demographic data.

• Along with the senior advancements in the previous year's requested statistic, it's crucial to demonstrate that if the business is growing, the employees who make it successful must also grow.

2. Recognize the vulnerabilities and strengths of your rivals

Steve Jobs was known for attacking his competition in interviews and in his strategies and roadmaps. This agenda mentions 18 competitors, including:

• Google 7 times

• Android 3 times

• Samsung 2 times

Jobs' agenda email was issued 6 days after Apple's Q4 results call (2010). On the call, Jobs trashed Google and Android. His 5-minute intervention included:

• Google has acknowledged that the present iteration of Android is not tablet-optimized.

• Future Android tablets will not work (Dead On Arrival)

• While Google Play only has 90,000 apps, the Apple App Store has 300,000.

• Android is extremely fragmented and is continuing to do so.

• The App Store for iPad contains over 35,000 applications. The market share of the latest generation of tablets (which debuted in 2011) will be close to nil.

Jobs' aim in blasting the competition on that call was to reassure investors about the upcoming flood of new tablets. Jobs often criticized Google, Samsung, and Microsoft, but he also acknowledged when they did a better job. He was great at detecting his competitors' advantages and devising ways to catch up.

• Jobs doesn't hold back when he says in bullet 1 of his agenda: "We further lock customers into our ecosystem while Google and Microsoft are further along on the technology, but haven't quite figured it out yet tie all of our goods together."

• The plan outlined in bullet point 5 is immediately clear: catch up to Android where we are falling behind (notifications, tethering, and speech), and surpass them (Siri,). It's important to note that Siri frequently let users down and never quite lived up to expectations.

• Regarding MobileMe, see Bullet 6 Jobs admits that when it comes to cloud services like contacts, calendars, and mail, Google is far ahead of Apple.

3. Adapt or perish

Steve Jobs was a visionary businessman. He knew personal computers were the future when he worked on the first Macintosh in the 1980s.

Jobs acknowledged the Post-PC age in his 2010 D8 interview.

Will the tablet replace the laptop, Walt Mossberg questioned Jobs? Jobs' response:

“You know, when we were an agrarian nation, all cars were trucks, because that’s what you needed on the farm. As vehicles started to be used in the urban centers and America started to move into those urban and suburban centers, cars got more popular and innovations like automatic transmission and things that you didn’t care about in a truck as much started to become paramount in cars. And now, maybe 1 out of every 25 vehicles is a truck, where it used to be 100%. PCs are going to be like trucks. They’re still going to be around, still going to have a lot of value, but they’re going to be used by one out of X people.”

Imagine how forward-thinking that was in 2010, especially for the Macintosh creator. You have to be willing to recognize that things were changing and that it was time to start over and focus on the next big thing.

Post-PC is priority number 8 in his 2010 agenda's 2011 Strategy section. Jobs says Apple is the first firm to get here and that Post PC items account about 66% of our income. The iPad outsold the Mac in 6 months, and the Post-PC age means increased mobility (smaller, thinner, lighter). Samsung had just introduced its first tablet, while Apple was working on the iPad 3. (as mentioned in bullet 4).

4. Plan ahead (and different)

Jobs' agenda warns that Apple risks clinging to outmoded paradigms. Clayton Christensen explains in The Innovators Dilemma that huge firms neglect disruptive technologies until they become profitable. Samsung's Galaxy tab, released too late, never caught up to Apple.

Apple faces a similar dilemma with the iPhone, its cash cow for over a decade. It doesn't sell as much because consumers aren't as excited about new iPhone launches and because technology is developing and cell phones may need to be upgraded.

Large companies' established consumer base typically hinders innovation. Clayton Christensen emphasizes that loyal customers from established brands anticipate better versions of current products rather than something altogether fresh and new technologies.

Apple's marketing is smart. Apple's ecosystem is trusted by customers, and its products integrate smoothly. So much so that Apple can afford to be a disruptor by doing something no one has ever done before, something the world's largest corporation shouldn't be the first to try. Apple can test the waters and produce a tremendous innovation tsunami, something few corporations can do.

In March 2011, Jobs appeared at an Apple event. During his address, Steve reminded us about Apple's brand:

“It’s in Apple’s DNA, that technology alone is not enough. That it’s technology married with liberal arts, married with the humanities that yields us the results that make our hearts sink. And nowhere is that more true that in these Post-PC devices.“

More than a decade later, Apple remains one of the most innovative and trailblazing companies in the Post-PC world (industry-disrupting products like Airpods or the Apple Watch came out after that 2011 strategy meeting), and it has reinvented how we use laptops with its M1-powered line of laptops offering unprecedented performance.

A decade after Jobs' death, Apple remains the world's largest firm, and its former CEO had a crucial part in its expansion. If you can do 1% of what Jobs did, you may be 1% as successful.

Not bad.

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.

The brand-new USB Rubber Ducky is much riskier than before.

With its own programming language, the well-liked hacking tool may now pwn you.

With a vengeance, the USB Rubber Ducky is back.

This year's Def Con hacking conference saw the release of a new version of the well-liked hacking tool, and its author, Darren Kitchen, was on hand to explain it. We put a few of the new features to the test and discovered that the most recent version is riskier than ever.

WHAT IS IT?

The USB Rubber Ducky seems to the untrained eye to be an ordinary USB flash drive. However, when you connect it to a computer, the computer recognizes it as a USB keyboard and will accept keystroke commands from the device exactly like a person would type them in.

Kitchen explained to me, "It takes use of the trust model built in, where computers have been taught to trust a human, in that anything it types is trusted to the same degree as the user is trusted. And a computer is aware that clicks and keystrokes are how people generally connect with it.

Over ten years ago, the first Rubber Ducky was published, quickly becoming a hacker favorite (it was even featured in a Mr. Robot scene). Since then, there have been a number of small upgrades, but the most recent Rubber Ducky takes a giant step ahead with a number of new features that significantly increase its flexibility and capability.

WHERE IS ITS USE?

The options are nearly unlimited with the proper strategy.

The Rubber Ducky has already been used to launch attacks including making a phony Windows pop-up window to collect a user's login information or tricking Chrome into sending all saved passwords to an attacker's web server. However, these attacks lacked the adaptability to operate across platforms and had to be specifically designed for particular operating systems and software versions.

The nuances of DuckyScript 3.0 are described in a new manual. 

The most recent Rubber Ducky seeks to get around these restrictions. The DuckyScript programming language, which is used to construct the commands that the Rubber Ducky will enter into a target machine, receives a significant improvement with it. DuckyScript 3.0 is a feature-rich language that allows users to write functions, store variables, and apply logic flow controls, in contrast to earlier versions that were primarily limited to scripting keystroke sequences (i.e., if this... then that).

This implies that, for instance, the new Ducky can check to see if it is hooked into a Windows or Mac computer and then conditionally run code specific to each one, or it can disable itself if it has been attached to the incorrect target. In order to provide a more human effect, it can also generate pseudorandom numbers and utilize them to add a configurable delay between keystrokes.

The ability to steal data from a target computer by encoding it in binary code and transferring it through the signals intended to instruct a keyboard when the CapsLock or NumLock LEDs should light up is perhaps its most astounding feature. By using this technique, a hacker may plug it in for a brief period of time, excuse themselves by saying, "Sorry, I think that USB drive is faulty," and then take it away with all the credentials stored on it.

HOW SERIOUS IS THE RISK?

In other words, it may be a significant one, but because physical device access is required, the majority of people aren't at risk of being a target.

The 500 or so new Rubber Duckies that Hak5 brought to Def Con, according to Kitchen, were his company's most popular item at the convention, and they were all gone on the first day. It's safe to suppose that hundreds of hackers already possess one, and demand is likely to persist for some time.

Additionally, it has an online development toolkit that can be used to create attack payloads, compile them, and then load them onto the target device. A "payload hub" part of the website makes it simple for hackers to share what they've generated, and the Hak5 Discord is also busy with conversation and helpful advice. This makes it simple for users of the product to connect with a larger community.

It's too expensive for most individuals to distribute in volume, so unless your favorite cafe is renowned for being a hangout among vulnerable targets, it's doubtful that someone will leave a few of them there. To that end, if you intend to plug in a USB device that you discovered outside in a public area, pause to consider your decision.

WOULD IT WORK FOR ME?

Although the device is quite straightforward to use, there are a few things that could cause you trouble if you have no prior expertise writing or debugging code. For a while, during testing on a Mac, I was unable to get the Ducky to press the F4 key to activate the launchpad, but after forcing it to identify itself using an alternative Apple keyboard device ID, the problem was resolved.

From there, I was able to create a script that, when the Ducky was plugged in, would instantly run Chrome, open a new browser tab, and then immediately close it once more without requiring any action from the laptop user. Not bad for only a few hours of testing, and something that could be readily changed to perform duties other than reading technology news.

The company's epidemic gains are gone.

Mark Zuckerberg was in line behind Jeff Bezos and Bill Gates less than two years ago. His wealth soared to $142 billion. Facebook's shares reached $382 in September 2021.

What comes next is either the start of something truly innovative or the beginning of an epic rise and fall story.

In order to start over (and avoid Facebook's PR issues), he renamed the firm Meta. Along with the new logo, he announced a turn into unexplored territory, the Metaverse, as the next chapter for the internet after mobile. Or, Zuckerberg believed Facebook's death was near, so he decided to build a bigger, better, cooler ship. Then we saw his vision (read: dystopian nightmare) in a polished demo that showed Zuckerberg in a luxury home and on a spaceship with aliens. Initially, it looked entertaining. A problem was obvious, though. He might claim this was the future and show us using the Metaverse for business, play, and more, but when I took off my headset, I'd realize none of it was genuine.

The stock price is almost as low as January 2019, when Facebook was dealing with the aftermath of the Cambridge Analytica crisis.

Irony surrounded the technology's aim. Zuckerberg says the Metaverse connects people. Despite some potential uses, this is another step away from physical touch with people. Metaverse worlds can cause melancholy, addiction, and mental illness. But forget all the cool stuff you can't afford. (It may be too expensive online, too.)

Metaverse activity slowed for a while. In early February 2022, we got an earnings call update. Not good. Reality Labs lost $10 billion on Oculus and Zuckerberg's Metaverse. Zuckerberg expects losses to rise. Meta's value dropped 20% in 11 minutes after markets closed.

It was a sign of things to come.

The corporation has failed to create interest in Metaverse, and there is evidence the public has lost interest. Meta still relies on Facebook's ad revenue machine, which is also struggling. In July, the company announced a decrease in revenue and missed practically all its forecasts, ending a decade of exceptional growth and relentless revenue. They blamed a dismal advertising demand climate, and Apple's monitoring changes smashed Meta's ad model. Throw in whistleblowers, leaked data revealing the firm knows Instagram negatively affects teens' mental health, the current Capital Hill probe, and the fact TikTok is eating its breakfast, lunch, and dinner, and 2022 might be the corporation's worst year ever.

After a rocky start, tech saw unprecedented growth during the pandemic. It was a tech bubble and then some.

The gains reversed after the dust settled and stock markets adjusted. Meta's year-to-date decline is 60%. Apple Inc is down 14%, Amazon is down 26%, and Alphabet Inc is down 29%. At the time of writing, Facebook's stock price is almost as low as January 2019, when the Cambridge Analytica scandal broke. Zuckerberg owns 350 million Meta shares. This drop costs him $71 billion.

The company's problems are growing, and solutions won't be easy.

• Facebook's period of unabated expansion and exorbitant ad revenue is ended, and the company's impact is dwindling as it continues to be the program that only your parents use. Because of the decreased ad spending and stagnant user growth, Zuckerberg will have less time to create his vision for the Metaverse because of the declining stock value and decreasing ad spending.

• Instagram is progressively dying in its attempt to resemble TikTok, alienating its user base and further driving users away from Meta-products.

• And now that the corporation has shifted its focus to the Metaverse, it is clear that, in its eagerness to improve its image, it fired the launch gun too early. You're fighting a lost battle when you announce an idea and then claim it won't happen for 10-15 years. When the idea is still years away from becoming a reality, the public is already starting to lose interest.

So, as I questioned earlier, is it the beginning of a technological revolution that will take this firm to stratospheric growth and success, or are we witnessing the end of Meta and Zuckerberg himself?