How to reframe irritation and go forward

“… before you can figure out where you are going, you need to know where you are, and once you know and accept where you are, you can design your way to where you want to be.” — Bill Burnett and Dave Evans

“You’ve been here before. But there are some new ingredients this time. What can tell yourself that will make you understand that now isn’t just like last year? That there’s something new in this August.”

My coach paused. I sighed, inhaled deeply, and considered her question.

What could I say? I simply needed a plan from her so everything would fall into place and I could be the happy, successful person I want to be.

Time passed. My mind was exhausted from running all morning, all summer, or the last five years, searching for what to do next and how to get there.

Calmer, I remembered that my coach's inquiry had benefited me throughout the summer. The month before our call, I read Designing Your Work Life — How to Thrive and Change and Find Happiness at Work from Standford University’s Bill Burnett and Dave Evans.

A passage in their book felt like a lifeline: “We have something important to say to you: Wherever you are in your work life, whatever job you are doing, it’s good enough. For now. Not forever. For now.”

As I remembered this book on the coaching call, I wondered if I could embrace where I am in August and say my job life is good enough for now. Only temporarily.

I've done that since. I'm getting unstuck.

Here's how you can take the first step in any area where you feel stuck.

How to acquire the perspective of "Good enough for now" for yourself

We’ve all heard the advice to just make the best of a bad situation. That´s not bad advice, but if you only make the best of a bad situation, you are still in a bad situation. It doesn’t get to the root of the problem or offer an opportunity to change the situation. You’re more cheerfully navigating lousiness, which is an improvement, but not much of one and rather hard to sustain over time.” — Bill Burnett and Dave Evans

Reframing Burnett at Evans says good enough for now is the key to being happier at work. Because, as they write, a designer always has options.

Choosing to believe things are good enough for now is liberating. It helps us feel less victimized and less judged. Accepting our situation helps us become unstuck.

Let's break down the process, which designers call constructing your way ahead, into steps you can take today.

Writing helps get started. First, write down your challenge and why it's essential to you. If pen and paper help, try this strategy:

• Make the decision to accept the circumstance as it is. Designers always begin by acknowledging the truth of the situation. You now refrain from passing judgment. Instead, you simply describe the situation as accurately as you can. This frees us from negative thought patterns that prevent us from seeing the big picture and instead keep us in a tunnel of negativity.

• Look for a reframing right now. Begin with good enough for the moment. Take note of how your body feels as a result. Tell yourself repeatedly that whatever is occurring is sufficient for the time being. Not always, but just now. If you want to, you can even put it in writing and repeatedly breathe it in, almost like a mantra.

• You can select a reframe that is more relevant to your situation once you've decided that you're good enough for now and have allowed yourself to believe it. Try to find another perspective that is possible, for instance, if you feel unappreciated at work and your perspective of I need to use and be recognized for all my new skills in my job is making you sad and making you want to resign. For instance, I can learn from others at work and occasionally put my new abilities to use.

• After that, leave your mind and act in accordance with your new perspective. Utilize the designer's bias for action to test something out and create a prototype that you can learn from. Your beginning point for creating experiences that will support the new viewpoint derived from the aforementioned point is the new perspective itself. By doing this, you recognize a circumstance at work where you can provide value to yourself or your workplace and then take appropriate action. Send two or three coworkers from whom you wish to learn anything an email, for instance, asking them to get together for coffee or a talk.

Choose tiny, doable actions. You prioritize them at work.

Let's assume you're feeling disconnected at work, so you make a list of folks you may visit each morning or invite to lunch. If you're feeling unmotivated and tired, take a daily walk and treat yourself to a decent coffee.

This may be plenty for now. If you want to take this procedure further, use Burnett and Evans' internet tools and frameworks.

Developing the daily practice of reframing

“We’re not discontented kids in the backseat of the family minivan, but how many of us live our lives, especially our work lives, as if we are?” — Bill Burnett and Dave Evans

I choose the good enough for me perspective every day, often. No quick fix. Am a failing? Maybe a little bit, but I like to think of it more as building muscle.

This way, every time I tell myself it's ok, I hear you. For now, that muscle gets stronger.

Hopefully, reframing will become so natural for us that it will become a habit, and not a technique anymore.

If you feel like you’re stuck in your career or at work, the reframe of Good enough, for now, might be valuable, so just go ahead and try it out right now.

And while you’re playing with this, why not think of other areas of your life too, like your relationships, where you live — even your writing, and see if you can feel a shift?

If I could tell my younger self a few rules, they would boost my career.

1. Treat design like medicine; don't get attached.

If it doesn't help, you won't be angry, but you'll try to improve it. Designers blame others if they don't like the design, but the rule is the same: we solve users' problems. You're not your design, and neither are they. Be humble with your work because your assumptions will often be wrong and users will behave differently.

2. Consider your design flawed.

Disagree with yourself, then defend your ideas. Most designers forget to dig deeper into a pattern, screen, button, or copywriting. If someone asked, "Have you considered alternatives? How does this design stack up? Here's a functional UX checklist to help you make design decisions.

3. Codeable solutions.

If your design requires more developer time, consider whether it's worth spending more money to code something with a small UX impact. Overthinking problems and designing abstract patterns is easy. Sometimes you see something on dribbble or bechance and try to recreate it, but it's not worth it. Here's my article on it.

4. Communication changes careers

Designers often talk with users, clients, companies, developers, and other designers. How you talk and present yourself can land you a job. Like driving or swimming, practice it. Success requires being outgoing and friendly. If I hadn't said "hello" to a few people, I wouldn't be where I am now.

5. Ignorance of the law is not an excuse.

Copyright, taxation How often have you used an icon without checking its license? If you use someone else's work in your project, the owner can cause you a lot of problems — paying a lot of money isn't worth it. Spend a few hours reading about copyrights, client agreements, and taxes.

6. Always test your design

If nobody has seen or used my design, it's not finished. Ask friends about prototypes. Testing reveals how wrong your assumptions were. Steve Krug, one of the authorities on this topic will tell you more about how to do testing.

7. Run workshops

A UX designer's job involves talking to people and figuring out what they need, which is difficult because they usually don't know. Organizing teamwork sessions is a powerful skill, but you must also be a good listener. Your job is to help a quiet, introverted developer express his solution and control the group. AJ Smart has more on workshops here.

Prudence is advised. Be debt-free. Be frugal. Spend less.

This advice sounds nice, but it rarely works.

Most people never learn these two money rules. Both approaches will impact how you see personal finance.

It may safeguard you from inflation or the inability to preserve money.

Let’s dive in.

#1: Making long-term debt your ally

High-interest debt hurts consumers. Many credit cards carry 25% yearly interest (or more), so always pay on time. Otherwise, you’re losing money.

Some low-interest debt is good. Especially when buying an appreciating asset with borrowed money.

Inflation helps you.

If you borrow $800,000 at 3% interest and invest it at 7%, you'll make $32,000 (4%).

As money loses value, fixed payments get cheaper. Your assets' value and cash flow rise.

The never-in-debt crowd doesn't know this. They lose money paying off mortgages and low-interest loans early when they could have bought assets instead.

#2: How To Buy Or Build Assets To Make Inflation Irrelevant

Dozens of studies demonstrate actual wage growth is static; $2.50 in 1964 was equivalent to $22.65 now.

These reports never give solutions unless they're selling gold.

But there is one.

Assets beat inflation.

$100 invested into the S&P 500 would have an inflation-adjusted return of 17,739.30%.

Likewise, you can build assets from nothing.  Doing is easy and quick. The returns can boost your income by 10% or more.

The people who obsess over inflation inadvertently make the problem worse for themselves.  They wait for The Big Crash to buy assets. Or they moan about debt clocks and spending bills instead of seeking a solution.

Conclusion

Being ultra-prudent is like playing golf with a putter to avoid hitting the ball into the water. Sure, you might not slice a drive into the pond. But, you aren’t going to play well either. Or have very much fun.

Money has rules.

Avoiding debt or investment risks will limit your rewards. Long-term, being too cautious hurts your finances.

Disclaimer: This article is for entertainment purposes only. It is not financial advice, always do your own research.

New ventures are exciting. It's fun to imagine yourself rich, successful, and famous (if that's your thing). How you'll help others and make your family proud. This excitement can pull you forward for years, even when you intuitively realize that the path you're on may not lead to your desired success.

Know when to change course. Switching course can mean pivoting or changing direction.

In this not-so-short blog, I'll describe the journey of building your dream. And how the journey might look when you think you're building your dream, but fall short of that vision. Both can feel similar in the beginning, but there are subtle differences.

Let’s dive in.

How an exciting journey to a dead end looks and feels.

You want to help many people. You're business-minded, creative, and ambitious. You jump into entrepreneurship. You're excited, free, and in control.

I'll use tech as an example because that's what I know best, but this applies to any entrepreneurial endeavor.

So you start learning the basics of your field, say coding/software development. You read books, take courses, and may even join a bootcamp. You start practicing, and the journey begins. Once you reach a certain level of skill (which can take months, usually 12-24), you gain the confidence to speak with others in the field and find common ground. You might attract a co-founder this way with time. You and this person embark on a journey (Tip: the idea you start with is rarely the idea you end with).

Amateur mistake #1: You spend months building a product before speaking to customers.

Building something pulls you forward blindly. You make mistakes, avoid customers, and build with your co-founder or small team in the dark for months, usually 6-12 months.

You're excited when the product launches. We'll be billionaires! The market won't believe it. This excites you and the team. Launch.

….

Nothing happens.

Some people may sign up out of pity, only to never use the product or service again.

You and the team are confused, discouraged and in denial. They don't get what we've built yet. We need to market it better, we need to talk to more investors, someone will understand our vision.

This is a hopeless path, and your denial could last another 6 months. If you're lucky, while talking to consumers and investors (which you should have done from the start), someone who has been there before would pity you and give you an idea to pivot into that can create income.

Suppose you get this idea and pivot your business. Again, you've just pivoted into something limited by what you've already built. It may be a revenue-generating idea, but it's rarely new. Now you're playing catch-up, doing something others are doing but you can do better. (Tip #2: Don't be late.) Your chances of winning are slim, and you'll likely never catch up.

You're finally seeing revenue and feel successful. You can compete, but if you're not a first mover, you won't earn enough over time. You'll get by or work harder than ever to earn what a skilled trade could provide. You didn't go into business to stress out and make $100,000 or $200,000 a year. When you can make the same amount by becoming a great software developer, electrician, etc.

You become stuck. Either your firm continues this way for years until you realize there isn't enough growth to recruit a strong team and remove yourself from day-to-day operations due to competition. Or a catastrophic economic event forces you to admit that what you were building wasn't new and unique and wouldn't get you where you wanted to be.

This realization could take 6-10 years. No kidding.

The good news is, you’ve learned a lot along the way and this information can be used towards your next venture (if you have the energy).

Key Lesson: Don’t build something if you aren’t one of the first in the space building it just for the sake of building something.

-

Let's discuss what it's like to build something that can make your dream come true.

Case 2: Building something the market loves is difficult but rewarding.

It starts with a problem that hasn't been adequately solved for a long time but is now solvable due to technology. Or a new problem due to a change in how things are done.

Let's examine each example.

Example #1: Mass communication. The problem is now solvable due to some technological breakthrough.

Twitter — One of the first web 2 companies that became successful with the rise of smart mobile computing.

People can share their real-time activities via mobile device with friends, family, and strangers. Web 2 and smartphones made it easy and fun.

Example #2: A new problem has emerged due to some change in the way things are conducted.

Zoom- A web-conferencing company that reached massive success due to the movement towards “work from home”, remote/hybrid work forces.

Online web conferencing allows for face-to-face communication.

-

These two examples show how to build a unicorn-type company. It's a mix of solving the right problem at the right time, either through a technological breakthrough that opens up new opportunities or by fundamentally changing how people do things.

Let's find these opportunities.

Start by examining problems, such as how the world has changed and how we can help it adapt. It can also be both. Start team brainstorming. Research technologies, current world-trends, use common sense, and make a list. Then, choose the top 3 that you're most excited about and seem most workable based on your skillsets, values, and passion.

Once you have this list, create the simplest MVP you can and test it with customers. The prototype can be as simple as a picture or diagram of user flow and end-user value. No coding required. Market-test. Twitter's version 1 was simple. It was a web form that asked, "What are you doing?" Then publish it from your phone. A global status update, wherever you are. Currently, this company has a $50 billion market cap.

Here's their MVP screenshot.

Small things grow. Tiny. Simplify.

Remember Frequency and Value when brainstorming. Your product is high frequency (Twitter, Instagram, Snapchat, TikTok) or high value (Airbnb for renting travel accommodations), or both (Gmail).

Once you've identified product ideas that meet the above criteria, they're simple, have a high frequency of use, or provide deep value. You then bring it to market in the simplest, most cost-effective way. You can sell a half-working prototype with imagination and sales skills. You need just enough of a prototype to convey your vision to a user or customer.

With this, you can approach real people. This will do one of three things: give you a green light to continue on your vision as is, show you that there is no opportunity and people won't use it, or point you in a direction that is a blend of what you've come up with and what the customer / user really wants, and you update the prototype and go back to the maze. Repeat until you have enough yeses and conviction to build an MVP.

Without a degree and experience, you can get a high-paying tech job.

Most organizations follow this hiring rule: you chat with HR, interview with your future boss and other senior managers, and they make the final hiring choice.

If you've ever applied for a job, you know how arduous it can be. A newly snapped photo and a glossy resume template can wear you out. Applying to Google can change this experience.

According to an Universum report, Google is one of the world's most coveted employers. It's not simply the search giant's name and reputation that attract candidates, but its role requirements or lack thereof.

Candidates no longer need a beautiful resume, cover letter, Ivy League laurels, or years of direct experience. The company requires no degree or experience.

Elon Musk started it. He employed the two-hands test to uncover talented non-graduates. The billionaire eliminated the requirement for experience.

Google is deconstructing traditional employment with programs like the Google Project Management Degree, a free online and self-paced professional credential course.

Google's hiring is interesting. After its certification course, applicants can work in project management. Instead of academic degrees and experience, the company analyzes coursework.

Google finds the best project managers and technical staff in exchange. Google uses three strategies to find top talent.

Chase down the innovators

Google eliminates restrictions like education, experience, and others to find the polar bear amid the snowfall. Google's free project management education makes project manager responsibilities accessible to everyone.

Many jobs don't require a degree. Overlooking individuals without a degree can make it difficult to locate a candidate who can provide value to a firm.

Firsthand knowledge follows the same rule. A lack of past information might be an employer's benefit. This is true for creative teams or businesses that prefer to innovate.

Or when corporations conduct differently from the competition. No-experience candidates can offer fresh perspectives. Fast Company reports that people with no sales experience beat those with 10 to 15 years of experience.

Give the aptitude test first priority.

Google wants the best candidates. Google wouldn't be able to receive more applications if it couldn't screen them for fit. Its well-organized online training program can be utilized as a portfolio.

Google learns a lot about an applicant through completed assignments. It reveals their ability, leadership style, communication capability, etc. The course mimics the job to assess candidates' suitability.

Basic screening questions might provide information to compare candidates. Any size small business can use screening questions and test projects to evaluate prospective employees.

Effective training for employees

Businesses must train employees regardless of their hiring purpose. Formal education and prior experience don't guarantee success. Maintaining your employees' professional knowledge gaps is key to their productivity and happiness. Top-notch training can do that. Learning and development are key to employee engagement, says Bob Nelson, author of 1,001 Ways to Engage Employees.

Google's online certification program isn't available everywhere. Improving the recruiting process means emphasizing aptitude over experience and a degree. Instead of employing new personnel and having them work the way their former firm trained them, train them how you want them to function.

If you want to know more about Google’s recruiting process, we recommend you watch the movie “Internship.”

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.