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.

We may never tap again in ten years.

I discussed styling websites and web apps on smartwatches in my earlier article on W3C standardization.

The Parallax Chronicles

Section containing examples and flying objects

Another intriguing Working Draft I found applies to all devices, including smartphones.

These pages may have something intriguing. Take your time. Return after scrolling:

• Exhibit 1

• Exhibit 2

• Exhibit 3

What connects these three pages?

JustinWick at English Wikipedia • CC-BY-SA-3.0

Scroll-linked animation, commonly called parallax, is the effect.

WordPress theme developers' quick setup and low-code tools made the effect popular around 2014.

Parallax: Why Designers Love It

The chapter that your designer shouldn't read

Online video playback required searching, scrolling, and clicking ten years ago. Scroll and click four years ago.

Some video sites let you swipe to autoplay the next video from an endless list.

UI designers create scrollable pages and apps to accommodate the behavioral change.

Web interactivity used to be mouse-based. Clicking a button opened a help drawer, and hovering animated it.

However, a large page with more material requires fewer buttons and less interactiveness.

Designers choose scroll-based effects. Design and frontend developers must fight the trend but prepare for the worst.

How to Create Parallax

The component that you might want to show the designer

JavaScript-based effects track page scrolling and apply animations.

Javascript libraries like lax.js simplify it.

Using it needs a lot of human mathematical and physical computations.

Your asset library must also be prepared to display your website on a laptop, television, smartphone, tablet, foldable smartphone, and possibly even a microwave.

Overall, scroll-based animations can be solved better.

CSS Scroll-linked Animations

CSS makes sense since it's presentational. A Working Draft has been laying the groundwork for the next generation of interactiveness.

The new CSS property scroll-timeline powers the feature, which MDN describes well.

Before testing it, you should realize it is poorly supported:

Firefox 103 currently supports it.

There is also a polyfill, with some demo examples to explore.

Summary

Web design was a protracted process. Started with pages with static backdrop images and scrollable text. Artists and designers may use the scroll-based animation CSS API to completely revamp our web experience.

It's a promising frontier. This post may attract a future scrollable web designer.

Ps. I have created flashcards for HTML, Javascript etc. Check them out!

I've summarized each.

Anne Lamott said books are important. Books help us understand ourselves and our behavior. They teach us about community, friendship, and death.

I read. One of my few life-changing habits. 100+ books a year improve my life. I'll list life-changing books you can read in a day. I hope you like them too.

Let's get started!

1) Seneca's Letters from a Stoic

One of my favorite philosophy books. Ryan Holiday, Naval Ravikant, and other prolific readers recommend it.

Seneca wrote 124 letters at the end of his life after working for Nero. Death, friendship, and virtue are discussed.

It's worth rereading. When I'm in trouble, I consult Seneca.

It's brief. The book could be read in one day. However, use it for guidance during difficult times.

My favorite book quotes:

• Many men find that becoming wealthy only alters their problems rather than solving them.

• You will never be poor if you live in harmony with nature; you will never be wealthy if you live according to what other people think.

• We suffer more frequently in our imagination than in reality; there are more things that are likely to frighten us than to crush us.

2) Steven Pressfield's book The War of Art

I’ve read this book twice. I'll likely reread it before 2022 is over.

The War Of Art is the best productivity book. Steven offers procrastination-fighting tips.

Writers, musicians, and creative types will love The War of Art. Workplace procrastinators should also read this book.

My favorite book quotes:

• The act of creation is what matters most in art. Other than sitting down and making an effort every day, nothing else matters.

• Working creatively is not a selfish endeavor or an attempt by the actor to gain attention. It serves as a gift for all living things in the world. Don't steal your contribution from us. Give us everything you have.

• Fear is healthy. Fear is a signal, just like self-doubt. Fear instructs us on what to do. The more terrified we are of a task or calling, the more certain we can be that we must complete it.

3) Darren Hardy's The Compound Effect

The Compound Effect offers practical tips to boost productivity by 10x.

The author believes each choice shapes your future. Pizza may seem harmless. However, daily use increases heart disease risk.

Positive outcomes too. Daily gym visits improve fitness. Reading an hour each night can help you learn. Writing 1,000 words per day would allow you to write a novel in under a year.

Your daily choices affect compound interest and your future. Thus, better habits can improve your life.

My favorite book quotes:

• Until you alter a daily habit, you cannot change your life. The key to your success can be found in the actions you take each day.

• The hundreds, thousands, or millions of little things are what distinguish the ordinary from the extraordinary; it is not the big things that add up in the end.

• Don't worry about willpower. Time to use why-power. Only when you relate your decisions to your aspirations and dreams will they have any real meaning. The decisions that are in line with what you define as your purpose, your core self, and your highest values are the wisest and most inspiring ones. To avoid giving up too easily, you must want something and understand why you want it.

Better technology and lower launch costs revive science-fiction tech.

Airbus engineers showed off sustainable energy's future in Munich last month. They captured sunlight with solar panels, turned it into microwaves, and beamed it into an airplane hangar, where it lighted a city model. The test delivered 2 kW across 36 meters, but it posed a serious question: Should we send enormous satellites to capture solar energy in space? In orbit, free of clouds and nighttime, they could create power 24/7 and send it to Earth.

Airbus engineer Jean-Dominique Coste calls it an engineering problem. “But it’s never been done at [large] scale.”

Proponents of space solar power say the demand for green energy, cheaper space access, and improved technology might change that. Once someone invests commercially, it will grow. Former NASA researcher John Mankins says it might be a trillion-dollar industry.

Myriad uncertainties remain, including whether beaming gigawatts of power to Earth can be done efficiently and without burning birds or people. Concept papers are being replaced with ground and space testing. The European Space Agency (ESA), which supported the Munich demo, will propose ground tests to member nations next month. The U.K. government offered £6 million to evaluate innovations this year. Chinese, Japanese, South Korean, and U.S. agencies are working. NASA policy analyst Nikolai Joseph, author of an upcoming assessment, thinks the conversation's tone has altered. What formerly appeared unattainable may now be a matter of "bringing it all together"

NASA studied space solar power during the mid-1970s fuel crunch. A projected space demonstration trip using 1970s technology would have cost $1 trillion. According to Mankins, the idea is taboo in the agency.

Space and solar power technology have evolved. Photovoltaic (PV) solar cell efficiency has increased 25% over the past decade, Jones claims. Telecoms use microwave transmitters and receivers. Robots designed to repair and refuel spacecraft might create solar panels.

Falling launch costs have boosted the idea. A solar power satellite large enough to replace a nuclear or coal plant would require hundreds of launches. ESA scientist Sanjay Vijendran: "It would require a massive construction complex in orbit."

SpaceX has made the idea more plausible. A SpaceX Falcon 9 rocket costs $2600 per kilogram, less than 5% of what the Space Shuttle did, and the company promised $10 per kilogram for its giant Starship, slated to launch this year. Jones: "It changes the equation." "Economics rules"

Mass production reduces space hardware costs. Satellites are one-offs made with pricey space-rated parts. Mars rover Perseverance cost $2 million per kilogram. SpaceX's Starlink satellites cost less than $1000 per kilogram. This strategy may work for massive space buildings consisting of many identical low-cost components, Mankins has long contended. Low-cost launches and "hypermodularity" make space solar power economical, he claims.

Better engineering can improve economics. Coste says Airbus's Munich trial was 5% efficient, comparing solar input to electricity production. When the Sun shines, ground-based solar arrays perform better. Studies show space solar might compete with existing energy sources on price if it reaches 20% efficiency.

Lighter parts reduce costs. "Sandwich panels" with PV cells on one side, electronics in the middle, and a microwave transmitter on the other could help. Thousands of them build a solar satellite without heavy wiring to move power. In 2020, a team from the U.S. Naval Research Laboratory (NRL) flew on the Air Force's X-37B space plane.

NRL project head Paul Jaffe said the satellite is still providing data. The panel converts solar power into microwaves at 8% efficiency, but not to Earth. The Air Force expects to test a beaming sandwich panel next year. MIT will launch its prototype panel with SpaceX in December.

As a satellite orbits, the PV side of sandwich panels sometimes faces away from the Sun since the microwave side must always face Earth. To maintain 24-hour power, a satellite needs mirrors to keep that side illuminated and focus light on the PV. In a 2012 NASA study by Mankins, a bowl-shaped device with thousands of thin-film mirrors focuses light onto the PV array.

International Electric Company's Ian Cash has a new strategy. His proposed satellite uses enormous, fixed mirrors to redirect light onto a PV and microwave array while the structure spins (see graphic, above). 1 billion minuscule perpendicular antennas act as a "phased array" to electronically guide the beam toward Earth, regardless of the satellite's orientation. This design, argues Cash, is "the most competitive economically"

If a space-based power plant ever flies, its power must be delivered securely and efficiently. Jaffe's team at NRL just beamed 1.6 kW over 1 km, and teams in Japan, China, and South Korea have comparable attempts. Transmitters and receivers lose half their input power. Vijendran says space solar beaming needs 75% efficiency, "preferably 90%."

Beaming gigawatts through the atmosphere demands testing. Most designs aim to produce a beam kilometers wide so every ship, plane, human, or bird that strays into it only receives a tiny—hopefully harmless—portion of the 2-gigawatt transmission. Receiving antennas are cheap to build but require a lot of land, adds Jones. You could grow crops under them or place them offshore.

Europe's public agencies currently prioritize space solar power. Jones: "There's a devotion you don't see in the U.S." ESA commissioned two solar cost/benefit studies last year. Vijendran claims it might match ground-based renewables' cost. Even at a higher price, equivalent to nuclear, its 24/7 availability would make it competitive.

ESA will urge member states in November to fund a technical assessment. If the news is good, the agency will plan for 2025. With €15 billion to €20 billion, ESA may launch a megawatt-scale demonstration facility by 2030 and a gigawatt-scale facility by 2040. "Moonshot"

(And you can have it for free)

Master email to sell anything.

Most novice creators don't know how to begin.

Many use online templates. These are usually fluff-filled and niche-specific.

They're robotic and "salesy."

I've attended 3 courses, read 10 books, and sent 600,000 emails in the past five years.

Outcome?

This *proven* email sequence assures me a month's salary every time I send it.

What you will discover in this article is that:

• A full 6-part email sales cycle

• The essential elements you must incorporate

• placeholders and text-filled images

• (Applies to any niche)

This can be a product introduction, holiday, or welcome sequence. This works for email-saleable products.

Let's start

Email 1: Describe your issue

This email is crucial.

How to? We introduce a subscriber or prospect's problem. Later, we'll frame our offer as the solution.

Label the:

• Problem

• Why it still hasn't been fixed

• Resulting implications for the customer

This puts our new subscriber in solve mode and queues our offer:

Email 2: Amplify the consequences

We're still causing problems.

We've created the problem, but now we must employ emotion and storytelling to make it real. We also want to forecast life if nothing changes.

Let's feel:

• What occurs if it is not resolved?

• Why is it crucial to fix it immediately?

• Tell a tale of a person who was in their position. To emphasize the effects, use a true account of another person (or of yourself):

Email 3: Share a transformation story

Selling stories.

Whether in an email, landing page, article, or video. Humanize stories. They give information meaning.

This is where "issue" becomes "solution."

Let's reveal:

• A tale of success

• A new existence and result

• tools and tactics employed

Start by transforming yourself.

Email 4: Prove with testimonials

No one buys what you say.

Emotionally stirred people buy and act. They believe in the product. They feel that if they buy, it will work.

Social proof shows prospects that your solution will help them.

Add:

• Earlier and Later

• Testimonials

• Reviews

Proof this deal works:

Email 5: Reveal your offer

It's showtime.

This is it. Until now, describing the offer and offering links to a landing page have been sparse in the email pictures.

We've been tense. Gaining steam. Building suspense. Email 5 reveals all.

In this email:

• a description of the deal

• A word about a promise

• recapitulation of the transformation

• and make a reference to the urgency Everything should be spelled out clearly:

Email no. 6: Instill urgency

When there are stakes, humans act.

Creating and marketing with haste raises the stakes. Urgency makes a prospect act because they'll miss out or gain immensely.

Urgency converts. Use:

• short time

• Screening

• Scarcity

Urgency and conversions. Limited-time offers are easy.

TL;DR

Use this proven 6-part email sequence (that turns subscribers into profit):

• Introduce a problem

• Amplify it with emotions

• Share transformation story

• Prove it works with testimonials

• Value-stack and present your offer

• Drive urgency and entice the purchase