DeCap is DeFi's killer app.

“Software is eating the world.” Marc Andreesen, venture capitalist

DeFi. Imagine a blockchain-based alternative financial system that offers the same products and services as traditional finance, but with more variety, faster, more secure, lower cost, and simpler access.

Decentralised finance (DeFi) is a marketplace without gatekeepers or central authority managing the flow of money, where customers engage directly with smart contracts running on a blockchain.

DeFi grew exponentially in 2020/21, with Total Value Locked (an inadequate estimate for market size) topping at $100 billion. After that, it crashed.

The accumulation of funds by individuals with high discretionary income during the epidemic, the novelty of crypto trading, and the high yields given (5% APY for stablecoins on established platforms to 100%+ for risky assets) are among the primary elements explaining this exponential increase.

No longer your older brothers DeFi

Since transactions are anonymous, borrowers had to overcollateralize DeFi 1.0. To borrow $100 in stablecoins, you must deposit $150 in ETH. DeFi 1.0's business strategy raises two problems.

• Why does DeFi offer interest rates that are higher than those of the conventional financial system?;

• Why would somebody put down more cash than they intended to borrow?

Maxed out on their own resources, investors took loans to acquire more crypto; the demand for those loans raised DeFi yields, which kept crypto prices increasing; as crypto prices rose, investors made a return on their positions, allowing them to deposit more money and borrow more crypto.

This is a bull market game. DeFi 1.0's overcollateralization speculation is dead. Cryptocrash sank it.

The “speculation by overcollateralisation” world of DeFi 1.0 is dead

At a JP Morgan digital assets conference, institutional investors were more interested in DeFi than crypto or fintech. To me, that shows DeFi 2.0's institutional future.

DeFi 2.0 protocols must handle KYC/AML, tax compliance, market abuse, and cybersecurity problems to be institutional-ready.

Stablecoins gaining market share under benign regulation and more CBDCs coming online in the next couple of years could help DeFi 2.0 separate from crypto volatility.

DeFi 2.0 will have a better footing to finally decouple from crypto volatility

Then we can transition from speculation through overcollateralization to DeFi's genuine comparative advantages: cheaper transaction costs, near-instant settlement, more efficient price discovery, faster time-to-market for financial innovation, and a superior audit trail.

Akin to Amazon for financial goods

Amazon decimated brick-and-mortar shops by offering millions of things online, warehouses by keeping just-in-time inventory, and back-offices by automating invoicing and payments. Software devoured retail. DeFi will eat banking with software.

DeFi is the Amazon for financial items that will replace fintech. Even the most advanced internet brokers offer only 100 currency pairings and limited bonds, equities, and ETFs.

Old banks settlement systems and inefficient, hard-to-upgrade outdated software harm them. For advanced gamers, it's like driving an F1 vehicle on dirt.

It is like driving a F1 car on a dirt road, for the most sophisticated players

Central bankers throughout the world know how expensive and difficult it is to handle cross-border payments using the US dollar as the reserve currency, which is vulnerable to the economic cycle and geopolitical tensions.

Decentralization is the only method to deliver 24h global financial markets. DeFi 2.0 lets you buy and sell startup shares like Google or Tesla. VC funds will trade like mutual funds. Or create a bundle coverage for your car, house, and NFTs. Defi 2.0 consumes banking and creates Global Wall Street.

Defi 2.0 is how software eats banking and delivers the global Wall Street

Decentralized Capitalism is Emerging

90% of markets are digital. 10% is hardest to digitalize. That's money creation, ID, and asset tokenization.

90% of financial markets are already digital. The only problem is that the 10% left is the hardest to digitalize

Debt helped Athens construct a powerful navy that secured trade routes. Bonds financed the Renaissance's wars and supply chains. Equity fueled industrial growth. FX drove globalization's payments system. DeFi's plans:

If the 20th century was a conflict between governments and markets over economic drivers, the 21st century will be between centralized and decentralized corporate structures.

Offices vs. telecommuting. China vs. onshoring/friendshoring. Oil & gas vs. diverse energy matrix. National vs. multilateral policymaking. DAOs vs. corporations Fiat vs. crypto. TradFi vs.

An age where the network effects of the sharing economy will overtake the gains of scale of the monopolistic competition economy

This is the dawn of Decentralized Capitalism (or DeCap), an age where the network effects of the sharing economy will reach a tipping point and surpass the scale gains of the monopolistic competition economy, further eliminating inefficiencies and creating a more robust economy through better data and automation. DeFi 2.0 enables this.

DeFi needs to pay the piper now.

DeCap won't be Web3.0's Shangri-La, though. That's too much for an ailing Atlas. When push comes to shove, DeFi folks want to survive and fight another day for the revolution. If feasible, make a tidy profit.

Decentralization wasn't meant to circumvent regulation. It circumvents censorship. On-ramp, off-ramp measures (control DeFi's entry and exit points, not what happens in between) sound like a good compromise for DeFi 2.0.

The sooner authorities realize that DeFi regulation is made ex-ante by writing code and constructing smart contracts with rules, the faster DeFi 2.0 will become the more efficient and safe financial marketplace.

More crucially, we must boost system liquidity. DeFi's financial stability risks are downplayed. DeFi must improve its liquidity management if it's to become mainstream, just as banks rely on capital constraints.

This reveals the complex and, frankly, inadequate governance arrangements for DeFi protocols. They redistribute control from tokenholders to developers, which is bad governance regardless of the economic model.

But crypto can only ride the existing banking system for so long before forming its own economy. DeFi will upgrade web2.0's financial rails till then.

Zero-Knowledge Proofs for Beginners

Published here originally.

Introduction

I Spy—did you play as a kid? One person chose a room object, and the other had to guess it by answering yes or no questions. I Spy was entertaining, but did you know it could teach you cryptography?

Zero Knowledge Proofs let you show your pal you know what they picked without exposing how. Math replaces electronics in this secret spy mission. Zero-knowledge proofs (ZKPs) are sophisticated cryptographic tools that allow one party to prove they have particular knowledge without revealing it. This proves identification and ownership, secures financial transactions, and more. This article explains zero-knowledge proofs and provides examples to help you comprehend this powerful technology.

What is a Proof of Zero Knowledge?

Zero-knowledge proofs prove a proposition is true without revealing any other information. This lets the prover show the verifier that they know a fact without revealing it. So, a zero-knowledge proof is like a magician's trick: the prover proves they know something without revealing how or what. Complex mathematical procedures create a proof the verifier can verify.

Want to find an easy way to test it out? Try out with tis awesome example! ZK Crush

Describe it as if I'm 5

Alex and Jack found a cave with a center entrance that only opens when someone knows the secret. Alex knows how to open the cave door and wants to show Jack without telling him.

Alex and Jack name both pathways (let’s call them paths A and B).

1. In the first phase, Alex is already inside the cave and is free to select either path, in this case A or B.

2. As Alex made his decision, Jack entered the cave and asked him to exit from the B path.

3. Jack can confirm that Alex really does know the key to open the door because he came out for the B path and used it.

To conclude, Alex and Jack repeat:

1. Alex walks into the cave.

2. Alex follows a random route.

3. Jack walks into the cave.

4. Alex is asked to follow a random route by Jack.

5. Alex follows Jack's advice and heads back that way.

What is a Zero Knowledge Proof?

At a high level, the aim is to construct a secure and confidential conversation between the prover and the verifier, where the prover convinces the verifier that they have the requisite information without disclosing it. The prover and verifier exchange messages and calculate in each round of the dialogue.

The prover uses their knowledge to prove they have the information the verifier wants during these rounds. The verifier can verify the prover's truthfulness without learning more by checking the proof's mathematical statement or computation.

Zero knowledge proofs use advanced mathematical procedures and cryptography methods to secure communication. These methods ensure the evidence is authentic while preventing the prover from creating a phony proof or the verifier from extracting unnecessary information.

ZK proofs require examples to grasp. Before the examples, there are some preconditions.

Criteria for Proofs of Zero Knowledge

1. Completeness: If the proposition being proved is true, then an honest prover will persuade an honest verifier that it is true.

2. Soundness: If the proposition being proved is untrue, no dishonest prover can persuade a sincere verifier that it is true.

3. Zero-knowledge: The verifier only realizes that the proposition being proved is true. In other words, the proof only establishes the veracity of the proposition being supported and nothing more.

The zero-knowledge condition is crucial. Zero-knowledge proofs show only the secret's veracity. The verifier shouldn't know the secret's value or other details.

Example after example after example

To illustrate, take a zero-knowledge proof with several examples:

Initial Password Verification Example

You want to confirm you know a password or secret phrase without revealing it.

Use a zero-knowledge proof:

1. You and the verifier settle on a mathematical conundrum or issue, such as figuring out a big number's components.

2. The puzzle or problem is then solved using the hidden knowledge that you have learned. You may, for instance, utilize your understanding of the password to determine the components of a particular number.

3. You provide your answer to the verifier, who can assess its accuracy without knowing anything about your private data.

4. You go through this process several times with various riddles or issues to persuade the verifier that you actually are aware of the secret knowledge.

You solved the mathematical puzzles or problems, proving to the verifier that you know the hidden information. The proof is zero-knowledge since the verifier only sees puzzle solutions, not the secret information.

In this scenario, the mathematical challenge or problem represents the secret, and solving it proves you know it. The evidence does not expose the secret, and the verifier just learns that you know it.

My simple example meets the zero-knowledge proof conditions:

1. Completeness: If you actually know the hidden information, you will be able to solve the mathematical puzzles or problems, hence the proof is conclusive.

2. Soundness: The proof is sound because the verifier can use a publicly known algorithm to confirm that your answer to the mathematical conundrum or difficulty is accurate.

3. Zero-knowledge: The proof is zero-knowledge because all the verifier learns is that you are aware of the confidential information. Beyond the fact that you are aware of it, the verifier does not learn anything about the secret information itself, such as the password or the factors of the number. As a result, the proof does not provide any new insights into the secret.

Explanation #2: Toss a coin.

One coin is biased to come up heads more often than tails, while the other is fair (i.e., comes up heads and tails with equal probability). You know which coin is which, but you want to show a friend you can tell them apart without telling them.

Use a zero-knowledge proof:

1. One of the two coins is chosen at random, and you secretly flip it more than once.

2. You show your pal the following series of coin flips without revealing which coin you actually flipped.

3. Next, as one of the two coins is flipped in front of you, your friend asks you to tell which one it is.

4. Then, without revealing which coin is which, you can use your understanding of the secret order of coin flips to determine which coin your friend flipped.

5. To persuade your friend that you can actually differentiate between the coins, you repeat this process multiple times using various secret coin-flipping sequences.

In this example, the series of coin flips represents the knowledge of biased and fair coins. You can prove you know which coin is which without revealing which is biased or fair by employing a different secret sequence of coin flips for each round.

The evidence is zero-knowledge since your friend does not learn anything about which coin is biased and which is fair other than that you can tell them differently. The proof does not indicate which coin you flipped or how many times you flipped it.

The coin-flipping example meets zero-knowledge proof requirements:

1. Completeness: If you actually know which coin is biased and which is fair, you should be able to distinguish between them based on the order of coin flips, and your friend should be persuaded that you can.

2. Soundness: Your friend may confirm that you are correctly recognizing the coins by flipping one of them in front of you and validating your answer, thus the proof is sound in that regard. Because of this, your acquaintance can be sure that you are not just speculating or picking a coin at random.

3. Zero-knowledge: The argument is that your friend has no idea which coin is biased and which is fair beyond your ability to distinguish between them. Your friend is not made aware of the coin you used to make your decision or the order in which you flipped the coins. Consequently, except from letting you know which coin is biased and which is fair, the proof does not give any additional information about the coins themselves.

Figure out the prime number in Example #3.

You want to prove to a friend that you know their product n=pq without revealing p and q. Zero-knowledge proof?

Use a variant of the RSA algorithm. Method:

1. You determine a new number s = r2 mod n by computing a random number r.

2. You email your friend s and a declaration that you are aware of the values of p and q necessary for n to equal pq.

3. A random number (either 0 or 1) is selected by your friend and sent to you.

4. You send your friend r as evidence that you are aware of the values of p and q if e=0. You calculate and communicate your friend's s/r if e=1.

5. Without knowing the values of p and q, your friend can confirm that you know p and q (in the case where e=0) or that s/r is a legitimate square root of s mod n (in the situation where e=1).

This is a zero-knowledge proof since your friend learns nothing about p and q other than their product is n and your ability to verify it without exposing any other information. You can prove that you know p and q by sending r or by computing s/r and sending that instead (if e=1), and your friend can verify that you know p and q or that s/r is a valid square root of s mod n without learning anything else about their values. This meets the conditions of completeness, soundness, and zero-knowledge.

Zero-knowledge proofs satisfy the following:

1. Completeness: The prover can demonstrate this to the verifier by computing q = n/p and sending both p and q to the verifier. The prover also knows a prime number p and a factorization of n as p*q.

2. Soundness: Since it is impossible to identify any pair of numbers that correctly factorize n without being aware of its prime factors, the prover is unable to demonstrate knowledge of any p and q that do not do so.

3. Zero knowledge: The prover only admits that they are aware of a prime number p and its associated factor q, which is already known to the verifier. This is the extent of their knowledge of the prime factors of n. As a result, the prover does not provide any new details regarding n's prime factors.

Types of Proofs of Zero Knowledge

Each zero-knowledge proof has pros and cons. Most zero-knowledge proofs are:

1. Interactive Zero Knowledge Proofs: The prover and the verifier work together to establish the proof in this sort of zero-knowledge proof. The verifier disputes the prover's assertions after receiving a sequence of messages from the prover. When the evidence has been established, the prover will employ these new problems to generate additional responses.

2. Non-Interactive Zero Knowledge Proofs: For this kind of zero-knowledge proof, the prover and verifier just need to exchange a single message. Without further interaction between the two parties, the proof is established.

3. A statistical zero-knowledge proof is one in which the conclusion is reached with a high degree of probability but not with certainty. This indicates that there is a remote possibility that the proof is false, but that this possibility is so remote as to be unimportant.

4. Succinct Non-Interactive Argument of Knowledge (SNARKs): SNARKs are an extremely effective and scalable form of zero-knowledge proof. They are utilized in many different applications, such as machine learning, blockchain technology, and more. Similar to other zero-knowledge proof techniques, SNARKs enable one party—the prover—to demonstrate to another—the verifier—that they are aware of a specific piece of information without disclosing any more information about that information.

5. The main characteristic of SNARKs is their succinctness, which refers to the fact that the size of the proof is substantially smaller than the amount of the original data being proved. Because to its high efficiency and scalability, SNARKs can be used in a wide range of applications, such as machine learning, blockchain technology, and more.

Uses for Zero Knowledge Proofs

ZKP applications include:

1. Verifying Identity ZKPs can be used to verify your identity without disclosing any personal information. This has uses in access control, digital signatures, and online authentication.

2. Proof of Ownership ZKPs can be used to demonstrate ownership of a certain asset without divulging any details about the asset itself. This has uses for protecting intellectual property, managing supply chains, and owning digital assets.

3. Financial Exchanges Without disclosing any details about the transaction itself, ZKPs can be used to validate financial transactions. Cryptocurrency, internet payments, and other digital financial transactions can all use this.

4. By enabling parties to make calculations on the data without disclosing the data itself, Data Privacy ZKPs can be used to preserve the privacy of sensitive data. Applications for this can be found in the financial, healthcare, and other sectors that handle sensitive data.

5. By enabling voters to confirm that their vote was counted without disclosing how they voted, elections ZKPs can be used to ensure the integrity of elections. This is applicable to electronic voting, including internet voting.

6. Cryptography Modern cryptography's ZKPs are a potent instrument that enable secure communication and authentication. This can be used for encrypted messaging and other purposes in the business sector as well as for military and intelligence operations.

Proofs of Zero Knowledge and Compliance

Kubernetes and regulatory compliance use ZKPs in many ways. Examples:

1. Security for Kubernetes ZKPs offer a mechanism to authenticate nodes without disclosing any sensitive information, enhancing the security of Kubernetes clusters. ZKPs, for instance, can be used to verify, without disclosing the specifics of the program, that the nodes in a Kubernetes cluster are running permitted software.

2. Compliance Inspection Without disclosing any sensitive information, ZKPs can be used to demonstrate compliance with rules like the GDPR, HIPAA, and PCI DSS. ZKPs, for instance, can be used to demonstrate that data has been encrypted and stored securely without divulging the specifics of the mechanism employed for either encryption or storage.

3. Access Management Without disclosing any private data, ZKPs can be used to offer safe access control to Kubernetes resources. ZKPs can be used, for instance, to demonstrate that a user has the necessary permissions to access a particular Kubernetes resource without disclosing the details of those permissions.

4. Safe Data Exchange Without disclosing any sensitive information, ZKPs can be used to securely transmit data between Kubernetes clusters or between several businesses. ZKPs, for instance, can be used to demonstrate the sharing of a specific piece of data between two parties without disclosing the details of the data itself.

5. Kubernetes deployments audited Without disclosing the specifics of the deployment or the data being processed, ZKPs can be used to demonstrate that Kubernetes deployments are working as planned. This can be helpful for auditing purposes and for ensuring that Kubernetes deployments are operating as planned.

ZKPs preserve data and maintain regulatory compliance by letting parties prove things without revealing sensitive information. ZKPs will be used more in Kubernetes as it grows.

Reflections on the closed company Hola! Dating app

I'll discuss my fuckups as an entrepreneur and CEO. All of them refer to the dating app Hola!, which I co-founded and starred in.

Spring 2021 was when we started. Two techies and two non-techies created a dating app. Pokemon Go and Tinder were combined.

Online dating is a business, and it takes two weeks from a like to a date. We questioned online dating app users if they met anyone offline last year.

75% replied yes, 50% sometimes, 25% usually.

Offline dating is popular, yet people have concerns.

• Men are reluctant to make mistakes in front of others.

• Women are curious about the background of everyone who approaches them.

We designed unique mechanics that let people date after a match. No endless chitchat. Women would be safe while men felt like cowboys.

I wish to emphasize three faults that lead to founders' estrangement.

This detachment ultimately led to us shutting down the company.

The wrong technology stack

Situation

Instead of generating a faster MVP and designing an app in a universal stack for iOS and Android, I argued we should pilot the app separately for iOS and Android. Technical founders' expertise made this possible.

Self-reflection

Mistaken strategy. We lost time and resources developing two apps at once. We chose iOS since it's more profitable. Apple took us out after the release, citing Guideline 4.3 Spam. After 4 months, we had nothing. We had a long way to go to get the app on Android and the Store.

I suggested creating a uniform platform for the company's growth. This makes parallel product development easier. The strategist's lack of experience and knowledge made it a piece of crap.

What would I have changed if I could?

We should have designed an Android universal stack. I expected Apple to have issues with a dating app.

Our approach should have been to launch something and subsequently improve it, but prejudice won.

The lesson

Discuss the IT stack with your CTO. It saves time and money. Choose the easiest MVP method.

2. A tardy search for investments

Situation

Though the universe and other founders encouraged me to locate investors first, I started pitching when we almost had an app.

When angels arrived, it was time to close. The app was banned, war broke out, I left the country, and the other co-founders stayed. We had no savings.

Self-reflection

I loved interviewing users. I'm proud of having done 1,000 interviews. I wanted to understand people's pain points and improve the product.

Interview results no longer affected the product. I was terrified to start pitching. I filled out accelerator applications and redid my presentation. You must go through that so you won't be terrified later.

What would I have changed if I could?

Get an external or internal mentor to help me with my first pitch as soon as possible. I'd be supported if criticized. He'd cheer with me if there was enthusiasm.

In 99% of cases, I'm comfortable jumping into the unknown, but there are exceptions. The mentor's encouragement would have prompted me to act sooner.

The lesson

Begin fundraising immediately. Months may pass. Show investors your pre-MVP project. Draw inferences from feedback.

3. Role ambiguity

Situation

My technical co-founders were also part-time lead developers, which produced communication issues. As co-founders, we communicated well and recognized the problems. Stakes, vesting, target markets, and approach were agreed upon.

We were behind schedule. Technical debt and strategic gap grew.

Bi-daily and weekly reviews didn't help. Each time, there were explanations. Inside, I was freaking out.

Self-reflection

I am a fairly easy person to talk to. I always try to stick to agreements; otherwise, my head gets stuffed with unnecessary information, interpretations, and emotions.

Sit down -> talk -> decide -> do -> evaluate the results. Repeat it.

If I don't get detailed comments, I start ruining everyone's mood. If there's a systematic violation of agreements without a good justification, I won't join the project or I'll end the collaboration.

What would I have done otherwise?

This is where it’s scariest to draw conclusions. Probably the most logical thing would have been not to start the project as we started it. But that was already a completely different project. So I would not have done anything differently and would have failed again.

But I drew conclusions for the future.

The lesson

First-time founders should find an adviser or team coach for a strategic session. It helps split the roles and responsibilities.

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.

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!