GM Friens

The space had better days. Those greenish spikes...oh wow, haven't felt that in ages. Cryptocurrencies and NFTs have lost popularity. Google agrees. Both are declining.

As seen below, crypto interest spiked in May because of the Luna fall. NFT interest is similar to early October last year.

This makes me think NFTs are mostly hype and FOMO. No art or community. I've seen enough initiatives to know that communities stick around if they're profitable. Once it starts falling, they move on to the next project. The space has no long-term investments. Flip everything.

OpenSea trading volume has stayed steady for months. May's volume is 1.8 million ETH ($3.3 billion).

Despite this, I think NFTs and crypto will stick around. In bad markets, builders gain most.

Only 4k developers are active on Ethereum blockchain. It's low. A great chance for the space enthusiasts.

An employee of OpenSea might get a 40-year prison sentence for insider trading using NFTs.

Nathaniel Chastian, an OpenSea employee, traded on insider knowledge. He'll serve 40 years for that.

Here's what happened if you're unfamiliar.

OpenSea is a secondary NFT marketplace. Their homepage featured remarkable drops. Whatever gets featured there, NFT prices will rise 5x.

Chastian was at OpenSea. He chose forthcoming NFTs for OpenSeas' webpage.

Using anonymous digital currency wallets and OpenSea accounts, he would buy NFTs before promoting them on the homepage, showcase them, and then sell them for at least 25 times the price he paid.

From June through September 2021, this happened. Later caught, fired. He's charged with wire fraud and money laundering, each carrying a 20-year maximum penalty.

Although web3 space is all about decentralization, a step like this is welcomed since it restores faith in the area. We hope to see more similar examples soon.

Here's the press release.

Understanding smart contracts

@cantino.eth has a Twitter thread on smart contracts. Must-read. Also, he appears educated about the space, so follow him.

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.

Corn Kid got viral on TikTok after being interviewed by Recess Therapy. Tariq, called the Corn Kid, ate a buttery ear of corn in the video. He's corn crazy. He thinks everyone just has to try it. It turns out, whether we know it or not, we already have.

Corn is a fruit, veggie, and grain. It's the second-most-grown crop. Corn makes up 36% of U.S. exports. In the U.S., it's easy to grow and provides high yields, as proven by the vast corn belt spanning the Midwest, Great Plains, and Texas panhandle. Since 1950, the corn crop has doubled to 10 billion bushels.

You say, "Fine." We shouldn't just grow because we can. Why so much corn? What's this corn for?

Why is practical and political. Michael Pollan's The Omnivore's Dilemma has the full narrative. Early 1970s food costs increased. Nixon subsidized maize to feed the public. Monsanto genetically engineered corn seeds to make them hardier, and soon there was plenty of corn. Everyone ate. Woot! Too much corn followed. The powers-that-be had to decide what to do with leftover corn-on-the-cob.

They are fortunate that corn has a wide range of uses.

First, the edible variants. I divide corn into obvious and stealth.

Obvious corn includes popcorn, canned corn, and corn on the cob. This form isn't always digested and often comes out as entire, polka-dotting poop. Cornmeal can be ground to make cornbread, polenta, and corn tortillas. Corn provides antioxidants, minerals, and vitamins in moderation. Most synthetic Vitamin C comes from GMO maize.

Corn oil, corn starch, dextrose (a sugar), and high-fructose corn syrup are often overlooked. They're stealth corn because they sneak into practically everything. Corn oil is used for frying, baking, and in potato chips, mayonnaise, margarine, and salad dressing. Baby food, bread, cakes, antibiotics, canned vegetables, beverages, and even dairy and animal products include corn starch. Dextrose appears in almost all prepared foods, excluding those with high-fructose corn syrup. HFCS isn't as easily digested as sucrose (from cane sugar). It can also cause other ailments, which we'll discuss later.

Most foods contain corn. It's fed to almost all food animals. 96% of U.S. animal feed is corn. 39% of U.S. corn is fed to livestock. But animals prefer other foods. Omnivore chickens prefer insects, worms, grains, and grasses. Captive cows are fed a total mixed ration, which contains corn. These animals' products, like eggs and milk, are also corn-fed.

There are numerous non-edible by-products of corn that are employed in the production of items like:

1. fuel-grade ethanol

2. plastics

3. batteries

4. cosmetics

5. meds/vitamins binder

6. carpets, fabrics

7. glutathione

8. crayons

9. Paint/glue

How does corn influence you? Consider quick food for dinner. You order a cheeseburger, fries, and big Coke at the counter (or drive-through in the suburbs). You tell yourself, "No corn." All that contains corn. Deconstruct:

Cows fed corn produce meat and cheese. Meat and cheese were bonded with corn syrup and starch (same). The bun (corn flour and dextrose) and fries were fried in maize oil. High fructose corn syrup sweetens the drink and helps make the cup and straw.

Just about everything contains corn. Then what? A cornspiracy, perhaps? Is eating too much maize an issue, or should we strive to stay away from it whenever possible?

As I've said, eating some maize can be healthy. 92% of U.S. corn is genetically modified, according to the Center for Food Safety. The adjustments are expected to boost corn yields. Some sweet corn is genetically modified to produce its own insecticide, a protein deadly to insects made by Bacillus thuringiensis. It's safe to eat in sweet corn. Concerns exist about feeding agricultural animals so much maize, modified or not.

High fructose corn syrup should be consumed in moderation. Fructose, a sugar, isn't easily metabolized. Fructose causes diabetes, fatty liver, obesity, and heart disease. It causes inflammation, which might aggravate gout. Candy, packaged sweets, soda, fast food, juice drinks, ice cream, ice cream topping syrups, sauces & condiments, jams, bread, crackers, and pancake syrup contain the most high fructose corn syrup. Everyday foods with little nutrients. Check labels and choose cane sugar or sucrose-sweetened goods. Or, eat corn like the Corn Kid.

Note-taking is a vital skill. But it's mostly learned.

Recently, innovative note-taking apps have flooded the market.

In the next few years, Evernote and Craft will be important digital note-taking companies.

Evernote is a 2008 note-taking program. It can capture ideas, track tasks, and organize information on numerous platforms.

It's one of the only note-taking app that lets users input text, audio, photos, and videos. It's great for collecting research notes, brainstorming, and remaining organized.

Craft is a popular note-taking app.

Craft is a more concentrated note-taking application than Evernote. It organizes notes into subjects, tags, and relationships, making it ideal for technical or research notes.

Craft's search engine makes it easy to find what you need.

Both Evernote and Craft are likely to be the major players in digital note-taking in the years to come.

Their concentration on gathering and organizing information lets users generate notes quickly and simply. Multimedia elements and a strong search engine make them the note-taking apps of the future.

Evernote and Craft are great note-taking tools for staying organized and tracking ideas and projects.

With their focus on acquiring and organizing information, they'll dominate digital note-taking in 2023.

Pros

• Concentrate on gathering and compiling information

• special features including a strong search engine and multimedia components

• Possibility of subject, tag, and relationship structuring

• enables users to incorporate multimedia elements

• Excellent tool for maintaining organization, arranging research notes, and brainstorming

Cons

• Software may be difficult for folks who are not tech-savvy to utilize.

• Limited assistance for hardware running an outdated operating system

• Subscriptions could be pricey.

• Data loss risk because of security issues

Evernote and Craft both have downsides.

1. The risk of data loss as a result of security flaws and software defects comes first.

2. Additionally, their subscription fees could be high, and they might restrict support for hardware that isn't running the newest operating systems.

3. Finally, folks who need to be tech-savvy may find the software difficult.

Evernote versus. Productivity Titans Evernote will make Notion more useful. medium.com