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.

This method scrapes websites with ChatGPT (demo with Amazon and Twitter)

In a recent article, I demonstrated how to scrape websites using ChatGPT prompts like scrape website X using Python.

But that doesn’t always work.

After scraping dozens of websites with ChatGPT, I realized that simple prompts rarely work for web scraping.

Using ChatGPT and basic HTML, we can scrape any website.

First things first, use ChatGPT's advanced version (Playground)

ChatGPT Playground's enhanced version is needed to scrape websites quickly. It generates code faster and has less constraints.

Here’s how it looks.

The classic ChatGPT display just allows you to type a prompt. Playground is more customizable and generates code faster than the basic version.

No more delays or restrictions.

In this tutorial, we'll write prompts underneath Playground.

How to Use ChatGPT to Scrape Any Website

To show you how to utilize ChatGPT to scrape any website, we'll use subslikescript, which lists movies.

Later in this post, I'll show you how to scrape Amazon and Twitter, but let's start easy.

If we try a basic prompt like “scrape the movie titles on this website: https://subslikescript.com/movies” it won’t scrape anything. Here’s when we need some HTML knowledge to build the right prompt for ChatGPT.Let's scrape the above movie titles. First, check the webpage. Right-click any element and choose Inspect.

Then see below.

We identify the element to scrape (those in the red box). The data elements are ul, a, and scripts-list.

Here's the prompt for movie titles.

Scrape this website: https://subslikescript.com/movies with Python and Beautiful Soup. Locate the element with tag “ul” and class “scripts-list”. Scrape all the “a” elements inside. Get the text attribute and print it.

Code generated:

import requests
from bs4 import BeautifulSoup

page = requests.get('https://subslikescript.com/movies/')

soup = BeautifulSoup(page.content, 'html.parser')

scripts_list = soup.find(class_="scripts-list")

all_a_elements = scripts_list.find_all('a')

for element in all_a_elements:
    print(element.get_text())

It extracts movie titles successfully.

Let's scrape Amazon and Twitter.

ChatGPT's Amazon scraping

Consider scraping Amazon for self-help books. First, copy the Amazon link for self-help books.

Here’s the link I got. Location-dependent connection. Use my link to replicate my results.

Now we'll check book titles. Here's our element.

If we want to extract the book titles, we need to use the tag name span, class attribute name and a-size-base-plus a-color-base a-text-normalattribute value.

This time I'll use Selenium. I'll add Selenium-specific commands like wait 5 seconds and generate an XPath.

Scrape this website https://www.amazon.com/s?k=self+help+books&sprefix=self+help+%2Caps%2C158&ref=nb_sb_ss_ts-doa-p_2_10 with Python and Selenium.

Wait 5 seconds and locate all the elements with the following xpath: “span” tag, “class” attribute name, and “a-size-base-plus a-color-base a-text-normal” attribute value. Get the text attribute and print them.

Code generated: (I only had to manually add the path where my chromedriver is located).

from selenium import webdriver
from selenium.webdriver.common.by import By
from time import sleep

#initialize webdriver
driver = webdriver.Chrome('<add path of your chromedriver>')

#navigate to the website
driver.get("https://www.amazon.com/s?k=self+help+books&sprefix=self+help+%2Caps%2C158&ref=nb_sb_ss_ts-doa-p_2_10")

#wait 5 seconds to let the page load
sleep(5)

#locate all the elements with the following xpath
elements = driver.find_elements(By.XPATH, '//span[@class="a-size-base-plus a-color-base a-text-normal"]')

#get the text attribute of each element and print it
for element in elements:
    print(element.text)

#close the webdriver
driver.close()

It pulls Amazon book titles.

Utilizing ChatGPT to scrape Twitter

Say you wish to scrape ChatGPT tweets. Search Twitter for ChatGPT and copy the URL.

Here’s the link I got. We must check every tweet. Here's our element.

To extract a tweet, use the div tag and lang attribute.

Again, Selenium.

Scrape this website: https://twitter.com/search?q=chatgpt&src=typed_query using Python, Selenium and chromedriver.

Maximize the window, wait 15 seconds and locate all the elements that have the following XPath: “div” tag, attribute name “lang”. Print the text inside these elements.

Code generated: (again, I had to add the path where my chromedriver is located)

from selenium import webdriver
import time

driver = webdriver.Chrome("/Users/frankandrade/Downloads/chromedriver")
driver.maximize_window()
driver.get("https://twitter.com/search?q=chatgpt&src=typed_query")
time.sleep(15)

elements = driver.find_elements_by_xpath("//div[@lang]")
for element in elements:
    print(element.text)

driver.quit()

You'll get the first 2 or 3 tweets from a search. To scrape additional tweets, click X times.

Congratulations! You scraped websites without coding by using ChatGPT.

TOP APPS

Who survives spring cleaning?

Relax. Notion is off-limits. This topic is popular.

(I wrote about it 2 years ago, before everyone else did.) So).

These apps are probably new to you. I hope you find a new phone app after reading this.

Outdooractive

ViewRanger is Google Maps for outdoor enthusiasts.

This app has been so important to me as a freedom-loving long-distance walker and hiker.

This app shows nearby trails and right-of-ways on top of an Open Street Map.

Helpful detail and data. Any route's distance,

You can download and follow tons of routes planned by app users.

This has helped me find new routes and places a fellow explorer has tried.

Free with non-intrusive ads. Years passed before I subscribed. Pro costs £2.23/month.

This app is for outdoor lovers.

Google Files

New phones come with bloatware. These rushed apps are frustrating.

We must replace these apps. 2017 was Google's year.

Files is a file manager. It's quick, innovative, and clean. They've given people what they want.

It's easy to organize files, clear space, and clear cache.

I recommend Gallery by Google as a gallery app alternative. It's quick and easy.

Trainline

App for trains, buses, and coaches.

I've used this app for years. It did the basics well when I first used it.

Since then, it's improved. It's constantly adding features to make traveling easier and less stressful.

Split-ticketing helps me save hundreds a year on train fares. This app is only available in the UK and Europe.

This service doesn't link to a third-party site. Their app handles everything.

Not all train and coach companies use this app. All the big names are there, though.

Here's more on the app.

Battlefield: Mobile

Play Store has 478,000 games. Few can turn my phone into a console.

Call of Duty Mobile and Asphalt 8/9 are examples.

Asphalt's loot boxes and ads make it unplayable. Call of Duty opens with a few ads. Close them to play without hassle.

This game uses all your phone's features to provide a high-quality, seamless experience. If my internet connection is good, I never experience lag or glitches.

The gameplay is energizing and intense, just like on consoles. Sometimes I'm too involved. I've thrown my phone in anger. I'm totally absorbed.

Customizability is my favorite. Since phones have limited screen space, we should only have the buttons we need, placed conveniently.

Size, opacity, and position are modifiable. Adjust audio, graphics, and textures. It's customizable.

This game has been on my phone for three years. It began well and has gotten better. When I think the creators can't do more, they do.

If you play, read my tips for winning a Battle Royale.

Lightroom

As a photographer, I believe your best camera is on you. The phone.

2017 was a big year for this app. I've tried many photo-editing apps since then. This always wins.

The app is dull. I've never seen better photo editing on a phone.

Adjusting settings and sliders doesn't damage or compress photos. It's detailed.

This is important for phone photos, which are lower quality than professional ones.

Some tools are behind a £4.49/month paywall. Adobe must charge a subscription fee instead of selling licenses. (I'm still bitter about Creative Cloud's price)

Snapseed is my pick. Lightroom is where I do basic editing before moving to Snapseed. Snapseed review:

These apps are great. They cover basic and complex editing needs while traveling.

Final Reflections

I hope you downloaded one of these. Share your favorite apps. These apps are scarce.

This post is for you if you can't read or study for 5 minutes.

If you clicked this post, you may be experiencing problems focusing on tasks. A few minutes of reading may tire you. Easily distracted? Using social media and video games for hours without being sidetracked may impair your dopamine system.

When we achieve a goal, the brain secretes dopamine. It might be as simple as drinking water or as crucial as college admission. Situations vary. Various events require different amounts.

Dopamine is released when we start learning but declines over time. Social media algorithms provide new material continually, making us happy. Social media use slows down the system. We can't continue without an award. We return to social media and dopamine rewards.

Mice were given a button that released dopamine into their brains to study the hormone. The mice lost their hunger, thirst, and libido and kept pressing the button. Think this is like someone who spends all day gaming or on Instagram?

When we cause our brain to release so much dopamine, the brain tries to balance it in 2 ways:

1- Decreases dopamine production

2- Dopamine cannot reach its target.

Too many quick joys aren't enough. We'll want more joys. Drugs and alcohol are similar. Initially, a beer will get you drunk. After a while, 3-4 beers will get you drunk.

Social media is continually changing. Updates to these platforms keep us interested. When social media conditions us, we can't read a book.

Same here. I used to complete a book in a day and work longer without distraction. Now I'm addicted to Instagram. Daily, I spend 2 hours on social media. This must change. My life needs improvement. So I started the 50-day challenge.

I've compiled three dopamine-related methods.

Recommendations:

1. Day-long dopamine detox

First, take a day off from all your favorite things. Social media, gaming, music, junk food, fast food, smoking, alcohol, friends. Take a break.

Hanging out with friends or listening to music may seem pointless. Our minds are polluted. One day away from our pleasures can refresh us.

2. One-week dopamine detox by selecting

Choose one or more things to avoid. Social media, gaming, music, junk food, fast food, smoking, alcohol, friends. Try a week without Instagram or Twitter. I use this occasionally.

1. One week all together

One solid detox week. It's the hardest program. First or second options are best for dopamine detox. Time will help you.

You can walk, read, or pray during a dopamine detox. Many options exist. If you want to succeed, you must avoid instant gratification. Success after hard work is priceless.