As the world watches the Russia-Ukraine border situation, This bill would bar aid to Ukraine until the Mexican border is secured.
Although Mexico and Ukraine are thousands of miles apart, this legislation would link their responses.
Context
Ukraine was a Soviet republic until 1991. A significant proportion of the population, particularly in the east, is ethnically Russian. In February, the Russian military invaded Ukraine, intent on overthrowing its democratically elected government.
This could be the biggest European land invasion since WWII. In response, President Joe Biden sent 3,000 troops to NATO countries bordering Ukraine to help with Ukrainian refugees, with more troops possible if the situation worsened.
In July 2021, the US Border Patrol reported its highest monthly encounter total since March 2000. Some Republicans compare Biden's response to the Mexican border situation to his response to the Ukrainian border situation, though the correlation is unclear.
What the bills do
Two new Republican bills seek to link the US response to Ukraine to the situation in Mexico.
The Secure America's Borders First Act would prohibit federal funding for Ukraine until the US-Mexico border is “operationally controlled,” including a wall as promised by former President Donald Trump. (The bill even mandates a 30-foot-high wall.)
The USB (Ukraine and Southern Border) Act, introduced on February 8 by Rep. Matt Rosendale (R-MT0), would allow the US to support Ukraine, but only if the number of Armed Forces deployed there is less than the number deployed to the Mexican border. Madison Cawthorne introduced H.R. 6665 on February 9th (R-NC11).
What backers say
Supporters argue that even if the US should militarily assist Ukraine, our own domestic border situation should take precedence.
After failing to secure our own border and protect our own territorial integrity, ‘America Last' politicians on both sides of the aisle now tell us that we must do so for Ukraine. “Before rushing America into another foreign conflict over an Eastern European nation's border thousands of miles from our shores, they should first secure our southern border.”
“If Joe Biden truly cared about Americans, he would prioritize national security over international affairs,” Rep. Cawthorn said in a separate press release. The least we can do to secure our own country is send the same number of troops to the US-Mexico border to assist our border patrol agents working diligently to secure America.
What opponents say
The president has defended his Ukraine and Mexico policies, stating that both seek peace and diplomacy.
Our nations [the US and Mexico] have a long and complicated history, and we haven't always been perfect neighbors, but we have seen the power and purpose of cooperation,” Biden said in 2021. “We're safer when we work together, whether it's to manage our shared border or stop the pandemic. [In both the Obama and Biden administration], we made a commitment that we look at Mexico as an equal, not as somebody who is south of our border.”
No mistake: If Russia goes ahead with its plans, it will be responsible for a catastrophic and unnecessary war of choice. To protect our collective security, the United States and our allies are ready to defend every inch of NATO territory. We won't send troops into Ukraine, but we will continue to support the Ukrainian people... But, I repeat, Russia can choose diplomacy. It is not too late to de-escalate and return to the negotiating table.”
Odds of passage
The Secure America's Borders First Act has nine Republican sponsors. Either the House Armed Services or Foreign Affairs Committees may vote on it.
Rep. Paul Gosar, a Republican, co-sponsored the USB Act (R-AZ4). The House Armed Services Committee may vote on it.
With Republicans in control, passage is unlikely.
More on Current Events
Erik Engheim
3 years ago
You Misunderstand the Russian Nuclear Threat
Many believe Putin is simply sabre rattling and intimidating us. They see no threat of nuclear war. We can send NATO troops into Ukraine without risking a nuclear war.
I keep reading that Putin is just using nuclear blackmail and that a strong leader will call the bluff. That, in my opinion, misunderstands the danger of sending NATO into Ukraine.
It assumes that once NATO moves in, Putin can either push the red nuclear button or not.
Sure, Putin won't go nuclear if NATO invades Ukraine. So we're safe? Can't we just move NATO?
No, because history has taught us that wars often escalate far beyond our initial expectations. One domino falls, knocking down another. That's why having clear boundaries is vital. Crossing a seemingly harmless line can set off a chain of events that are unstoppable once started.
One example is WWI. The assassin of Archduke Franz Ferdinand could not have known that his actions would kill millions. They couldn't have known that invading Serbia to punish them for not handing over the accomplices would start a world war. Every action triggered a counter-action, plunging Europe into a brutal and bloody war. Each leader saw their actions as limited, not realizing how they kept the dominos falling.
Nobody can predict the future, but it's easy to imagine how NATO intervention could trigger a chain of events leading to a total war. Let me suggest some outcomes.
NATO creates a no-fly-zone. In retaliation, Russia bombs NATO airfields. Russia may see this as a limited counter-move that shouldn't cause further NATO escalation. They think it's a reasonable response to force NATO out of Ukraine. Nobody has yet thought to use the nuke.
Will NATO act? Polish airfields bombed, will they be stuck? Is this an article 5 event? If so, what should be done?
It could happen. Maybe NATO sends troops into Ukraine to punish Russia. Maybe NATO will bomb Russian airfields.
Putin's response Is bombing Russian airfields an invasion or an attack? Remember that Russia has always used nuclear weapons for defense, not offense. But let's not panic, let's assume Russia doesn't go nuclear.
Maybe Russia retaliates by attacking NATO military bases with planes. Maybe they use ships to attack military targets. How does NATO respond? Will they fight Russia in Ukraine or escalate? Will they invade Russia or attack more military installations there?
Seen the pattern? As each nation responds, smaller limited military operations can grow in scope.
So far, the Russian military has shown that they begin with less brutal methods. As losses and failures increase, brutal means are used. Syria had the same. Assad used chemical weapons and attacked hospitals, schools, residential areas, etc.
A NATO invasion of Ukraine would cost Russia dearly. “Oh, this isn't looking so good, better pull out and finish this war,” do you think? No way. Desperate, they will resort to more brutal tactics. If desperate, Russia has a huge arsenal of ugly weapons. They have nerve agents, chemical weapons, and other nasty stuff.
What happens if Russia uses chemical weapons? What if Russian nerve agents kill NATO soldiers horribly? West calls for retaliation will grow. Will we invade Russia? Will we bomb them?
We are angry and determined to punish war criminal Putin, so NATO tanks may be heading to Moscow. We want vengeance for his chemical attacks and bombing of our cities.
Do you think the distance between that red nuclear button and Putin's finger will be that far once NATO tanks are on their way to Moscow?
We might avoid a nuclear apocalypse. A NATO invasion force or even Western cities may be used by Putin. Not as destructive as ICBMs. Putin may think we won't respond to tactical nukes with a full nuclear counterattack. Why would we risk a nuclear Holocaust by launching ICBMs on Russia?
Maybe. My point is that at every stage of the escalation, one party may underestimate the other's response. This war is spiraling out of control and the chances of a nuclear exchange are increasing. Nobody really wants it.
Fear, anger, and resentment cause it. If Putin and his inner circle decide their time is up, they may no longer care about the rest of the world. We saw it with Hitler. Hitler, seeing the end of his empire, ordered the destruction of Germany. Nobody should win if he couldn't. He wanted to destroy everything, including Paris.
In other words, the danger isn't what happens after NATO intervenes The danger is the potential chain reaction. Gambling has a psychological equivalent. It's best to exit when you've lost less. We humans are willing to take small risks for big rewards. To avoid losses, we are willing to take high risks. Daniel Kahneman describes this behavior in his book Thinking, Fast and Slow.
And so bettors who have lost a lot begin taking bigger risks to make up for it. We get a snowball effect. NATO involvement in the Ukraine conflict is akin to entering a casino and placing a bet. We'll start taking bigger risks as we start losing to Russian retaliation. That's the game's psychology.
It's impossible to stop. So will politicians and citizens from both Russia and the West, until we risk the end of human civilization.
You can avoid spiraling into ever larger bets in the Casino by drawing a hard line and declaring “I will not enter that Casino.” We're doing it now. We supply Ukraine. We send money and intelligence but don't cross that crucial line.
It's difficult to watch what happened in Bucha without demanding NATO involvement. What should we do? Of course, I'm not in charge. I'm a writer. My hope is that people will think about the consequences of the actions we demand. My hope is that you think ahead not just one step but multiple dominos.
More and more, we are driven by our emotions. We cannot act solely on emotion in matters of life and death. If we make the wrong choice, more people will die.
Read the original post here.
Cory Doctorow
3 years ago
The downfall of the Big Four accounting companies is just one (more) controversy away.
Economic mutual destruction.
Multibillion-dollar corporations never bothered with an independent audit, and they all lied about their balance sheets.
It's easy to forget that the Big Four accounting firms are lousy fraud enablers. Just because they sign off on your books doesn't mean you're not a hoax waiting to erupt.
This is *crazy* Capitalism depends on independent auditors. Rich folks need to know their financial advisers aren't lying. Rich folks usually succeed.
No accounting. EY, KPMG, PWC, and Deloitte make more money consulting firms than signing off on their accounts.
The Big Four sign off on phony books because failing to make friends with unscrupulous corporations may cost them consulting contracts.
The Big Four are the only firms big enough to oversee bankruptcy when they sign off on fraudulent books, as they did for Carillion in 2018. All four profited from Carillion's bankruptcy.
The Big Four are corrupt without any consequences for misconduct. Who can forget when KPMG's top management was fined millions for helping auditors cheat on ethics exams?
Consulting and auditing conflict. Consultants help a firm cover its evil activities, such as tax fraud or wage theft, whereas auditors add clarity to a company's finances. The Big Four make more money from cooking books than from uncooking them, thus they are constantly embroiled in scandals.
If a major scandal breaks, it may bring down the entire sector and substantial parts of the economy. Jim Peterson explains system risk for The Dig.
The Big Four are voluntary private partnerships where accountants invest their time, reputations, and money. If a controversy threatens the business, partners who depart may avoid scandal and financial disaster.
When disaster looms, each partner should bolt for the door, even if a disciplined stay-and-hold posture could weather the storm. This happened to Arthur Andersen during Enron's collapse, and a 2006 EU report recognized the risk to other corporations.
Each partner at a huge firm knows how much dirty laundry they've buried in the company's garden, and they have well-founded suspicions about what other partners have buried, too. When someone digs, everyone runs.
If a firm confronts substantial litigation damages or enforcement penalties, it could trigger the collapse of one of the Big Four. That would be bad news for the firm's clients, who would have trouble finding another big auditor.
Most of the world's auditing capacity is concentrated in four enormous, brittle, opaque, compromised organizations. If one of them goes bankrupt, the other three won't be able to take on its clients.
Peterson: Another collapse would strand many of the world's large public businesses, leaving them unable to obtain audit views for their securities listings and regulatory compliance.
Count Down: The Past, Present, and Uncertain Future of the Big Four Accounting Firms is in its second edition.
https://www.emerald.com/insight/publication/doi/10.1108/9781787147003
Claire Berehova
3 years ago
There’s no manual for that
| Kyiv oblast in springtime. Photo by author. |
We’ve been receiving since the war began text messages from the State Emergency Service of Ukraine every few days. They’ve contained information on how to comfort a child and what to do in case of a water outage.
But a question that I struggle to suppress irks within me: How would we know if there really was a threat coming our away? So how can I happily disregard an air raid siren and continue singing to my three-month-old son when I feel like a World War II film became reality? There’s no manual for that.
Along with the anxiety, there’s the guilt that always seems to appear alongside dinner we’re fortunate to still have each evening while brave Ukrainian soldiers are facing serious food insecurity. There’s no manual for how to deal with this guilt.
When it comes to the enemy, there is no manual for how to react to the news of Russian casualties. Every dead Russian soldier weakens Putin, but I also know that many of these men had wives and girlfriends who are now living a nightmare.
So, I felt like I had to start writing my own manual.
The anxiety around the air raid siren? Only with time does it get easier to ignore it, but never completely.
The guilt? All we can do is pray.
That inner conflict? As Russia continues to stun the world with its war crimes, my emotions get less gray — I have to get used to accommodating absurd levels of hatred.
Sadness? It feels a bit more manageable when we laugh, and a little alcohol helps (as it usually does).
Cabin fever? Step outside in the yard when possible. At least the sunshine is becoming more fervent with spring approaching.
Slava Ukraini. Heroyam slava. (Glory to Ukraine. Glory to the heroes.)
You might also like
Amelia Winger-Bearskin
3 years ago
Hate NFTs? I must break some awful news to you...
If you think NFTs are awful, check out the art market.
The fervor around NFTs has subsided in recent months due to the crypto market crash and the media's short attention span. They were all anyone could talk about earlier this spring. Last semester, when passions were high and field luminaries were discussing "slurp juices," I asked my students and students from over 20 other universities what they thought of NFTs.
According to many, NFTs were either tasteless pyramid schemes or a new way for artists to make money. NFTs contributed to the climate crisis and harmed the environment, but so did air travel, fast fashion, and smartphones. Some students complained that NFTs were cheap, tasteless, algorithmically generated schlock, but others asked how this was different from other art.
I'm not sure what I expected, but the intensity of students' reactions surprised me. They had strong, emotional opinions about a technology I'd always considered administrative. NFTs address ownership and accounting, like most crypto/blockchain projects.
Art markets can be irrational, arbitrary, and subject to the same scams and schemes as any market. And maybe a few shenanigans that are unique to the art world.
The Fairness Question
Fairness, a deflating moral currency, was the general sentiment (the less of it in circulation, the more ardently we clamor for it.) These students, almost all of whom are artists, complained to the mismatch between the quality of the work in some notable NFT collections and the excessive amounts these items were fetching on the market. They can sketch a Bored Ape or Lazy Lion in their sleep. Why should they buy ramen with school loans while certain swindlers get rich?
I understand students. Art markets are unjust. They can be irrational, arbitrary, and governed by chance and circumstance, like any market. And art-world shenanigans.
Almost every mainstream critique leveled against NFTs applies just as easily to art markets
Over 50% of artworks in circulation are fake, say experts. Sincere art collectors and institutions are upset by the prevalence of fake goods on the market. Not everyone. Wealthy people and companies use art as investments. They can use cultural institutions like museums and galleries to increase the value of inherited art collections. People sometimes buy artworks and use family ties or connections to museums or other cultural taste-makers to hype the work in their collection, driving up the price and allowing them to sell for a profit. Money launderers can disguise capital flows by using market whims, hype, and fluctuating asset prices.
Almost every mainstream critique leveled against NFTs applies just as easily to art markets.
Art has always been this way. Edward Kienholz's 1989 print series satirized art markets. He stamped 395 identical pieces of paper from $1 to $395. Each piece was initially priced as indicated. Kienholz was joking about a strange feature of art markets: once the last print in a series sells for $395, all previous works are worth at least that much. The entire series is valued at its highest auction price. I don't know what a Kienholz print sells for today (inquire with the gallery), but it's more than $395.
I love Lee Lozano's 1969 "Real Money Piece." Lozano put cash in various denominations in a jar in her apartment and gave it to visitors. She wrote, "Offer guests coffee, diet pepsi, bourbon, half-and-half, ice water, grass, and money." "Offer real money as candy."
Lee Lozano kept track of who she gave money to, how much they took, if any, and how they reacted to the offer of free money without explanation. Diverse reactions. Some found it funny, others found it strange, and others didn't care. Lozano rarely says:
Apr 17 Keith Sonnier refused, later screws lid very tightly back on. Apr 27 Kaltenbach takes all the money out of the jar when I offer it, examines all the money & puts it all back in jar. Says he doesn’t need money now. Apr 28 David Parson refused, laughing. May 1 Warren C. Ingersoll refused. He got very upset about my “attitude towards money.” May 4 Keith Sonnier refused, but said he would take money if he needed it which he might in the near future. May 7 Dick Anderson barely glances at the money when I stick it under his nose and says “Oh no thanks, I intend to earn it on my own.” May 8 Billy Bryant Copley didn’t take any but then it was sort of spoiled because I had told him about this piece on the phone & he had time to think about it he said.
Smart Contracts (smart as in fair, not smart as in Blockchain)
Cornell University's Cheryl Finley has done a lot of research on secondary art markets. I first learned about her research when I met her at the University of Florida's Harn Museum, where she spoke about smart contracts (smart as in fair, not smart as in Blockchain) and new protocols that could help artists who are often left out of the economic benefits of their own work, including women and women of color.
Her talk included findings from her ArtNet op-ed with Lauren van Haaften-Schick, Christian Reeder, and Amy Whitaker.
NFTs allow us to think about and hack on formal contractual relationships outside a system of laws that is currently not set up to service our community.
The ArtNet article The Recent Sale of Amy Sherald's ‘Welfare Queen' Symbolizes the Urgent Need for Resale Royalties and Economic Equity for Artists discussed Sherald's 2012 portrait of a regal woman in a purple dress wearing a sparkling crown and elegant set of pearls against a vibrant red background.
Amy Sherald sold "Welfare Queen" to Princeton professor Imani Perry. Sherald agreed to a payment plan to accommodate Perry's budget.
Amy Sherald rose to fame for her 2016 portrait of Michelle Obama and her full-length portrait of Breonna Taylor, one of the most famous works of the past decade.
As is common, Sherald's rising star drove up the price of her earlier works. Perry's "Welfare Queen" sold for $3.9 million in 2021.
Imani Perry's early investment paid off big-time. Amy Sherald, whose work directly increased the painting's value and who was on an artist's shoestring budget when she agreed to sell "Welfare Queen" in 2012, did not see any of the 2021 auction money. Perry and the auction house got that money.
Sherald sold her Breonna Taylor portrait to the Smithsonian and Louisville's Speed Art Museum to fund a $1 million scholarship. This is a great example of what an artist can do for the community if they can amass wealth through their work.
NFTs haven't solved all of the art market's problems — fakes, money laundering, market manipulation — but they didn't create them. Blockchain and NFTs are credited with making these issues more transparent. More ideas emerge daily about what a smart contract should do for artists.
NFTs are a copyright solution. They allow us to hack formal contractual relationships outside a law system that doesn't serve our community.
Amy Sherald shows the good smart contracts can do (as in, well-considered, self-determined contracts, not necessarily blockchain contracts.) Giving back to our community, deciding where and how our work can be sold or displayed, and ensuring artists share in the equity of our work and the economy our labor creates.
Dani Herrera
3 years ago
What prevents companies from disclosing salary information?
Yes, salary details ought to be mentioned in job postings. Recruiters and candidates both agree, so why doesn't it happen?
The short answer is “Unfortunately, it’s not the Recruiter’s decision”. The longer answer is well… A LOT.
Starting in November 2022, NYC employers must include salary ranges in job postings. It should have started in May, but companies balked.
I'm thrilled about salary transparency. This decision will promote fair, inclusive, and equitable hiring practices, and I'm sure other states will follow suit. Good news!
Candidates, recruiters, and ED&I practitioners have advocated for pay transparency for years. Why the opposition?
Let's quickly review why companies have trouble sharing salary bands.
💰 Pay Parity
Many companies and leaders still oppose pay parity. Yes, even in 2022.
💰 Pay Equity
Many companies believe in pay parity and have reviewed their internal processes and systems to ensure equality.
However, Pay Equity affects who gets roles/promotions/salary raises/bonuses and when. Enter the pay gap!
💰Pay Transparency and its impact on Talent Retention
Sharing salary bands with external candidates (and the world) means current employees will have access to that information, which is one of the main reasons companies don't share salary data.
If a company has Pay Parity and Pay Equity issues, they probably have a Pay Transparency policy as well.
Sharing salary information with external candidates without ensuring current employees understand their own salary bands and how promotions/raises are decided could impact talent retention strategies.
This information should help clarify recent conversations.
Dmitrii Eliuseev
2 years ago
Creating Images on Your Local PC Using Stable Diffusion AI
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 condaInstall 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 --upgradeDownload 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 1Almost. 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 1Stable 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 1The 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 0.8It 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 ldmHugging 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.ckptThis 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.