When My Remote Leadership Skills Took Off
4 Ways To Manage Remote Teams & Employees
The wheels hit the ground as I landed in Rochester.
Our six-person satellite office was now part of my team.
Their manager only reported to me the day before, but I had my ticket booked ahead of time.
I had managed remote employees before but this was different. Engineers dialed into headquarters for every meeting.
So when I learned about the org chart change, I knew a strong first impression would set the tone for everything else.
I was either their boss, or their boss's boss, and I needed them to know I was committed.
Managing a fleet of satellite freelancers or multiple offices requires treating others as more than just a face behind a screen.
You must comprehend each remote team member's perspective and daily interactions.
The good news is that you can start using these techniques right now to better understand and elevate virtual team members.
1. Make Visits To Other Offices
If budgeted, visit and work from offices where teams and employees report to you. Only by living alongside them can one truly comprehend their problems with communication and other aspects of modern life.
2. Have Others Come to You
• Having remote, distributed, or satellite employees and teams visit headquarters every quarter or semi-quarterly allows the main office culture to rub off on them.
When remote team members visit, more people get to meet them, which builds empathy.
If you can't afford to fly everyone, at least bring remote managers or leaders. Hopefully they can resurrect some culture.
3. Weekly Work From Home
No home office policy?
Make one.
WFH is a team-building, problem-solving, and office-viewing opportunity.
For dial-in meetings, I started working from home on occasion.
It also taught me which teams “forget” or “skip” calls.
As a remote team member, you experience all the issues first hand.
This isn't as accurate for understanding teams in other offices, but it can be done at any time.
4. Increase Contact Even If It’s Just To Chat
Don't underestimate office banter.
Sometimes it's about bonding and trust, other times it's about business.
If you get all this information in real-time, please forward it.
Even if nothing critical is happening, call remote team members to check in and chat.
I guarantee that building relationships and rapport will increase both their job satisfaction and yours.
More on Leadership
Caspar Mahoney
2 years ago
Changing Your Mindset From a Project to a Product
Product game mindsets? How do these vary from Project mindset?
1950s spawned the Iron Triangle. Project people everywhere know and live by it. In stakeholder meetings, it is used to stretch the timeframe, request additional money, or reduce scope.
Quality was added to this triangle as things matured.
Quality was intended to be transformative, but none of these principles addressed why we conduct projects.
Value and benefits are key.
Product value is quantified by ROI, revenue, profit, savings, or other metrics. For me, every project or product delivery is about value.
Most project managers, especially those schooled 5-10 years or more ago (thousands working in huge corporations worldwide), understand the world in terms of the iron triangle. What does that imply? They worry about:
a) enough time to get the thing done.
b) have enough resources (budget) to get the thing done.
c) have enough scope to fit within (a) and (b) >> note, they never have too little scope, not that I have ever seen! although, theoretically, this could happen.
Boom—iron triangle.
To make the triangle function, project managers will utilize formal governance (Steering) to move those things. Increase money, scope, or both if time is short. Lacking funds? Increase time, scope, or both.
In current product development, shifting each item considerably may not yield value/benefit.
Even terrible. This approach will fail because it deprioritizes Value/Benefit by focusing the major stakeholders (Steering participants) and delivery team(s) on Time, Scope, and Budget restrictions.
Pre-agile, this problem was terrible. IT projects failed wildly. History is here.
Value, or benefit, is central to the product method. Product managers spend most of their time planning value-delivery paths.
Product people consider risk, schedules, scope, and budget, but value comes first. Let me illustrate.
Imagine managing internal products in an enterprise. Your core customer team needs a rapid text record of a chat to fix a problem. The consumer wants a feature/features added to a product you're producing because they think it's the greatest spot.
Project-minded, I may say;
Ok, I have budget as this is an existing project, due to run for a year. This is a new requirement to add to the features we’re already building. I think I can keep the deadline, and include this scope, as it sounds related to the feature set we’re building to give the desired result”.
This attitude repeats Scope, Time, and Budget.
Since it meets those standards, a project manager will likely approve it. If they have a backlog, they may add it and start specking it out assuming it will be built.
Instead, think like a product;
What problem does this feature idea solve? Is that problem relevant to the product I am building? Can that problem be solved quicker/better via another route ? Is it the most valuable problem to solve now? Is the problem space aligned to our current or future strategy? or do I need to alter/update the strategy?
A product mindset allows you to focus on timing, resource/cost, feasibility, feature detail, and so on after answering the aforementioned questions.
The above oversimplifies because
Leadership in discovery
Project managers are facilitators of ideas. This is as far as they normally go in the ‘idea’ space.
Business Requirements collection in classic project delivery requires extensive upfront documentation.
Agile project delivery analyzes requirements iteratively.
However, the project manager is a facilitator/planner first and foremost, therefore topic knowledge is not expected.
I mean business domain, not technical domain (to confuse matters, it is true that in some instances, it can be both technical and business domains that are important for a single individual to master).
Product managers are domain experts. They will become one if they are training/new.
They lead discovery.
Product Manager-led discovery is much more than requirements gathering.
Requirements gathering involves a Business Analyst interviewing people and documenting their requests.
The project manager calculates what fits and what doesn't using their Iron Triangle (presumably in their head) and reports back to Steering.
If this requirements-gathering exercise failed to identify requirements, what would a project manager do? or bewildered by project requirements and scope?
They would tell Steering they need a Business SME or Business Lead assigning or more of their time.
Product discovery requires the Product Manager's subject knowledge and a new mindset.
How should a Product Manager handle confusing requirements?
Product Managers handle these challenges with their talents and tools. They use their own knowledge to fill in ambiguity, but they have the discipline to validate those assumptions.
To define the problem, they may perform qualitative or quantitative primary research.
They might discuss with UX and Engineering on a whiteboard and test assumptions or hypotheses.
Do Product Managers escalate confusing requirements to Steering/Senior leaders? They would fix that themselves.
Product managers raise unclear strategy and outcomes to senior stakeholders. Open talks, soft skills, and data help them do this. They rarely raise requirements since they have their own means of handling them without top stakeholder participation.
Discovery is greenfield, exploratory, research-based, and needs higher-order stakeholder management, user research, and UX expertise.
Product Managers also aid discovery. They lead discovery. They will not leave customer/user engagement to a Business Analyst. Administratively, a business analyst could aid. In fact, many product organizations discourage business analysts (rely on PM, UX, and engineer involvement with end-users instead).
The Product Manager must drive user interaction, research, ideation, and problem analysis, therefore a Product professional must be skilled and confident.
Creating vs. receiving and having an entrepreneurial attitude
Product novices and project managers focus on details rather than the big picture. Project managers prefer spreadsheets to strategy whiteboards and vision statements.
These folks ask their manager or senior stakeholders, "What should we do?"
They then elaborate (in Jira, in XLS, in Confluence or whatever).
They want that plan populated fast because it reduces uncertainty about what's going on and who's supposed to do what.
Skilled Product Managers don't only ask folks Should we?
They're suggesting this, or worse, Senior stakeholders, here are some options. After asking and researching, they determine what value this product adds, what problems it solves, and what behavior it changes.
Therefore, to move into Product, you need to broaden your view and have courage in your ability to discover ideas, find insightful pieces of information, and collate them to form a valuable plan of action. You are constantly defining RoI and building Business Cases, so much so that you no longer create documents called Business Cases, it is simply ingrained in your work through metrics, intelligence, and insights.
Product Management is not a free lunch.
Plateless.
Plates and food must be prepared.
In conclusion, Product Managers must make at least three mentality shifts:
You put value first in all things. Time, money, and scope are not as important as knowing what is valuable.
You have faith in the field and have the ability to direct the search. YYou facilitate, but you don’t just facilitate. You wouldn't want to limit your domain expertise in that manner.
You develop concepts, strategies, and vision. You are not a waiter or an inbox where other people can post suggestions; you don't merely ask folks for opinion and record it. However, you excel at giving things that aren't clearly spoken or written down physical form.
Sam Hickmann
3 years ago
Improving collaboration with the Six Thinking Hats
Six Thinking Hats was written by Dr. Edward de Bono. "Six Thinking Hats" and parallel thinking allow groups to plan thinking processes in a detailed and cohesive way, improving collaboration.
Fundamental ideas
In order to develop strategies for thinking about specific issues, the method assumes that the human brain thinks in a variety of ways that can be intentionally challenged. De Bono identifies six brain-challenging directions. In each direction, the brain brings certain issues into conscious thought (e.g. gut instinct, pessimistic judgement, neutral facts). Some may find wearing hats unnatural, uncomfortable, or counterproductive.
The example of "mismatch" sensitivity is compelling. In the natural world, something out of the ordinary may be dangerous. This mode causes negative judgment and critical thinking.
Colored hats represent each direction. Putting on a colored hat symbolizes changing direction, either literally or metaphorically. De Bono first used this metaphor in his 1971 book "Lateral Thinking for Management" to describe a brainstorming framework. These metaphors allow more complete and elaborate thought separation. Six thinking hats indicate ideas' problems and solutions.
Similarly, his CoRT Thinking Programme introduced "The Five Stages of Thinking" method in 1973.
| HAT | OVERVIEW | TECHNIQUE |
|---|---|---|
| BLUE | "The Big Picture" & Managing | CAF (Consider All Factors); FIP (First Important Priorities) |
| WHITE | "Facts & Information" | Information |
| RED | "Feelings & Emotions" | Emotions and Ego |
| BLACK | "Negative" | PMI (Plus, Minus, Interesting); Evaluation |
| YELLOW | "Positive" | PMI |
| GREEN | "New Ideas" | Concept Challenge; Yes, No, Po |
Strategies and programs
After identifying the six thinking modes, programs can be created. These are groups of hats that encompass and structure the thinking process. Several of these are included in the materials for franchised six hats training, but they must often be adapted. Programs are often "emergent," meaning the group plans the first few hats and the facilitator decides what to do next.
The group agrees on how to think, then thinks, then evaluates the results and decides what to do next. Individuals or groups can use sequences (and indeed hats). Each hat is typically used for 2 minutes at a time, although an extended white hat session is common at the start of a process to get everyone on the same page. The red hat is recommended to be used for a very short period to get a visceral gut reaction – about 30 seconds, and in practice often takes the form of dot-voting.
| ACTIVITY | HAT SEQUENCE |
|---|---|
| Initial Ideas | Blue, White, Green, Blue |
| Choosing between alternatives | Blue, White, (Green), Yellow, Black, Red, Blue |
| Identifying Solutions | Blue, White, Black, Green, Blue |
| Quick Feedback | Blue, Black, Green, Blue |
| Strategic Planning | Blue, Yellow, Black, White, Blue, Green, Blue |
| Process Improvement | Blue, White, White (Other People's Views), Yellow, Black, Green, Red, Blue |
| Solving Problems | Blue, White, Green, Red, Yellow, Black, Green, Blue |
| Performance Review | Blue, Red, White, Yellow, Black, Green, Blue |
Use
Speedo's swimsuit designers reportedly used the six thinking hats. "They used the "Six Thinking Hats" method to brainstorm, with a green hat for creative ideas and a black one for feasibility.
Typically, a project begins with extensive white hat research. Each hat is used for a few minutes at a time, except the red hat, which is limited to 30 seconds to ensure an instinctive gut reaction, not judgement. According to Malcolm Gladwell's "blink" theory, this pace improves thinking.
De Bono believed that the key to a successful Six Thinking Hats session was focusing the discussion on a particular approach. A meeting may be called to review and solve a problem. The Six Thinking Hats method can be used in sequence to explore the problem, develop a set of solutions, and choose a solution through critical examination.
Everyone may don the Blue hat to discuss the meeting's goals and objectives. The discussion may then shift to Red hat thinking to gather opinions and reactions. This phase may also be used to determine who will be affected by the problem and/or solutions. The discussion may then shift to the (Yellow then) Green hat to generate solutions and ideas. The discussion may move from White hat thinking to Black hat thinking to develop solution set criticisms.
Because everyone is focused on one approach at a time, the group is more collaborative than if one person is reacting emotionally (Red hat), another is trying to be objective (White hat), and another is critical of the points which emerge from the discussion (Black hat). The hats help people approach problems from different angles and highlight problem-solving flaws.
Aniket
3 years ago
Yahoo could have purchased Google for $1 billion
Let's see this once-dominant IT corporation crumble.
What's the capital of Kazakhstan? If you don't know the answer, you can probably find it by Googling. Google Search returned results for Nur-Sultan in 0.66 seconds.
Google is the best search engine I've ever used. Did you know another search engine ruled the Internet? I'm sure you guessed Yahoo!
Google's friendly UI and wide selection of services make it my top choice. Let's explore Yahoo's decline.
Yahoo!
YAHOO stands for Yet Another Hierarchically Organized Oracle. Jerry Yang and David Filo established Yahoo.
Yahoo is primarily a search engine and email provider. It offers News and an advertising platform. It was a popular website in 1995 that let people search the Internet directly. Yahoo began offering free email in 1997 by acquiring RocketMail.
According to a study, Yahoo used Google Search Engine technology until 2000 and then developed its own in 2004.
Yahoo! rejected buying Google for $1 billion
Larry Page and Sergey Brin, Google's founders, approached Yahoo in 1998 to sell Google for $1 billion so they could focus on their studies. Yahoo denied the offer, thinking it was overvalued at the time.
Yahoo realized its error and offered Google $3 billion in 2002, but Google demanded $5 billion since it was more valuable. Yahoo thought $5 billion was overpriced for the existing market.
In 2022, Google is worth $1.56 Trillion.
What happened to Yahoo!
Yahoo refused to buy Google, and Google's valuation rose, making a purchase unfeasible.
Yahoo started losing users when Google launched Gmail. Google's UI was far cleaner than Yahoo's.
Yahoo offered $1 billion to buy Facebook in July 2006, but Zuckerberg and the board sought $1.1 billion. Yahoo rejected, and Facebook's valuation rose, making it difficult to buy.
Yahoo was losing users daily while Google and Facebook gained many. Google and Facebook's popularity soared. Yahoo lost value daily.
Microsoft offered $45 billion to buy Yahoo in February 2008, but Yahoo declined. Microsoft increased its bid to $47 billion after Yahoo said it was too low, but Yahoo rejected it. Then Microsoft rejected Yahoo’s 10% bid increase in May 2008.
In 2015, Verizon bought Yahoo for $4.5 billion, and Apollo Global Management bought 90% of Yahoo's shares for $5 billion in May 2021. Verizon kept 10%.
Yahoo's opportunity to acquire Google and Facebook could have been a turning moment. It declined Microsoft's $45 billion deal in 2008 and was sold to Verizon for $4.5 billion in 2015. Poor decisions and lack of vision caused its downfall. Yahoo's aim wasn't obvious and it didn't stick to a single domain.
Hence, a corporation needs a clear vision and a leader who can see its future.
Liked this article? Join my tech and programming newsletter here.
You might also like
Abhimanyu Bhargava
3 years ago
VeeFriends Series 2: The Biggest NFT Opportunity Ever
VeeFriends is one NFT project I'm sure will last.
I believe in blockchain technology and JPEGs, aka NFTs. NFTs aren't JPEGs. It's not as it seems.
Gary Vaynerchuk is leading the pack with his new NFT project VeeFriends, I wrote a year ago. I was spot-on. It's the most innovative project I've seen.
Since its minting in May 2021, it has given its holders enormous value, most notably the first edition of VeeCon, a multi-day superconference featuring iconic and emerging leaders in NFTs and Popular Culture. First-of-its-kind NFT-ticketed Web3 conference to build friendships, share ideas, and learn together.
VeeFriends holders got free VeeCon NFT tickets. Attendees heard iconic keynote speeches, innovative talks, panels, and Q&A sessions.
It was a unique conference that most of us, including me, are looking forward to in 2023. The lineup was epic, and it allowed many to network in new ways. Really memorable learning. Here are a couple of gratitude posts from the attendees.
VeeFriends Series 2
This article explains VeeFriends if you're still confused.
GaryVee's hand-drawn doodles have evolved into wonderful characters. The characters' poses and backgrounds bring the VeeFriends IP to life.
Yes, this is the second edition of VeeFriends, and at current prices, it's one of the best NFT opportunities in years. If you have the funds and risk appetite to invest in NFTs, VeeFriends Series 2 is worth every penny. Even if you can't invest, learn from their journey.
1. Art Is the Start
Many critics say VeeFriends artwork is below average and not by GaryVee. Art is often the key to future success.
Let's look at one of the first Mickey Mouse drawings. No one would have guessed that this would become one of the most beloved animated short film characters. In Walt Before Mickey, Walt Disney's original mouse Mortimer was less refined.
First came a mouse...
These sketches evolved into Steamboat Willie, Disney's first animated short film.
Fred Moore redesigned the character artwork into what we saw in cartoons as kids. Mickey Mouse's history is here.
Looking at how different cartoon characters have evolved and gained popularity over decades, I believe Series 2 characters like Self-Aware Hare, Kind Kudu, and Patient Pig can do the same.
GaryVee captures this journey on the blockchain and lets early supporters become part of history. Time will tell if it rivals Disney, Pokemon, or Star Wars. Gary has been vocal about this vision.
2. VeeFriends is Intellectual Property for the Coming Generations
Most of us grew up watching cartoons, playing with toys, cards, and video games. Our interactions with fictional characters and the stories we hear shape us.
GaryVee is slowly curating an experience for the next generation with animated videos, card games, merchandise, toys, and more.
VeeFriends UNO, a collaboration with Mattel Creations, features 17 VeeFriends characters.
VeeFriends and Zerocool recently released Trading Cards featuring all 268 Series 1 characters and 15 new ones. Another way to build VeeFriends' collectibles brand.
At Veecon, all the characters were collectible toys. Something will soon emerge.
Kids and adults alike enjoy the YouTube channel's animated shorts and VeeFriends Tunes. Here's a song by the holder's Optimistic Otter-loving daughter.
This VeeFriends story is only the beginning. I'm looking forward to animated short film series, coloring books, streetwear, candy, toys, physical collectibles, and other forms of VeeFriends IP.
3. Veefriends will always provide utilities
Smart contracts can be updated at any time and authenticated on a ledger.
VeeFriends Series 2 gives no promise of any utility whatsoever. GaryVee released no project roadmap. In the first few months after launch, many owners of specific characters or scenes received utilities.
Every benefit or perk you receive helps promote the VeeFriends brand.
Recent partnerships are listed below.
MaryRuth's Multivitamin Gummies
Productive Puffin holders from VeeFriends x Primitive
Pickleball Scene & Clown Holders Only
Pickleball & Competitive Clown Exclusive experience, anteater multivitamin gummies, and Puffin x Primitive merch
Considering the price of NFTs, it may not seem like much. It's just the beginning; you never know what the future holds. No other NFT project offers such diverse, ongoing benefits.
4. Garyvee's team is ready
Gary Vaynerchuk's team and record are undisputed. He's a serial entrepreneur and the Chairman & CEO of VaynerX, which includes VaynerMedia, VaynerCommerce, One37pm, and The Sasha Group.
Gary founded VaynerSports, Resy, and Empathy Wines. He's a Candy Digital Board Member, VCR Group Co-Founder, ArtOfficial Co-Founder, and VeeFriends Creator & CEO. Gary was recently named one of Fortune's Top 50 NFT Influencers.
Gary Vayenerchuk aka GaryVee
Gary documents his daily life as a CEO on social media, which has 34 million followers and 272 million monthly views. GaryVee Audio Experience is a top podcast. He's a five-time New York Times best-seller and sought-after speaker.
Gary can observe consumer behavior to predict trends. He understood these trends early and pioneered them.
1997 — Realized e-potential commerce's and started winelibrary.com. In five years, he grew his father's wine business from $3M to $60M.
2006 — Realized content marketing's potential and started Wine Library on YouTube. TV
2009 — Estimated social media's potential (Web2) and invested in Facebook, Twitter, and Tumblr.
2014: Ethereum and Bitcoin investments
2021 — Believed in NFTs and Web3 enough to launch VeeFriends
GaryVee isn't all of VeeFriends. Andy Krainak, Dave DeRosa, Adam Ripps, Tyler Dowdle, and others work tirelessly to make VeeFriends a success.
GaryVee has said he'll let other businesses fail but not VeeFriends. We're just beginning his 40-year vision.
I have more confidence than ever in a company with a strong foundation and team.
5. Humans die, but characters live forever
What if GaryVee dies or can't work?
A writer's books can immortalize them. As long as their books exist, their words are immortal. Socrates, Hemingway, Aristotle, Twain, Fitzgerald, and others have become immortal.
Everyone knows Vincent Van Gogh's The Starry Night.
We all love reading and watching Peter Parker, Thor, or Jessica Jones. Their behavior inspires us. Stan Lee's message and stories live on despite his death.
GaryVee represents VeeFriends. Creating characters to communicate ensures that the message reaches even those who don't listen.
Gary wants his values and messages to be omnipresent in 268 characters. Messengers die, but their messages live on.
Gary envisions VeeFriends creating timeless stories and experiences. Ten years from now, maybe every kid will sing Patient Pig.
6. I love the intent.
Gary planned to create Workplace Warriors three years ago when he began designing Patient Panda, Accountable Ant, and Empathy elephant. The project stalled. When NFTs came along, he knew.
Gary wanted to create characters with traits he values, such as accountability, empathy, patience, kindness, and self-awareness. He wants future generations to find these traits cool. He hopes one or more of his characters will become pop culture icons.
These emotional skills aren't taught in schools or colleges, but they're crucial for business and life success. I love that someone is teaching this at scale.
In the end, intent matters.
Humans Are Collectors
Buy and collect things to communicate. Since the 1700s. Medieval people formed communities around hidden metals and stones. Many people still collect stamps and coins, and luxury and fashion are multi-trillion dollar industries. We're collectors.
The early 2020s NFTs will be remembered in the future. VeeFriends will define a cultural and technological shift in this era. VeeFriends Series 1 is the original hand-drawn art, but it's expensive. VeeFriends Series 2 is a once-in-a-lifetime opportunity at $1,000.
If you are new to NFTs, check out How to Buy a Non Fungible Token (NFT) For Beginners
This is a non-commercial article. Not financial or legal advice. Information isn't always accurate. Before making important financial decisions, consult a pro or do your own research.
This post is a summary. Read the full article here
Katrine Tjoelsen
2 years ago
8 Communication Hacks I Use as a Young Employee
Learn these subtle cues to gain influence.
Hate being ignored?
As a 24-year-old, I struggled at work. Attention-getting tips How to avoid being judged by my size, gender, and lack of wrinkles or gray hair?
I've learned seniority hacks. Influence. Within two years as a product manager, I led a team. I'm a Stanford MBA student.
These communication hacks can make you look senior and influential.
1. Slowly speak
We speak quickly because we're afraid of being interrupted.
When I doubt my ideas, I speak quickly. How can we slow down? Jamie Chapman says speaking slowly saps our energy.
Chapman suggests emphasizing certain words and pausing.
2. Interrupted? Stop the stopper
Someone interrupt your speech?
Don't wait. "May I finish?" No pause needed. Stop interrupting. I first tried this in Leadership Laboratory at Stanford. How quickly I gained influence amazed me.
Next time, try “May I finish?” If that’s not enough, try these other tips from Wendy R.S. O’Connor.
3. Context
Others don't always see what's obvious to you.
Through explanation, you help others see the big picture. If a senior knows it, you help them see where your work fits.
4. Don't ask questions in statements
“Your statement lost its effect when you ended it on a high pitch,” a group member told me. Upspeak, it’s called. I do it when I feel uncertain.
Upspeak loses influence and credibility. Unneeded. When unsure, we can say "I think." We can even ask a proper question.
Someone else's boasting is no reason to be dismissive. As leaders and colleagues, we should listen to our colleagues even if they use this speech pattern.
Give your words impact.
5. Signpost structure
Signposts improve clarity by providing structure and transitions.
Communication coach Alexander Lyon explains how to use "first," "second," and "third" He explains classic and summary transitions to help the listener switch topics.
Signs clarify. Clarity matters.
6. Eliminate email fluff
“Fine. When will the report be ready? — Jeff.”
Notice how senior leaders write short, direct emails? I often use formalities like "dear," "hope you're well," and "kind regards"
Formality is (usually) unnecessary.
7. Replace exclamation marks with periods
See how junior an exclamation-filled email looks:
Hi, all!
Hope you’re as excited as I am for tomorrow! We’re celebrating our accomplishments with cake! Join us tomorrow at 2 pm!
See you soon!
Why the exclamation points? Why not just one?
Hi, all.
Hope you’re as excited as I am for tomorrow. We’re celebrating our accomplishments with cake. Join us tomorrow at 2 pm!
See you soon.
8. Take space
"Playing high" means having an open, relaxed body, says Stanford professor and author Deborah Gruenfield.
Crossed legs or looking small? Relax. Get bigger.
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.