Next Photowalk this Sunday

 Seeing from Both Sides Now

Sunday 3rd December 2023

1:00-2:30pm

Meet at Madeline's Cafe, Jells Park

“Albert Einstein put it best: “The intuitive mind is a sacred gift, and the rational mind is a faithful servant. We have created a society that honours the servant and has forgotten the gift.”  

Betty Edwards, Drawing on the Right Side of the Brain. This Photowalk will introduce the ideas of Betty Edwards, on right and left brain thinking, and how they can be applied to significantly improve how you “see” what you are photographing. We will use our cameras and our perceptions to consider the questions “Who am I?” and “What do I want?”

$7.50 - $10 Bookings Essential  Register via MAPh events page

Simplifying My Backup Strategy:

It's been a while since I posted here. Today I wanted to share some changes I've made to my backup and archiving strategies. Back in my consulting days, I relied on a NAS storage system, specifically a Netgear Stora. It had some fantastic automatic backup features, making it easy to keep duplicates of anything sent to it. It also allowed me to sync folders from each computer, ensuring only recent files were sent to the NAS. It was simple and reliable.

Fast forward to today, and retirement has brought about a shift in my storage needs. I no longer need to hold on to large amounts of client data. Also thanks to the relentless upgrades in Windows that unfortunately led to the demise of my previous backup Stora software, I can no longer use that NAS.

Rather than buy a New NAS system, I realised the bulk of my long-term storage is dedicated to my photography and art projects, totalling around 6 gigabytes. After spending a month decluttering duplicates and obvious duds, I repurposed older USB external drives no longer needed for client data for my photo archive. In addition to the current “originals on spinning discs connected to my main computer, and available across my LAN, I've organized them into three sets: one as a master archive in my office, and two duplicate sets rotated, with one stored off-site for added security. The rotation has been roughly monthly

Without a functioning NAS, I've reverted to a more manual approach, reminiscent of the magnetic tape days. I've set up a small, manually triggered incremental backup stream onto my locally held external archive sets.

Here's the breakdown of my new system:

1. I've allocated five folders with appropriate week names.
2. I manually perform the incremental backup at the end of each week.
3. At the end of the first week, I store all files that have changed since the beginning of the month in the respective weekly folder.
4. At the end of the second week, I copy all files changed since the beginning of the month, extending my increments back to the start of the month. I don't worry about overlapping days between months; those files go into the appropriate week's data set.
5. In months with only four weeks, I also copy the entire increment into week five, ensuring it contains the full month of new and changed files.
6. At the beginning of the next month, I clear out the first four weekly folders but keep week five, which now holds the backup of the previous month.

This system gives me a two-month window to recover files. While it might not be perfect, it's easy to manage and ensures the job gets done. Although I'm not backed up to the minute, the simplicity and ease of execution make it a viable solution for my needs. Plus, for anything super important, I can always make an additional copy to the current increment folder. Easy and quick!

I used ChatGPT to help proofread my typos etc, and simplify the text, most of which it did well BUT it clearly didn't understand my process and made up some stuff, so I've used the good bits, and corrected or deleted the rubbish

Descript : making a quick video?

I've recently had a corneal graft, my second. The original graft was over 25 years ago and it was failing relatively quickly. Thus the need for a replacement graft. As a reference, I had painted the same brush a few times over the past year. I'm still in the recuperation phase and have to take it easy which includes limiting time on the computer.

In the ever-evolving landscape of video editing software, Descript has emerged as a promising contender, luring creators with its innovative approach to simplifying the editing process. I decided to dive in and see whether it truly lived up to the hype. Perhaps it could save me precious computer and therefore eye strain time.

The standout feature that initially caught my attention was Descript's automatic transcription capability. This unique functionality allows you to transcribe your videos into text, essentially transforming them into editable documents. The allure of being able to edit videos as effortlessly as word processing documents was undeniable. Moreover, the software offered a free trial, giving me the perfect opportunity to explore its offerings.

One of the immediate benefits I experienced was the ability to effortlessly eliminate verbal hiccups like "umms" and awkward pauses. Descript's features allowed me to easily identify and remove these moments, making the editing process not only smoother but also enjoyable. This aspect of the software lived up to its promise of quick and intuitive editing.

However, as with any tool, there were challenges that arose as I delved deeper into my video editing journey. My primary struggle revolved around incorporating scanned paintings and overlaying them onto the video. Descript introduced a concept called "scenes" for this purpose, which was a unique approach not commonly found in other video editing platforms. While the idea was intriguing, I found that achieving the level of control I desired over these scenes required a more intricate understanding of the software's mechanics.

When it came to incorporating additional graphics, titles, and other visual elements, my progress was stalled. I struggled to find the small icons for tools, which  I had not used before and on a screen layout that was not familiar. The process turned into a frustrating challenge, demanding better eyesight and a steeper learning curve than I had anticipated.

Despite my minor struggles, it got the video above produces in a couple of hours. I can't dismiss the potential that Descript holds. The software's approach to script-based editing is undeniably a game-changer, particularly for creators seeking a quicker and more fluid way to edit their videos. As for the complexities of adding intricate graphics and titles, I've come to realize that these challenges may be conquered with time and dedicated learning.

PS Another admission, I use ChatGPT to summaries my original three short typo filled paragraphs into a blog post, and it gave me 10 paragraphs! I've cut out a lot and removed some over-hyped claims, but it reads well so there you have it an AI chat bot commenting on an AI based transcription tool

Taming the Cable Chaos: A Creative Solution

If you're anything like me, you've probably experienced the frustration of dealing with a growing mess of cables and chargers around your computers. It's a common struggle in our increasingly connected world, with USB cables and their various iterations being the primary culprits. The sight of tangled wires behind the desk and in drawers is enough to induce a headache. The real challenge arises when you need to reconnect a long-forgotten device or simply ensure that a cable is still functional.

The first step was to prepare these clips for their new purpose. I decided to paint them with fluorescent acrylic paint, opting for different colours based on their designated usage or storage location. My simple colour-coding system instantly gave each cable its own identity.

With the multitude of places where computers are stationed and cables are used, I knew I needed a solution to keep things organized. That's when the idea struck me – why not tag each cable for its specific purpose/place? And so began my journey to conquer the cable chaos.

In the quest for an innovative yet accessible solution, I found an unlikely hero – the plastic clips that come with bread bags and many other grocery items. Instead of letting them go to waste, I started collecting these clips. They had the perfect shape for attaching to cables and were ripe for customization.

USB cables and power cords received their own distinct tags. Even the smaller chargers that always seemed to vanish into the abyss of drawers were not spared. I extended this tagging system to cables I frequently used during travel or those required for specific tasks. This sometimes led to a cable sporting multiple tags, each representing a different context in which it played a role.

No longer did I have to play the guessing game when searching for a particular cable or charger. The colour-coded tags eliminated the frustration of untangling a web of wires. Reconnecting devices I hadn't used in a while became a breeze, and the reassurance of a cable's functionality was just a glance away.

In the end, what started as a simple quest to tackle cable clutter turned into a creative endeavor. Those humble bread bag clips, transformed by a coat of paint, became the guardians of order in my tech realm. So, if you find yourself in a similar cable conundrum, consider giving this colourful solution a try. You might just find yourself appreciating the organized aesthetics as much as the functional benefits.

The hyper-real, as a replacement for our photographs?

 

I was out scouting for my last photowalk, on a bright winters day with virtually no breeze. The Jells Park lake was forming a beautiful mirror with strong reflections. I am also testing out the new Skylum Neo extension for creating a multi-image stitched panorama, its nice and much faster than the stitching routine I'm currently using in ON1 Photo RAW.

Things are changing fast in generative AIart all the time and I was also testing out the latest version of Stable Diffusion (model SDXL 1.0) on Nightcafe studio and thought a sunny winter's scene like the above would make a good test. I used the text prompt -

"bright winter blue sky, some clouds over a still lake with strong reflection, yellow ochre grasses in foreground, Professional photography, natural lighting, shot on micro four third digital camera sharp focus"

With the above photo being given the defaults of a 50% Prompt Weight and 50% Noise Weight as the starting diffusion image for the generative process.

Certainly the capabilities of these generative AI systems has become really great, the detail is definitely starp and the reflections undoubted strong. However is it just a bit disturbingly too much on the hyper-real side?

"Hyper-real: More real than reality..." Brookes Jensen, Lenswork PodcastLW1362 - The End of the Trail, Sort Of

Is it me or AI that’s improving" ?

 Painting Granitic Rocks

This week's Wednesday Wanderers was painting a vista on the East Coast of Tasmania, a little channel of granitic rocks against some silhouetted trees reflected in the water. I was trying out a different Art Spectrum watercolour paper, 300gsm but 20% cotton and heavily textured. Didn’t really like it at first, unfortunately it’s also very absorbent so I ran out of time to wait for it to dry during the session. I returned to it yesterday, adding a little bit of detail, some deep tone and colour. It turned out OK (see below).

As has been my way of late I have also checked out what AI might make of my style. I did a “sty;e transfer” on night café studio, which trains on my artwork (above) and applies that to the originl photo. The results were pretty good (see below). Still a couple of tiny “distractions”. So the question is “Have I improved or has AI?” Perhaps its both, especially in the rendering of the granite boulders.

Pushing my luck I decided to also do some generative Ai testing using the prompt- "bright blue sky granite rocks silhouetted trees with strong reflections watercolor" 

So the score (according to me).

Me  1/1           my Style Transfer   0.95/1         Generative AI   0.2/3

How would you score the images?

Make your own Colour Wheel Dot Card

This is something every water-colourist should do. Make yourself a dot card of your favourite colours, Better still make it a colour wheel, then slip it into an old DVD case, add a small sketchbook, a pencil or pen, a water brush and your have a very compact and portable plein-air kit.

Next Photowalk is on Sunday

 

Taking advantage of winter light 30 July 2023 Sunday 1:00pm – 2:30pm Meet at Madeline's Cafe, Jells Park "Bad weather makes for good photography." Ansel Adams Winter is a good time for photographers to take advantage of the lower sun and softer, angled light. Melbourne's weather is notorious for its changeability: mid-winter can be bright – with strong, long shadows that add extra depth to your photographs – or dark and brooding. Even "bad" weather can create drama. It's a great time to change your viewpoint to capture more moody or abstract images. Rug-up for this photowalk session and be prepared to explore the changeable light as a way to gain a different view of the world. Further details and registration on MAPh

Collaging myself onto a famous painting and then Hand Colouring

An example I made for yesterday's "Hand colouring photographs" workshop at the Museum Of     Australian Photography, this collage is based on Charles Conder's famous impressionist painting of the Mentone Baths. I grew up near them.

Both Conder's painting and my photo were printed on a laser printer. My photo was cut out and stuck down with diluted PVC glue. I also gave the collage a little wash of Gesso (50% diluted) to give the very absorbent paper a light sizing to better hold water colour. I then use my watercolour to build up a few coloured washes over the collage.

Link to a pdf of the step by step

Tomorrow :: A different kind of photowalk

 It's Tomorrow, so don't delay registering

Have some fun experimenting with different ways to handcolour old or new photos. While you are at MAPh have a look at ZAHALKAWORLD, particularly her hand coloured collages and recoloured old photos as inspiration.

What's in my Camera Bag Now?

It’s been a while since  I posted what’s in my “travel” camera bag. It's got a lot smaller. Back in the day before I retired and was travelling internationally too much My camera gear took up most of my backpack as well an extra camera bag or two. There was quite a lot to carry around and I still often forgot extra batteries or specific cables or card readers. Things changed a lot and I probably have purchased too many different camera bags (and more than one backpack). Such is life.

A Think Thank Mirrorless Mover bag and my little mirrorless OMD10 opened my eyes to the lighter and happier world of smaller kit. 

Over time yet a smaller lowpro shoulder bag and another Olympus has joined my gear. Now everything is in one bag, available at any time, its easy to pick up the bag and I’m off. It currently houses two small Olympus bodies, new OMD5 & original OMD10, 4 lenses, extra batteries, memory cards and other paraphernalia. I have everything I need.  

The small travel tripod (it's very light and fits nicely in my suitcase case and some of the ancillary gear, like a wireless WIFI modem, battery charger and extra USB cables travel in my luggage. When away for extended periods I also pack an external USB harddrive for backup and my old HP Spectre laptop (not shown in the photos). 

The phone, which does sport a decent camera, travellers in my pocket.

Why I like Water Brushes

I've been using water brushes for some time, I particularly loved them in the field with a small portable palette, like my little Cotman sketcher box. Alas, I tend to lose them.

On a recent visit to the art shop, I found that Derivan now makes a set of four refillable brush pens. This set is reasonably priced and comes in different tip sizes and a larger barrel capacity. The brushes are made of nylon hairs, one Chisel tip and the other is pointed rounds of three sizes. They are designed for both water and Derivan’s acrylic inks. I decided to add my watercolour ink, diluted about 50% to one of the middle-sized round tips as a worthwhile addition to my sketching stuff. The idea is it could add the mid-tones while I just sketched with a normal black pen. This combination struck me as ideal for getting that first compositional/tonal sketch down quickly. It worked perfectly.

I chose the cyan ink just because I've been using the cyan gel pen which blends in quite well if you want to paint over the top of it. Also, I didn't have any grey watercolour ink on hand. At some future stage, I'll probably try diluted fountain pen ink but I will avoid Indian Inks it's likely to come up the brush tip.

If you want a laugh, read how ChatGPT rewrote this post for Instagram, less the outrageous bit I removed.

Secure Drawingboard Tripod Mount

It was time to update my flimsy method of connecting my sketch board to a tripod (it was just a ¼” nut glued onto the back of a plywoodboard).

I had been given a wonderful little connector which can be hammered into the board (I now know they are called T-Nuts ¼” or maybe barrel nuts and used extensively in prefabricated furniture manufacture). I decided to add a separate piece/pad to hold the nut securely in place (with gorilla glue this time).

I have a variety of tripods and camera plates to allow connection to tripods and other stands, and they are different sizes. Also, the tripods they serve have different heads allowing different movements. I made this extra pad square with the maximum dimension of connector plates (70cm) so I could mount this either way (with the board either vertically or horizontally aligned). Importantly with the rotate/tilt handle easily accessed from the front, so you don’t need to get up to adjust the drawing/painting surface. I also added a layer of the “bubbly” rubber sheet sold for lining kitchen pot and pan draws to provide a very sound surface for the plate to screw into and hold firm.

The result is versatile and holds firm, from my lightweight portable tripod to a desk mounting position and all other options.

Pastel Plein Air Kit Colour Selection

I’ve rearranged my soft pastel plein air kit (actually just two plastic boxes with a minimal set of useful colours in ”half sticks” that I might find handy for sketching). Making them into a set of the 6 primary colours I use (RGB + CYM), plus a neutral greyish column and a couple of columns of earth colours. Within each colour group, I have something intense along with lighter and darker tonal variations including very soft and harder composition pastels

Let's see how I go. I’m sure to need to change out and swap a few sticks. BUT the new arrangement looks nice.

Asking AI for help writing this post

I had set up this topic to do a little test of AI chatbots from Open AI's (chatGPT) and Google’s (Bard), using the simple prompt “write a short blog post on why an old TV makes a great monitor for an artist's studio”. Well, it was a no contest, ChatGPT took old TV to mean a cathode ray screen and its text was overly enthusiastic and provided very dubious reasons. Bard did provide clearly correct information and a couple of items I’d overlook. Neither appealed for direct use as the "content" in this blog.

So then I tried Generative AI (Text-to-Image) comparing Stable Diffusion versus Dall.E (using nightcafe studio). I altered the prompt a little “Artist viewing a wall-mounted LCD TV to copy a reference photo and paint at easel”. Again pretty unusable perhaps except for the large one shown below. It’s superficially ok has some artistic merit and just might be partly on topic.

Worryingly he appears to be considering painting on the wall-mounted picture, which isn't a TV!
Using his right hand attached to his left arm!!

Maybe I’m getting a bit picky now. I’m a little spooked now that Google might be downgrading access to your blog if it’s using chatGPT. 

It's alright now....

After possibly too much mucking around, I am proud of my new computer set-up and work table in my studio.

Again it is a large screen Tv mounted on the wall that really lifts this work area, integrated the computer technology and adds flexibility.

• Bigger images as reference
• Wider viewing angle, Less affected by ambient light
• You’re not chained to a desk. Better when standing (eg at an easel)
• Affordable, Repurposed rather than new consumption
• Can still be a TV and/or Chromecast.

Some Frustration along the way

The computer system in my studio has developed over time. Computers have come and gone, devices have been added and taken away or died, interfaces changed, and monitors of different sizes swapped in and out. The use of an older Bravia LCD TV wall mounted was a game changer at the time. Allowing me to redesign my work table to suit both sitting-down art-making, and/or standing at my easel (now my favourite way to work). However, this ad hoc approach meant I had a plethora of cables, power, video, audio and lots of tangled USB cables. Some actually go nowhere and are no longer used. It was a mess.

As it was playing up the old Bravia TV had apparently modified the graphic card drivers or reset something deep in the operating system. So on first attempts, I couldn’t get the repurposed TV replacement to work at all. A fair bit of time was wasted not knowing what was wrong, Attaching the computer to other monitors showed that the screen only worked when connected to the older style VGA cable but not to HDMI. Well very inconsistently on HDMI. So I dug out a very old flat-screen monitor I hadn't used for years. This gave me two screens and let me waste a lot of time checking the graphics card setting, updating drivers, swapping cables and also fiddling with the settings on the TV. Eventually, I got it going reliably.

Now to simplify that wiring….

Oh no….

My large screen TV used as a monitor in my studio was a great friend. It worked well as a sit-down position, or moving around with a wireless keyboard, but it was also wonderful for standup work (eg painting at my easel), It had a reasonable built-in sound so I avoided speakers on the table. It did what I wanted without getting in the way.

Unfortunately, it became terminally ill and I have had to pull the studio apart to find an alternative (at a reasonable price) …   Uggh, all those wires.....

What can we now believe?

I like Sean Tucker am moving to the view that the greatest threat from the current crop of large-scale neural networks, which currently indiscriminately scrap the internet for their training data, is that they will destroy the potential credibility of everything on the internet. Particularly the veracity of photographs.

  

Yet, I also agree that at least some people will appreciate the real. "We'll always want to know whether what we are looking at is real or not and justice like with Photoshop and CGI will come up with systems and rules to differentiate where it counts." Fingers crossed.

Next Photowalk :: Seeing the Person

The next photo walk is coming up.  Sunday 7th May, 1:00 to 2:30pm. Meet at Madeline's Cafe, Jells Park.

In this Photowalk session, we will investigate using the landscape as the background for an “environmental portrait” that perhaps gives some insight into the personality, hobbies or lifestyle of the subject. We’ll explore a ‘keep it simple’ strategy to arrange visual elements. In the case of a  portrait in nature, we need a complementary centre of interest so as not to distract but rather to compliment and give context to the subject.

Composition becomes very important as an aid to telling a subject's story. Composition is a massive topic in art and design. So we will just explore some of the rules of composition and share tips and common pitfalls in developing a strong design for your photos. We’ll also have a bit of fun deliberately breaking some of the common rules of composition.

Register via the MAPh events page

Also staying on thing photographic,  MAPh – Museum of Australian Photography (formerly mga) is holding their 100 faces exhibition until 29^th May. It’s a great opportunity to study a range of portraiture.

New port for the Spirit of Tasmania

 

Co-incidence or Urban Myth?

"Google recognizes posts created from ChatGPT and downgrades them in search"

I've seen similar comments on several Instagram reels (I'd never followed them by the way they were pushed at me), google news, youtube and a couple of blog posts. Sounds like a bit of viral hype/myth to me but thought I would check my blog stats.

Well isn't that a coincidence?

I still doubt that things are moving that fast, and are so competitive. Maybe they are. There does seem to be a race to claim technical dominance of the ChatAI and AIart fields. Also I'm not sure I yet trust OpenAI to be driving the developments, there are the issues of secrecy, open letters by many important people and experts to have a pause in building of bigger models and not forgetting the whole issue of the ethics of scraping the uncensored net for data. Finally, it is logical that having the training of these deep networks based on these unverified sources include all the bias and unfettered untruths that are increasing within the unrestricted websites and social media, with many of those publishing "content" hiding behind anonymity, What should we expect?

Personally, I'm not thrilled that Google might be one potentially trying to dominate yet another field/service that so many people are flocking towards. Google has an extensive history of introducing new things and then killing them, They prefer to call it deprecation.

Anyway I'm suspicious it might be true and I rather let those interested find my thoughts rather than have to get through an unnecessary layer of possible google "censorship". So no more blog posts written (or even reviewed) by ChatGPT. I'll still be investigating how artists and photographers might use and be affected by this technology. 

So, if you are interested in my opinion please stick around.

MD5 Reminder

In our digital age, it has become increasingly important to protect our personal data and information from accidental loss, malicious individuals and cyber threats. Photos can hold a lot of sentimental value and unsuspected personal information. A simple way to ensure the integrity of our photos is by creating an MD5 hash code.

An MD5 hash code is a one-way encryption that produces a fixed-length string of characters that is unique to the photo, and supposedly a unique identifier. By checking an MD5 hash code for your photos, you can verify that the photo has not been tampered with or altered in any way.

My heart sank recently when I realised I had a significant difference in the archived directories and files saved during 2010. I have been using a couple of repurposed old harddisk, standing in for one set of my photo archives, and alas they are showing signs of aging, and probably slow failure. Maybe I’ve been backing up a corrupted or damaged digital photo set. I hadn’t even gone looking for photo there for a while.

Yet it wasn’t time to panic, I had actually gone back and generated an MD5 hash code list for each directory of files (one list per monthly directory) back in 2017. Despite having three versions of the archives (one possibly suspect) and significant differences in files, these MD5 directory lists were largely the same and when checked identified the missing files. Fortunately, there was always one version of these missing files, sometimes in a different directory,  and on checking they were photos I didn’t want to keep (out of focus, almost duplicate shots, overexposed etc.). There were just three photos in the end that may have gone astray. Trying to do this by visually browsing the pictorial version of the photos amongst such a large group of files would have been very difficult, if not almost impossible. So phew…

I didn’t find any corrupted files looking through the photos or the MD5 Checks but I am confident the hash code will identify such damaged files, but avoid overwriting older undamaged versions and unknowingly backing them up. I can breathe easy now...

PS Another advantage of creating an MD5 hash codes for photos is that it provides a way to detect if the photo has been tampered with or modified. For example a hacker might encrypt the photo in order to send you a ransome, the MD5 hash code will change, indicating that the photo has been altered. To beat the hacker you should already have a viable backup, but you will be able to avoid unknowingly backup his altered file(s) and could ignore his ransome request. 

The “A Picture is worth a 1000 Words” Project

This might be a bit long but it documents an interesting self-referencing project I envisioned to have Deep Learning AI create and reuse something in a self-referencing strange loop. I consider this a personal Art Project BUT it was interesting, and may I suggest worth reading. 

Does AI really know what it is doing?

 1. First up I gave chatGPT the following task.

It actually only wrote 499 words but they do seem intelligent and coherent enough (in a roundabout way). They are reproduced unedited below.

2. I took this text and duplicated it and literally added “two words.” then reproduced it on a single A4 sheet (I had to make it a landscape orientation and make the font tiny)

3.  I photographed it (to make it an image).

4. Then I submitted the same 1000-word quote as a prompt and a photograph of the text to Stable Diffusion as a reference/starter image. Not sure what it is trying to portray (if anything). Yet I can see how it is related to my 1000 word project.

The text from ChatGPT …..

The phrase "a picture is worth a thousand words" is a timeless adage that has been passed down through generations. It speaks to the idea that visual imagery can convey a wealth of meaning and emotion in a way that words cannot always capture. This quote has become so ubiquitous that it is often used in everyday conversation, advertising, and even in academic circles. However, the idea behind it is much deeper and more complex than the simple phrase suggests.

To truly understand the significance of this quote, we must first explore the relationship between words and images. Words are powerful tools for communication, but they have their limitations. They rely on the reader's ability to interpret them correctly, and they can be subject to different interpretations depending on the reader's perspective. Images, on the other hand, are more universally understood. They can communicate ideas and emotions in a way that is less dependent on interpretation and more dependent on the visual experience.

One of the main advantages of visual imagery is that it can capture complex emotions and ideas that are difficult to express in words. For example, an image of a sunset over a calm ocean can evoke a sense of peace and tranquility that is hard to capture in words. Similarly, an image of a child's face can convey a range of emotions from joy to sadness, without the need for a single word. These emotions and ideas can be conveyed in an instant through an image, while it would take much longer to express them through words.

Another advantage of visual imagery is that it can convey information quickly and efficiently. This is particularly true in the age of social media and the internet, where people are bombarded with information every day. A well-crafted image can capture a person's attention and convey a message much more effectively than a block of text. This is why social media platforms like Instagram and Pinterest have become so popular, as they allow people to share images and visual content in a way that is easily digestible and engaging.

Despite these advantages, it is important to remember that images and words are not mutually exclusive. In fact, they often work together to convey meaning and emotion. For example, a news article may use words to describe an event, but it is often accompanied by an image that helps to bring the story to life. Similarly, a marketing campaign may rely on both words and images to convey its message and connect with its audience.

In conclusion, the phrase "a picture is worth a thousand words" captures the idea that visual imagery can convey a wealth of meaning and emotion in a way that words cannot always capture. While words are powerful tools for communication, images have their advantages, particularly in their ability to capture complex emotions and ideas quickly and efficiently. Ultimately, it is the combination of words and images that can create a truly powerful and engaging message.

…..Actually only 499 words

I also submitted the prompt to Dall.E (although I couldn’t submit a reference/starter image). These don’t make a lot of sense to me. Although they are photorealistic?

And also a couple of other systems, similar to MidJourney, again not making a lot of sense.

But my favourite is still Style Transfer. I can see a little creative self-reference here, I’m just not sure it was created intentionally

All images, other than those created in Dall.E 4, where created at @nightcafe studio

PS: If you want to consider "worth" to be represented by bandwidth or file space required. Then an image will cost at least between 5 and 10 times that of the equivalent raw text, or even 100 to 300 times if you need something of higher resolution. SO a picture costs a lot more than 1000 words to move around the internet.