Fast. Easy. Beautiful.
Viewing entries in
Images
This image will go in the history books anytime the election of 2024 will be discussed. Image credit: Evan Vucci , image analysis: David Altizer
The trick here is cropping. A good photographer will have a good first start when snapping the image, but adjusting things slightly afterwards can add a lot.
Stock images can be cheesy and cliche, and the current AI image generators are trained on tons of stock images. So if you ask for an image using a stock-image-like prompt, you will get a stock image…
Stock images can happen to the best of us, above, SlideMagic had a go at “a happy group of young adults taking selfies”.
See below a screenshot of a news article discussing a pipeline review of a pharmaceutical company. Some drugs will be cut and the editor added an image of a worker chopping a tree.
Not sure about this. For this type of publication and news, another cliche image of the main entrance of the corporate building with a big logo might have been more appropriate.
Professional photographs of your team can give a great lift to your presentation or web site. Either individual headshots all in a consistent style, or even better, a group photo of your entire team in one place.
A good photographer will do two things: firstly, make sure that the technicalities such as focus and lighting are perfect, and secondly, try and create interesting crops and compositions.
Having a photographer set your image crop in stone might not always be good though. What looks great in a 4:3 view finder of a camera, can look suboptimal on web sites that need to handle unusual screen sizes, all the way from big widescreen TVs to small smartphones.
The problem usually is that the center composition will stay constant (the subject area of your team that will probably occupy a 4:3 rectangle or square in the middle of your image), but the background can have vastly different aspect ratios.
The solution: have your photographer take a snap which the crop she prefers, but always add a second one completely zoomed out as a backup.
If you forgot to make that second image, you might have to revert to AI tools such as Adobe Firefly to add the missing pieces of background back in.
Firefly is Adobe’s stab at generative AI. I had a quick look at it an and am pretty impressed.
Most current AI image generators make either very cute artificial / fantasy / cartoon style photos, or allow you to create crazy / unreal compositions. For example: creating compositions you would not normally see (an elephant riding a bike), or mixing styles (the US president soloing on a guitar in the style of Van Gogh).
Adobe Firefly is more useful. You can extend backgrounds on existing images, or position objects in pictures. Below are some of my efforts to add a purple cow to an Alpine background.
Here is a basic background. You can now add an object in it. This is the first result after prompting “purple cow”
The placing of the cow is very good, the purple cow itself is totally unrealistic, probably because “purple cow” in itself is not a concept that is very common. You can select alternative versions of the cow that are more realistic (and less purple):
It’s pretty good (although not perfect). Here is the layer that the app generated on top of the background image (I disabled the background layer)
The best feature of the app might actually be the extension of backgrounds. See the example below, the area to the right was added automatically.
Firefly is part of a beta version of Photoshop (it will soon appear in other Adobe apps as well), and as a result requires a bit of Photoshop skill to use it (which will be a drawback from many). You can also access its features via the web interface. Results are pretty good (you can see that Adobe is very good at separating the foreground and background of the image), but the style is still slightly cartoonish.
Why is the quality of Firefly better than other image generators such as DALL-E or Midjourney? Adobe trained its model purely on high quality stock images rather than relatively random internet content.
You can see where this all is going. The quality of images will increase as people get better in feeding quality data in models. Not only stock images, but maybe you can actually analyse entire movies that give you the context of a visual, plus the same image with objects positioned differently. And that I think is the second area for improvement, describing a required composition (background, position of objects, lighting, camera view, etc.).
Check out Adobe Firefly here, including instructions for installation on your computer and/or access the web interface
I added 2 additional AI generators to SlideMagic, the produce a slide with some text and an image based on your prompt. One generator pulls the image from Unsplash, the other creates it from scratch. There is no update to your SlideMagic app needed to see the extra image generators.
See an example below:
I swapped the DALL-E image generation engine for a different one, and the quality of the AI-generated images in SlideMagic has improved dramatically. Prompt and responses behave similarly to Midjourney. Below an example of a few quick prompts. (I on purpose forced the 1950s vibe on the last 2 images)
Make sure to have version 3.1.5 installed to see the new image engine. There is a cost associated with generating these images, hence this feature is only available to SlideMagic Pro subscribers. Other AI-related functions (slide and story line generation) are free for all users.
A few months ago, I added a DALL-E AI-image generator to SlideMagic. AI-generated images can be great for presentations:
You can get very precise in defining what you want to see, much more so than browsing endless stock images search results that are not exactly right
You can make images look visually consistent across a presentation
The DALL-E engine is not accurate enough though. Especially when it comes to humans/faces. Midjourney is doing a far better job at this but is not (yet) providing 3rd party API access to its engine, the only way to get images out is via a web-based interface.
I am starting to look into deploying the same open source models that are actually the basis of Midjourney, directly into SlideMagic. You can see the results below and they look very promising. More to come.
Image found with an automated prompt to a stock image site
Open-source AI-generated image
Very poor result from DALL-E
A good presentation has images that are consistent in style throughout the deck. Same color palate, same mood, same type of characters. This was very hard to achieve unless you make drastic design decisions: vintage black and white only, pop art cartoons only, impressionist paintings only (remember Ideatransplant ?), or cheesy stock images only.
AI can bring a solution here. Invest time in developing a standard prompt that generates the desired setting for your photo, then apply that same prompt consistently with small variations to get your snaps.
Databases of image prompts are starting to pop up (see a list here, writing this in May 2023) and this trend might well be the beginning of the end of stock image sites and even model agencies.
The F1 graphics designer has the same problem that we presentation designers face: how to deal with logos that have completely different aspect ratios. Very long ones vanish in a square tile, square and round ones don’t look good in a wide rectangular box.
Their solution: let go of the requirement that the entire logo should be visible. Carefully crop out parts of the logo while making sure that it can still be recognized and read. All this is supported by borrowing the dominant color of the logo in the text box.
Most people use AI image generators to create something funny (a cat riding an elephant) or something artsy (a formula 1 car in the style of Van Gogh). This is not the primary motivation why I included OpenAI image generation in SlideMagic.
Image generators can be useful already in presentations, especially for image concepts that are relatively straightforward, but hard to find on stock image sites. The example that came along yesterday with an image of a ‘sleeping bull’ for a economics-related presentation. Perfect for OpenAI, see the result below.
Getting logos to line up properly is one of the hardest things in slide design. I have not been able to come up with a set of rules to do it, every time I need to eye ball things to see whether things somehow look right. Below is an example from the 9xchange web site:
There are a number of (conflicting) inputs:
The middle of the image file
The typographical baseline of the text
The middle of the non-text part of the logo
Tag lines above or below the brand name
Always fine tune logo pages because any automated adjustment will for sure not get it right.
In most cases, it is not worth the time and effort in a short presentation to take the audience through a demo or a series of screenshots of your application. At this stage in the pitch process, understanding the exact flow of your application is not critical.
What can matter though is the simple question of whether you have a decent product or prototype or not. The role of a screen shot here is not to show the exact detail of your app, but more a proof point.
One way to make this point is to use an office background with some screens, and paste a number of screens on the monitors. That’s what I did in a recent deck for my other venture 9xchange. I made the office background black and white, to make the screens pop a bit more.
(Look how I managed to Photoshop the screen shot behind the standing desk light)
When using images from Google Maps, pay attention to the direction of the sun light and shadows the moment the picture was taken. Only 1 of the four possible orientations is the right one, and this is by no way the default north up. Example below. These are 2 pictures of the same are, and you can clearly see that one just does not feel right.
When looking for images, pay attention to how they can lead the eye of the audience. Below are 2 examples of images that draw the eye to a certain spot. (RSS email readers might have to open the link to the blog post to see the images).
I have added the images to the SlideMagic slide library so you can use them in your own presentations. (Search for example for “direction” and they will show up, see the example image below).
Pro users can convert these slides to PowerPoint or PDF
It happens to the best of us. Using a cliche chart. In a recent presentation, I had to refer to the so called “patent cliff”, a number of very big selling drugs will come off patent and become vulnerable to low cost generic alternatives. Everyone in the audience knows what it is.
I put an empty image (see below) of a cliff without any data or text, and literally apologized for the cliche visual. A 1 second reminder and * click * I could continue with the story
I have added this image to the SlideMagic slide library, search for “cliff” in the SlideMagic app and you can use this slide in your own presentation.
A well-chosen image creates a “visual shortcut”. While you explain your idea, the visual of the image gets stored in your brain alongside your story. Seeing the image again, immediately makes the whole idea pop up again, including its more complex nuances.
You can use this in presentations. Obviously on one slide. But it can also be very effective to use similar (or the same) image to make a connection between multiple slides. You introduce a concept early on (let’s say a problem) and when you get back at it later (with the solution), a related image can quickly pull back up the original story.
As an example, two slides I used in a recent presentation. The first image introduces the concept of FOMO (fear of missing out), in this case of a business that becomes wildly successful after you spun it out. The second image relates back to the slot machine / lottery concept.
If you are reading this blog post via an email update, you might have to open the link to the blog post to see the images. My email service can only take a limited amount of images from the blog feed (I am working to fix this).
I have added these slides to the SlideMagic template library, for example search for “gamble” in the SlideMagic app and the slides will pop up for you to use in your own presentation. Pro users can covert the slides to PDF and/or PowerPoint.
All the images and icons that are available in SlideMagic are royalty free, without copy right. For some memes that I have been adding recently, there are copyright issues. To solve it, I added a giant water mark over the image so you can replace it with your own. This placeholder is useful thought to get the positioning of boxes right.
You can download the slide template for the distracted boyfriend meme online, but it is even simpler to search for “distracted” and get a number of layout suggestions directly in the app.
SlideMagic Pro users (free for students) can convert slides in the SlideMagic app to PowerPoint.
Dream Studio uses machine learning to create images based on sentences and keywords a user enters. Unlike searching for an image based on a keyword in a big data base with tagged pictures, Dream Studio would generate pixels from scratch. Some results are stunning, others have surprising errors (faces that are not finished for example).
You can also mix and match art styles (the image below is a mix up of Mondriaan and Van Gogh).
At the moment these type of services are a gimmick. People try a few creations, share them, and move on. But in a few years from now, this might be the way image “databases” work. No need for that database anymore as photographs are created on the fly,
(Another similar service is DALL-E, but it has a waiting list)
When you right click an image in Google Chrome, you now get an extra option to search the image with Google Lens, which generates similar images, find places where the same image is used (often including the original source), translations etc.
