For each pair of images below, the left or first image (depending on your screen size and email program) is Nano Banana 2, and the right or second image is from GPT Image 2 (the newest model in ChatGPT). In general, I prefer the Nano Banana 2 images; they feel a bit less staged and less like stock photos to me.

If you’re viewing this on my site and not via email, you can click each image to expand it.

Wheelchairs

Wheelchairs have been a problem for AI-generated images in the past, partly because so many stock images show able-bodied actors using temporary wheelchairs incorrectly. I was overall pleased with the results for both a “sporty wheelchair” and an “electric wheelchair.” There are still some flaws though—check the spokes on the wheels and the foot rests.

Style: Editorial photo
Subject: A Puerto Rican man, mid 20s, in a sporty wheelchair
Action: Working at a computer
Setting; A modern open office in a large city, high rises visible through the windows, other employees in casual clothes working nearby
Light: Natural light from large windows

Style: Editorial photo
Person 1: A Black woman, mid 40s, average weight, in an electric wheelchair. Wearing A pink t-shirt and jeans
Person 2: A Korean woman, mid 40s, wearing a long gray t-shirt and black leggings
Pose: Talking to each other, gesturing with their hands, friendly conversation
Setting: A trail in a suburban park with a playground in the background
Light: dappled afternoon light, partial shade from trees

Forearm crutch

Forearm crutches are one of the objects I’ve never been able to generate accurately in Midjourney. Even a year ago, ChatGPT struggled to show them accurately while also fulfilling the rest of the prompt. It’s much closer now. We often default to wheelchairs to represent disabilities in images, but mobility aids like leg braces and forearm crutches should be shown too.

Style: Editorial photo
Subject: Native American man, mid 50s, graying hair in a long braid
Clothes: A red button down shirt and gray slacks
Details: Using a forearm crutch
Action: Presenting at a small team meeting, explaining and gesturing with one hand
Setting: A small modern office conference room, a projector screen with a column chart behind him
Light: overhead florescent lights

Hearing aids

When I wanted an illustration of a woman wearing a hearing aid in January 2025 for a blog post, it took me over a dozen variations and edits to get it right. I’ve also had issues in the past where the AI models insisted that anyone wearing a hearing aid must be older and have gray hair, no matter what age I prompted for. This time, I got two plausible behind-the-ear hearing aids on my first attempt.

Style: Editorial photo
Subject: White woman, mid 20s, hair pulled back into a messy bun
Clothes: A dark blue business casual blouse
Details: Wearing a behind-the-ear hearing aid 
Pose: Typing, working at a computer with two monitors
Setting: An office cubicle with gray walls
Shot: Medium shot, head and shoulders

Cochlear implants

I think the cochlear implants here aren’t quite accurate; I don’t think they’d meet the approval of someone really familiar with these devices, especially at higher resolution. But this is closer than I’ve been able to get in the past. Because the implant is black in the Nano Banana image, it’s hard to detect.

Style: Editorial photo
Subject: Indian woman, mid 30s, braided hair
Clothes: A red tunic
Details: Wearing a cochlear implant
Pose: Sitting behind a desk, working on paperwork, focused expression
Setting: A private office in a bank, dark wood desk
Shot: Close shot, focus on the side of the head

Prosthetic leg

I set up my prompt for this image to put the subject in shorts so the prosthetic leg is visible without any weird artifacts like hiking up someone’s pant leg to show the prosthesis. I was also curious how the models would handle the setting of the YMCA; both models included the logo.

Style: Editorial photo
Subject: White man, mid 40s with a prosthetic leg
Clothes: A black athletic shirt and gray athletic shorts
Pose: Playing basketball, passing the ball to a friend
Setting: A gymnasium in the YMCA
Lighting: Overhead lights
Shot: Wide shot

Upcoming webinar on inclusive images

Disability representation is one of the topics I’m going to address in my upcoming Training Mag Network webinar, “Better Prompts, Better Representation: Inclusive AI Images for Learning.” This free webinar will focus less on the tools for AI images and more how to explicitly prompt for images that are more inclusive of gender, race, disability, and more. AI image models can reinforce stereotypes if you don’t prompt to counter their natural tendencies. That makes it important to know how to prompt well and what problems to watch out for.

Register for my free webinar on May 20, 2026 at 12 PM PT/3 PM ET.

What are your challenges with disability representation?

What challenges have you found with representing disabilities using AI images? Comment on this post or reply to this email. I’d love to have some more specific examples to test to see if it’s possible to generate with the most current models. What are the inclusive images you wish you had for your training?

The post Disability Representation in AI Images appeared first on Experiencing Elearning.

Principles of Multimedia Learning

Mayer’s Principles of Multimedia Learning – Educational Technology

This article summarizes Mayer’s Principles of Multimedia Learning with a few tips for instructional design aligned with each principle.

Personalization Principle – Using a conversational style in multimedia content makes learning more effective than a formal tone.

• Use a relaxed tone with contractions.
• Speak directly to the audience using “I,” “you,” “we,” and similar words.

—Dr. Serhat Kurt

Style of language Formal Versus Conversational

This guide provides a summary of the personalization principle with a focus on the writing or speaking style. A polite, conversational style is more effective for learning in general (with some exceptions noted). I appreciate the examples in this guide so you can compare the difference between formal and conversational style.

Water use for generative AI

How Much Water Does AI Use? An Expert Analysis of the Real Footprint.

The water use for AI data centers isn’t as big of a problem as it’s often made out to be. Don’t let the exaggerated claims about water use distract you from larger issues (including energy use, which is a real environmental consideration). We can push for improved efficiency and make choices about when and how we use AI to reduce that energy use

For 11 weeks, I tracked all of my AI use. One hundred sessions. I counted the tokens processed and applied publicly available numbers on per-token energy and water intensity from Epoch AI and operator-reported data from Microsoft and Google. Anyone can run this math.

In those 11 weeks, I built an iOS app from scratch and wrote policy briefs on extreme heat for nonprofits I work with. I produced documentary pitch decks and drafted a 15,000-word climate fiction piece about the Colorado River collapse. I used AI every single day, often for hours at a time.

Total lifecycle water footprint of all that work: about five gallons. That accounts for everything: the water used to cool the data centers, the water consumed at power plants to generate the electricity, and the water embedded in manufacturing the hardware.

…

You may have read stories about how data centers use lots of water, and how these massive warehouses of computer servers are being built across the country to help with the expanding use of AI. Here is the part that I think gets lost in the discourse. All U.S. data centers combined—not just AI, all of them—account for roughly 0.3 percent of total national water withdrawals. Agriculture consumes approximately 80 percent of Colorado River water.

AI images and voices

Seven Prompts No AI Image Generator Can Get Right

(If the link above to LinkedIn doesn’t work, try this version instead.)

Really interesting research on the limits of AI image generation. Hands and text are both much better than a year ago, but multi line text (especially with numbers) fails because text isn’t generated sequentially. AI images approximate rather than counting, and all models fail with prime numbers. Reflections are also approximate; there’s no geometry behind them.

Vois – Professional AI Voice Studio

While Vois doesn’t have as many voices as some other platforms, it has several other advantages. It runs locally on your machine, so there’s no risk of content being used to train AI. You can tag your script for multiple speakers, making it easier to manage dialogue. You can also buy just the credits you need rather than paying a monthly or annual fee, and you only use credits when you publish (not for each iteration and typo fix).

Automating repetitive design tasks

7 Ways to Automate Repetitive Design Tasks with Affinity and Claude

I use Affinity as my primary tool for editing images. Affinity now can connect with Claude to automate repetitive tasks like renaming layers and prepping files. It looks like a great way to speed up some boring tasks so you have more time on the fun work. This is currently in beta and free, but will probably become a paid feature later. Still, if it saves time, it may be worth a paid upgrade.

The post Multimedia Learning, GenAI: ID Links 5/12/26 appeared first on Experiencing Elearning.

One of the AI tools I’ve been using more lately is Flora. Instead of a chat interface like many AI tools, Flora gives you a canvas with multiple nodes where you can see and organize multiple results. Flora includes most of the main image generation models, so you can switch between tools easily. For my post comparing how different image models handled the same prompt, I used Flora’s built-in feature to run a single prompt with multiple models at once. In this post, I’ll show how I used Flora’s batch feature to generate character images in multiple poses quickly. After experimenting with this, I think this process can really speed up character image creation for scenarios. You can generate multiple poses of a character with consistent aspect ratios and even transparent backgrounds much faster than if you prompt one at a time in other tools.

This isn’t a sponsored post; I’m sharing my own experiences so you can see what worked for me. I’ll share some of my mistakes and lessons learned as well.

How do you create a character reference image in Flora?

The first step for generating character image sets is always generating a reference image. If your reference image isn’t good,

In this case, I wanted to replicate the visual style from another image I’d previously generated for a presentation. I uploaded that image to Claude and asked it to describe the style so I could use it in an image prompt. Claude gave me much more detail than I wanted, but I picked several of those phrases to include in my prompt.

I used a structured prompt with labels. Nano Banana and ChatGPT work well with this kind of prompt. It’s simpler than JSON prompting, and you get some of the same benefits of repeatability without needing to be so precise in your syntax.

Style: Contemporary digital painting, visible brushstrokes with flat color blocking, realistic body proportions, acrylic painting blended with vector-style cel shading
Subject: A Latino man, mid 40s, black hair, well-trimmed short beard
Clothes: Navy blue button-down shirt, khakis, brown Oxford shoes, black glasses
Pose: Standing, looking at the camera, smiling, relaxed pose
Background: Solid white

Here’s my reference image using Nano Banana 2 after a few attempts. I tried the ChatGPT Image 2.0 model too, but that was much slower.

How do you batch generate poses from a CSV in Flora?

Next, I wrote a list of poses and saved them in a CSV file. I used 8 simple poses for my examples for this post, but Flora can handle up to 100 at once in a batch. Practically speaking, I probably wouldn’t do more than 20 images at a time. If something goes wrong and you need to adjust your prompt or settings, it’s easier to adjust with smaller numbers of images.

• Talking gesturing with hands
• Joyous laughing
• Listening thoughtful arms crossed
• Disappointed slight frown looking down
• Frustrated upset
• Confused head tilted slightly
• Turned to the side talking and gesturing with hands
• Turned to the side listening with arms crossed

I uploaded the CSV with the list above to a Batch node in Flora. Flora separates out each row into a separate prompt.

How do you combine the reference image and batch prompt list?

This is where Flora really speeds up the process of character image generation. Instead of prompting 8 different times, I connect the node with my character reference image to my batch of prompts. With the batch, I can run 8 generations with a single click.

Running the batch of 8 prompts gave me these variations on the original character image. Note that even though it’s a single node on the right, there are actually 8 variations all stacked in the same node. Click each image in the gallery below to view a larger version. (If you’re reading this in email, you may have to view it on my blog instead.)

How do you remove backgrounds from a batch of images?

While I often generate scenario images of characters directly in scenes with context, sometimes it’s easier to work with separate character images with transparent backgrounds and then manually place them against a background image later. Flora makes this easy; removing the background is one of the tool options on image nodes. Since all of my character variations are in a single node, I just have to click remove the background in all 8 images in one step.

How do you scale this image creation process?

I generated another reference image for a character named Maia and used the same batch prompts for the variations. This time I used a 3:4 aspect ratio instead of a 1:1 ratio. I don’t know why Nano Banana matches the aspect ratio just fine in Flora but ignores it in prompts in the regular interface. But I get consistent ratios in Flora.

I also generated a set of images for a character named Ji-hun. These were a little less consistent, but still usable. I’m not sure sure she suddenly has wavy hair when she’s frustrated, and I don’t know why the laughing image wasn’t a full body picture. These are good examples of why you probably don’t want to run too large of a batch at once, and sometimes you’ll have to manually adjust and re-run specific images.

What are mistakes when batch generating character images?

I tried a few things that didn’t quite work out and that I’d do differently next time. Hopefully you can learn from my mistakes!

The standing pose is really similar in all of these results because I didn’t include any specific body changes in my prompt list. I think with a better list of prompts I could get more variety in the results. The facial expressions are good, but the poses don’t vary enough.

I didn’t realize that Ji-hun’s reference image wasn’t on a solid white background; it had a paper texture instead. The flaw in the character reference image meant I got more variety in the backgrounds later. That’s an easy fix if I remove the backgrounds, but it’s a good reminder to be more careful with the reference image.

With Maia’s character image set, I tried putting the reference image on a transparent background. I’d hoped it would generate all of the subsequent images also on a transparent background, but it it just put them on a solid black background instead. Again, an easy fix with removing the backgrounds, but I created some extra work for myself in needing a step to put them all on a white background for this blog post.

Some of these characters have shadows around their feet, but not all of them. That’s easy enough to fix in an image editing program though. I could probably add “no shadows” to the prompts as well.

Reflections

Overall, I think this is a really promising workflow for generating images for scenarios. I often generate a “shot list” for branching scenarios as a table (sometimes using Claude to generate a list based on my Twine export), so I already have a table describing scenes. This would work for generating images in context for scenarios all in a batch like this.

If I wanted to generate multiple sets of characters in standard poses with transparent backgrounds, this would be significantly faster than generating them one-by-one. Even if I just start with a standard set of poses and then prompt individually for a few specific images, this would speed up my process.

While I still like Midjourney for generating blog cover images and my initial reference images, I’m finding myself using Flora more often. It’s a definite shift in process, and I feel like I still need to spend more time to get really efficient at it. But I’m getting better the more I practice and refine my processes and prompts.

More on AI image generation

Learn more about generating character images using other AI tools.

• Generating Consistent Characters in the Midjourney Web Interface
• Using the Midjourney Editor to Change Character Expressions
• Testing Freepik Spaces for Character Image Generation
• Nano Banana (Gemini) Character Image Experiments
• Character Consistency Q&A

The post Speed Up Character Image Creation with Flora appeared first on Experiencing Elearning.

In branching scenarios with simulated conversations, sometimes I see people build every single exchange as an interaction. With that approach, if you’re controlling a character, then every single sentence that comes out of that character’s mouth has to be a decision point. It can get pretty tedious, both for the user and for the ID building it.

Example without a cutscene

Here’s what that might look like with some dialogue excerpted from the middle of a larger scenario.

Decision point 1

Decision point 2

Decision point 3

With a choice for every line of dialogue, that creates 3 decision points, each with 3 choices. That’s 10 screens that have to be built.

Example with a cutscene

Compare the version above to this version using a cutscene. This time, all of the dialogue continues seamlessly. You see some back and forth between the two characters before having a single decision point at the end. Instead of 10 screens, this is only 4 to build (the conversation shown here plus the results of the 3 choices).

See the cutscene in action

You can see the cutscene in action on its own or as part of the complete branching scenario. This full cutscene includes some additional dialogue prior to the script excerpt shown above.

I wrote about the specifics of building a simulated phone conversation previously.

Advantages of cutscenes

Simplify the scenario

The biggest advantage of showing a conversation in a cutscene like this is reducing the total number of slides (from 10 to 4) and decision points (from 3 to 1). That reduces time building the other options, as well as the time writing plausible distractors for the additional decision points.

Reduce cognitive load

Trimming extraneous decision points helps reduce the cognitive load on users. With a cutscene, they can see the conversation and focus their efforts on the decisions that matter. They don’t need to put in cognitive effort on the less important decisions of every line of dialogue.

Meet critical objectives

The cutscene moves the conversation forward quickly to get to the next critical point. In this particular example, the objective is to propose a road mapping. That needs to be a decision point.

The other parts of the conversation aren’t as critical for the learning objective. Therefore, it’s not as important for them to be decision points. I can collapse that dialogue into a single, non-interactive conversation. We need the context, but not everything has to be a decision point.

More tips on streamlining branching scenarios

For more tips for making branching scenarios easier and more manageable, download my guide on Streamlining Branching Scenario Planning and Design. This is a free 25-page PDF guide on how to save time and manage the complexity of branching scenarios while still providing rich, valuable learning experiences.

Originally published 3/3/2020. Updated 4/23/2026.

The post Cutscenes in Branching Scenarios appeared first on Experiencing Elearning.

AI image models compared

These are the specific models I used for testing. Except for Midjourney, I generated all of these within Flora. Flora makes these sorts of comparisons much easier, since you can add the prompt once, select multiple models, and generate them all at the same time.

• Nano Banana 2
• GPT Image 1.5
• Midjourney v7 or v8.1
• Flux 2 Pro
• Recraft v4
• Seedream 5.0 Lite

Prompt 1: A single person

For my first test, I wanted a photorealistic image with a focus on a single person. As I expected, all of the results were pretty good; this is something all the tools can generate now. I like the aesthetic and pose for some results better than others, but none of these were failures.

Editorial photo, an Indian woman, mid 40s, dark hair pulled back in a single long braid, wearing a kurti with a small burgundy geometric pattern, walking in past desks in a modern open office, trees visible through the windows

Prompt 2: Photorealistic objects

For my second test, I used a prompt for two objects: a hard hat and a pair of safety glasses. There were a few issues with these images (the plywood in the Nano Banana image looks too worn, for example), but they weren’t bad. All of the models followed the directions for the focus objects, setting, and camera angle.

Editorial photo, a yellow hard hat and a pair of safety glasses on a stack of plywood sheets on a construction site, low angle

Prompt 3: Illustration

For this prompt, I used the style of “digital illustration” as a starting point. However, Recraft and Flux both failed to generate illustrations initially; they generated photorealistic images instead. I had to change the prompt to “vector illustration” for those image models. With illustrations, you see more variety in the default styles. Obviously, I don’t have a lot of detail in the prompt about the style; that would affect the similarity more.

While it’s not my favorite of this set, I was pleasantly surprised at how well ChatGPT did. The most recent updates to ChatGPT’s image model have made it much more comparable to other tools. It doesn’t always have the yellow filter, and the overall illustration style has greatly improved. His back blends into the back of the bench in this example though, so this would require some editing or iteration to be usable.

Digital illustration, modern corporate style, a Black man typing on his phone, thoughtful expression, wearing a dark blue t-shirt, sitting on a bench in a park, medium shot from the waist up, viewed at a side angle

Prompt 4: Group of people plus text

For my final prompt, I wanted to challenge the models. This time, I prompted for a group of people, plus I asked for text on a whiteboard in the background. The more people you add to an image, the more likely it is that something goes wrong in the generation.

The Recraft image here is the biggest failure out of all of the images for all of the prompts. All of these images have some issues though; this is still where the image models require a lot more iteration and editing to get it right (if it’s possible at all). Most of these images look very obviously AI, especially in the text. Midjourney looks a little better partly because it didn’t actually try to make readable text.

Candid photo of a racially and ethnically diverse team of designers discussing solutions, sitting around a light wooden table in an office conference room, gray walls, whiteboard with brainstorming mind map on one wall

Reflections on the differences

Reflecting on these results, I still find myself drawn to Midjourney. I like the overall look of Midjourney more, and I find that it’s easier to generate a wider range of faces. But Nano Banana is great, and better than Midjourney for consistency (although I may revise that opinion after I test the new Midjourney v8.1 a little more). ChatGPT has improved enough to be genuinely useful now, although it still looks more like stock photography. Flux, Recraft, and Seedream are all useful in some situations too.

If you’re going to pay for a single image tool, I recommend Flora or Freepik. Even though they don’t have access to Midjourney, both Flora and Freepik give you access to multiple image models. You have a lot more flexibility that way.

Your thoughts?

Which examples do you think turned out the best? Which models do you prefer working with? Let me know in the comments.

Further reading

Check out my comparison of AI image generation tools for more information on the strengths and weaknesses of different tools.

The post Same Prompt, Different AI Image Models appeared first on Experiencing Elearning.

How AI is affecting entry-level jobs

The Perils of Using AI to Replace Entry-Level Jobs | Harvard Business Impact Education

One theme I see coming up repeatedly in L&D conversations is that using AI requires expertise to evaluate AI-generated results. That’s fine right now where we have experienced people who built skills pre-AI. But what about entry-level workers now and in the future? If those entry-level jobs are eliminated, how will the next generation learn those skills and judgment? This article has some ideas about restructuring work. This also points to some areas where L&D could help support people whose jobs are redefined and restructured. Training people to question and evaluate AI output and apprenticeships are two possibilities to address the challenges.

Imagine recruiting managers who have never worked at the front lines, never handled customer complaints, never written up notes from consequential meetings, never grappled with the minutiae of operational work. Leadership would become abstract, detached, and dangerously naive.

Junior roles must no longer be defined by the repetitive, automatable tasks that AI can do better and faster. Instead, they should be designed to expose people to the why behind the work.

AI is only useful when paired with critical thinking. Productivity gains are meaningless if they come at the expense of professional judgment.

The default use of AI is substitution: Let the machine do the work and cut headcount. A smarter approach is to redesign workflows, so AI handles rote execution while humans focus on framing the problems, asking better questions, and building relationships.

Consider the analogy of education: If a student outsources every essay to generative AI, they bypass the intellectual struggle that produces deep learning. It is like microwaving ideas: fast, convenient, and unsatisfying. The effort, even the pain, of thinking for yourself is what builds a student’s capacity.

—All quotes above by Amy C. Edmondson and Tomas Chamorro-Premuzic

Is AI closing the door on entry-level job opportunities?

AI will result in both job losses and opportunities, changing the career ladder that used to provide entry-level opportunities and a mostly linear path upward. But eliminating entry-level roles will dramatically affect the long-term talent pipeline.

AI images

Three Steps for L&D Professionals to Legally Use AI Images and Video

Debbie Richards shares tips for using AI image and video legally. Personally, I’d probably add a few other image tools to that list of professional options (like Flora and Freepik), but she’s correct that Firefly is the safest for images based on training on licensed data. Free tools are fine to experiment with, but don’t use them for commercial projects.

Simple Ways to Create Consistent Characters in ChatGPT

Tom Kuhlmann shares his workflow for generating consistent character images using ChatGPT using a GPT or a project with saved instructions. Even if you don’t use ChatGPT for image generation, the descriptions of image styles in the download are useful for working with any tool.

The AI Image Generation System for Learning Designers

Despite the article title of “How to Get Consistent, On-Brand Course Images from Any AI Image Tool,” this system doesn’t actually work with all AI image tools. The process is different with Midjourney, Recraft, Brushless, Flora, etc. But this process will work with any of the LLM-based image tools like Nano Banana, ChatGPT, and Copilot, since those all work in similar ways. That means it covers what most people have access to. The character reference images are key to getting scenes with consistent characters in LLM-based image tools.

The fix is an 3-step process which gives you superpowers in AI image generation:

• Write a visual brief — answer six questions that close the creative and pedagogical gaps before you generate a single image.
• Build a mood board — gather images that capture the lighting, energy, and environment of your learner’s world. Select the 3 that look like they were shot by the same photographer on the same day and upload them individually as style references.
• Create character anchors — your style references fix the visual world; your character references fix the people inside it. For each named character, generate a head-and-shoulders image on a neutral background, facing forward. This is your master reference. Attach it alongside your style references every time you generate a scene featuring that character — and the tool stops making casting decisions on your behalf.

—Dr. Philippa Hardman

AI literacy framework

AI Literacy Framework updated April 2026

Stella Lee has updated her AI Literacy Framework to include 8 interconnected domains covering foundational knowledge, critical practice, and responsible leadership.

Rebuilding simulations with AI

I Rebuilt a 10-Year-Old Simulation with AI in Half a Day. Here’s What I Learned.

Trina Rimmer shares her experiences rebuilding an old Rise scenario activity as a new experience with Claude. You can see the projects side-by-side to compare. Trina’s reflections add a lot of value here; you can see how the AI tools enabled her to do something new, but that was only possible because of her existing instructional design skills. If she didn’t have that expertise, then she couldn’t have gotten as successful a result with AI.

And then there was Claude’s desire to help. It was relentless. I pushed back constantly on anything that broke the “fourth wall,” anything that handed the learner an insight before they’d reached for it themselves, and anything that sounded like a training exercise instead of a real situation. Productive struggle is where learning happens.

AI is a design collaborator, not a design replacement. Every meaningful improvement in the rebuilt project came from my instructional design judgment, not from Claude’s defaults. The dialogue, the model interaction structure—me insisting that learners identify what worked before being told—and the debrief—me pushing back on Claude’s first version until it asked more than it told—that was all me. Claude made those things possible faster, but without the ID judgment driving the prompts, the end result would have been slicker but shallower.

—Trina Rimmer

The post Entry-Level Jobs, AI Images: ID Links 4/14/26 appeared first on Experiencing Elearning.

You’ll learn how to:

• Apply a repeatable prompting framework that works across AI image tools
• Create diverse, representative character images for scenario-based learning
• Keep a consistent visual style across an entire course
• Generate icon sets and visual metaphors in a single prompt
• Navigate copyright, ethics, and commercial use considerations

For the post header image below, I used Midjourney to create the four images in a consistent style and colors. While Nano Banana is better at consistent character images, Midjourney is still my favorite tool for interesting and cohesive illustration styles. This set uses sref 361625325, which means I just needed to add that code to the end of my prompts to get these results fast. You can explore more styles to use on Midjourney’s website.

Watch the recording

If the video isn’t embedded below, you can watch it directly on YouTube.

Handout, practice exercises, and articles

This was a hands-on webinar, and you can follow along with the practice exercises with the recording.

dominKnow published two follow-up articles building on the webinar content.

• Build Cohesive Learning Visuals with AI: From Generic to Purpose-Built
• How to Create AI Images for eLearning: Prompts, Styles, and Consistency

IDIODC podcast

For more about AI images with the folks from dominKnow, watch or listen to my conversation about AI-generated images with Paul Schneider and Chris Van Wingerden on the Instructional Designers in Offices Drinking Coffee (IDIODC) podcast.

Character consistency webinar

If you’re interested in learning more about character images with AI, check out my webinar Character Consistency Solved: AI Image Generation Workflows and my follow-up character Q&A post.

I try not to post webinar recordings back-to-back on my blog, but March was a busy month for speaking for me with five webinars. At least this week’s recording is on a different topic from the branching scenario webinar I shared last week. I’ll be back to my regularly scheduled post schedule soon!

More on AI and instructional design

Check out my growing collection of articles about AI and instructional design, including a number of posts specifically focused on AI image generation.

The post dominKnow Webinar: Build Cohesive Learning Visuals with AI appeared first on Experiencing Elearning.

I gave a quick overview of branching scenarios, their benefits, and when to use them. We looked at some before and after examples of branching scenarios. This included comparing a scenario I built manually pre-GenAI and how the workflow can change with AI. I shared some examples of how my process is changing with AI-generated images for scenarios and using scenarios to assist and augment my writing. We discussed the options for AI video generation and how fast those tools are improving. Mike demonstrated some new capabilities in Near-Life to speed up the process of building scenarios where the AI generates a draft structure for you.

Watch the video

If the video isn’t embedded below, you can watch the recording of my Near-Life webinar on YouTube.

More webinars on scenarios

I’ve given a number of webinars in the past few years through Training Mag Network, TLDC, and other organizations. Check out my collection of webinars on scenarios for tips on working with SMEs, improving engagement, managing the complexity of scenarios, and more.

The post Near-Life Webinar: Leveraging the Power of AI in Branching Scenario Design appeared first on Experiencing Elearning.

I use affiliate links when I share books and some additional resources (like the SiteGround link below). It won’t cost you anything additional, but a small portion of the purchase price comes to me to help pay for hosting my blog. I have partnered with elearningfreak on this post, but all opinions are my own.

Why do you need a portfolio?

If you’re wondering why you need a portfolio, read Tom Kuhlmann’s explanation about being “at the crossroads when opportunity and preparation meet.” Christopher Pappas provides another 7 reasons you need a portfolio, if you need more motivation.

I have heard all the excuses why you can’t build one: everything is confidential, you don’t have the tools, no time to work on it, etc. But if you’re looking for work and trying to get interviews or attract freelance clients, you still need to be able to show that you have the skills you say you do.

What to include

My post on 30+ ideas for portfolio samples can give you some inspiration if you need to create new artifacts.

Watch the recording of my webinar with Danielle Watkins on 5 Portfolio Mistakes Instructional Designers Keep Making (and How to Fix Them).

Kristin Anthony’s “Go Design Something” site automatically generates ideas for portfolio samples.

This post on building an instructional design portfolio includes what to include and additional tips.

These 10 tips for building a portfolio include picking the right projects and pairing each project with a description.

Tools for creating samples

Storyline and Rise

Prospective employers expect to see a few samples using standard tools. Two of the most common tools are Articulate Storyline and Rise.

Rise is part of the Articulate 360 Suite. It’s easy to learn, but be cautious of relying too heavily on their templates and course starters. Plenty of hiring managers will recognize those course starters.

Job seekers often can’t afford to purchase expensive software licenses. If you’re a student, discounts are available for Articulate 360 (which includes Storyline and Rise).

Articulate offers 30-day free trials. If you storyboard and plan before you start your trial, you can make several samples during that month.

Authoring tool options

Although employers are likely to look for Storyline, you can use other tools. In fact, right now I see a lot of interest in other authoring tools. Mike Stein’s comparison of elearning authoring tools is a great place to look for alternatives, many of which are more affordable than Articulate.

iSpring’s tools are solid alternatives, and they’re hosting a course creation contest this spring. If you register by April 24, you’ll get free access to iSpring and training to help you use it effectively. This would be a great way to create a sample and potentially win prizes. I’m on the panel of judges for this contest.

I’ve used Genially to build interactive activities for a client before, and it’s another good alternative authoring tool for samples. Genially’s free plan would be sufficient for your portfolio samples.

I haven’t personlly tried Parta, but I’ve heard it as another option. One reason it might be a better choice for a portfolio is that you can pay for the license monthly, rather than for the whole year. If you just need a month or two to build your samples, then you can pay for that and then unsubscribe later.

Adobe Captivate is much less in-demand than it used to be, but it’s an option for portfolio samples. It’s also possible to earn a free Captivate license by participating in their community.

Video tools

Camtasia is a great option for videos. Check out Cara North’s video series on creating a Camtasia portfolio sample from start to finish for a plan and example.

Animated videos can make great, visually appealing portfolio samples. PowToon and Vyond are popular choices.

Open source tools

If you want to use open source tools, check out Adapt and H5P. Neither one has seen widespread adoption, partly because they both require more technical expertise. However, you can create some really cool things with both.

It’s more specialized, and therefore not necessarily a good choice for everyone, but I also have Twine samples in my portfolio. Twine is great for branching scenarios, plus it’s free and open source. Learn more about Twine from my posts to get some ideas.

Hosting your portfolio

This blog and my portfolio were both built with WordPress. These are both self-hosted sites now, although my blog was on WordPress.com for many years. You can use a free WordPress.com site as your portfolio as a job seeker, but you’ll have to host your samples somewhere else or upgrade to a paid plan that allows plugins. (And if you’re upgrading to a paid plan for WordPress, you might as well just pay to host it yourself—you can do that cheaper.)

Check out Dianne Hope’s article on how to build a portfolio in WordPress.

In her article, Dianne explains how to use a free WordPress plugin to upload elearning samples. That plugin works regardless of what tool you use to create your samples (Storyline, iSpring, etc.).

I host my websites on Siteground. Shared hosting starts at $2.99/month for the first year, so it’s quite affordable to get your own site and have full control.

Free and low cost hosting options

Some people use template sites like use Google Sites, Wix, Weebly, or Squarespace. Those sites can work, especially if you find a template you like since editing can be challenging. The designs can be limited, and it can be challenging to post real samples with interactivity. It’s not my first choice personally, but it definitely works for many people.

If you’re using a free site like Wix, you probably need to host your samples elsewhere. WordPress.com and other free hosts don’t allow you to upload published Storyline or SCORM files (at least not on the free plan, and not necessarily even on a paid plan).

You can use Amazon AWS storage to host and share your files, linking to them from your portfolio. Google Cloud is another option; Kimberly Goh’s video explains how to use Google Cloud to host portfolio samples. Both of those options for file hosting are either free or very low cost for most portfolios.

Mike Taylor lists several free or low-cost options for hosting in this post (although a few, like Dropbox, are no longer options).

Portfolio examples

It helps to see other portfolios as inspiration for your own work. See how others have organized their samples and what they include.

Check out this post with 24 great examples of instructional design and elearning portfolios, collected by Scott Winstead. (Mine is included.)

The Articulate community also has a collection of portfolios.

Portfolio building course with personalized assistance

What if you need more than a collection of resources—you need a structured process for building your portfolio with step-by-step guidance and personalized feedback? Dani Watkins and I are re-launching our portfolio course, Create a Portfolio That Gets You Hired. We previously taught this course for UC-Irvine, but now we’re offering it publicly with new updates. If you want a clear framework to build your portfolio so hiring managers can see how you think, design, and solve problems, this course is for you.

Your favorite resources?

Do you have a favorite tool for creating portfolios or a resource I’ve missed? Let me know.

Originally published 3/16/2011. Republished 7/2/2019, updated 7/21/2022, 1/1/2024, 3/6/2024, 2/3/2025, 12/5/2025, 3/19/2026.

The post Instructional Design Portfolio Resources appeared first on Experiencing Elearning.

Elearning Characters

Character-Driven Learning Experiences

Great insights here from Teresa Moreno about using characters effectively in elearning. I especially appreciate the learning science angle here focusing on improving self-efficacy through “coping models.”

A mastery model demonstrates perfect performance from the start. They know exactly what to do, execute flawlessly, and model ideal behavior. This is what most learning designers and SMEs default to: show the “right” way immediately.   A coping model struggles, verbalizes their thinking process, makes mistakes, and demonstrates the process of overcoming challenges. They eventually succeed, but only after working through realistic difficulties.

Characters in learning design don’t need movie-like backstories. They need a recognizable problem intrinsically connected to what people need to learn. The swap question is the real test: could this character or story be replaced without changing what’s learned? If yes, it’s probably decoration.

—Teresa Moreno

Generating AI images

Agentic Image Generation

This is an interesting example of using agentic AI to generate an infographic based on a blog post. This uses Claude Code to connect Nano Banana Pro for image generation with an additional tool for providing AI feedback on the image. The workflow iterates and improves the initial image based on the AI-generated feedback, without human intervention.

How to use JSON to build better AI image prompts

JSON is a way of structuring your image prompts, clearly labeling what each detail is. It can help you think through the specifics of your prompt and generate more systematic and repeatable prompts. This prompt structure doesn’t work with all tools (including Midjourney), but it’s something to consider for more advanced prompting in other tools.

Fixing Plastic AI Skin: The Complete Guide to Realistic Prompts – Rezience | Andy H. Tu

While I don’t think that prompting alone will fix all problems with waxy skin texture in AI images, better prompting can improve your results. The specific phrases and tips here should work in any image generation tool (but watch out for the negative prompts; sometimes those confuse the models).

Midjourney releases Niji v7 & an interview with Google

Midjourney’s new Niji 7 model is designed especially for anime, but it should show improvements for other character illustration styles in consistency and prompt understanding. This article also includes some notes on Freepik’s prompt generation feature.

Working with AI

AI: You Still Have to Know Stuff – Usable Learning

Julie Dirksen articulates what many of us have experienced. Yes, AI can be useful…but we still have to have enough expertise to know what’s good about the AI output. You have to know what to discard or revise. Even as AI gets more accurate, you need to know what quality results look like. Plus, what happens when people come into jobs and don’t have that prior experience that helps them evaluate AI output?

I need to use my expertise to craft a prompt that will get the most accurate result, while still recognizing the parts that need revision.

—Julie Dirksen

Making the Grade: Can AI Be Trusted to Score Assessment Tests?

How do you train AI to score open-ended assessments and provide feedback? The same way you train human assessment scorers (a job I did for a few summers): with a detailed rubric, examples, and spot checking the results.

Memory research

Memory Rewritten: Study Finds No Clear Line Between Episodic and Semantic Retrieval – Neuroscience News

Previous research had pointed to the idea that episodic and semantic memory were different types of memory that used different parts of the brain. This study contradicts that earlier theory, finding that the whole brain is involved in memory.

…there is no difference in neural activity between successful semantic and episodic retrieval.

Episodic memory refers to the ability to remember a past event that occurred in a particular spatial and temporal context. This type of memory supports the human capacity to re-experience events from our past, as a form of “mental time travel”. Semantic memory, on the other hand, refers to the ability to remember facts and general knowledge about the world that are retrieved independently from their original spatial or temporal context.

Useful tools

BuddyBar – Color Palette Manager for Design Tools

A free color palette tool for Windows, Mac, or Chrome. Add your colors so you can copy hex codes or apply them in programs. This works with Storyline and Rise.

Grasp

AI tool to create a personalized collection of resources and a sequence to help you learn a skill based on a goal you identify. h/t Nejc

Chat Scenario Builder

Beta version of a vibe coded tool to create branching scenarios that look like chat conversations. I’m saving this to test later.

The post Elearning Characters, Generating AI Images: ID Links 3/17/26 appeared first on Experiencing Elearning.