I published my original version of this post almost a year ago, and so much has changed since then! This is my update as of October 2026, with notes focused on how AI image generation tools work for L&D tasks.

What to pay for: The quick answers

I currently pay for both Flora and Midjourney. Flora gives me a wide range of image models and tools, and Midjourney gives me more interesting artistic styles for my blog headers.

One tool

If you’re going to pay for one tool specifically for image creation, I recommend you subscribe to one of the all-in-one multimodal tools like Flora or Magnific. These give you access to multiple frontier models plus additional tools to make professional work easier.

Two tools

If you can pay for two tools, add Midjourney or another specialized tool depending on your needs (Recraft, Brushless, Napkin, etc.) Which specialized tool is best depends on your specific needs.

Cost comparison

This comparison includes the lowest paid plan, which is generally enough for L&D work.

All of these tools except for Midjourney have a free trial. I recommend that you pay for one month and try a tool with your own projects before committing to a longer subscription.

Flora: Connect multiple tools for better workflows

If you do regular professional work generating images and videos, an all-in-one canvas tool like Flora provides a much better interface and workflow than working with a chat interface. Flora connects multiple tools into a single workflow, so you can switch between Nano Banana, GPT Image, or whatever image model you need. Unlike other tools, their pricing for each generation is completely transparent; I can see how much each image or video I generate will cost in actual dollars, not just tokens or credits.

With a node-based tool, you can combine multiple reference images and prompts and then generate and iterate multiple outputs. It’s also easier in this type of tool to do multiple types of transformations such as editing images, removing backgrounds, or adding text as a separate layer. You can easily switch modalities at different points in your workflow, so you can generate images with one tool and then switch to generating audio or video with other tools all in the same canvas or project.

Rather than generating each image one at a time, you can batch generate multiple images at once or use techniques to save a series of actions to repeat later. I used a list of poses to generate sets of character variations from a single reference image, all in a single step. Features like batch nodes and repeatable techniques can speed up your workflow.

Flora is the tool I use most often for generating images and videos for training. If you’re only going to pay for one image generation tool, I recommend a tool that gives you access to all the major models and additional features like Flora or Magnific. These give you the flexibility to use different image models plus all of the other features for professional work at scale.

Midjourney: Most interesting and artistic, style consistency

Midjourney is the tool I use most often for my blog header images. It’s the image generation tool that I find most interesting; it’s easier to generate images that don’t look like typical AI or stock images. You can create images in consistent styles and colors from any starting image, and you can use and generate style codes to expand your options.

Both the overall aesthetic of Midjourney and the infinite range of styles possible are reasons I see many top AI image experts start with Midjourney, even if they then move to other tools in their workflow. I generally have the highest success with Midjourney for generating visual metaphors and symbolic images to support learning. Midjourney is the best at artistic images, which means it’s a great choice for illustrations.

Midjourney handles photorealistic characters reasonably well, including generating multiple poses and expressions from the same starting character image. It’s not as good at consistency as Nano Banana, ChatGPT, or some other tools. I find that skin textures become less realistic over subsequent generations though. Midjourney’s editing tools like inpainting are useful.

Midjourney is better at generating text than it was a year ago, but still not effective enough to rely on it. For my blog headers, I just add the text in Affinity Designer so I can maintain consistency.

Gemini (Nano Banana): Best free tool, character consistency

Of the free tools for AI image generation, Gemini is probably the best overall option. It’s capable of generating and editing images and creating multiple poses of photorealistic characters. It’s easy to make the edits by describing them in plain language. You may run into limits or experience slower generation on a free plan.

Gemini is the tool; Nano Banana is the general name for the image models in the Gemini LLM and available through other tools. Although I work within Flora for the interface, I use Nano Banana image models most often for photorealistic images.

Nano Banana is good at generating consistent icon sets; you can prompt for a grid of icons in a single prompt and get results with high accuracy. It’s not as good at illustration styles as Midjourney; the styles tend to look more similar and more recognizable as AI.

Basically, Gemini’s image generator does all the things that ChatGPT’s image generation can do, but it does them all a little better. It doesn’t look as obviously AI, and it tends to be more accurate in following prompts both for initial generation and edits. I find that it still looks like stock images if you don’t prompt well. While the text accuracy is good, the fonts sometimes look out of place, especially on edits.

ChatGPT: Improving, but still clearly AI

ChatGPT’s latest image models, GPT Image 2.5 Flare and Sunburst, were released in September 2026. These models are both significant improvements from the early models. They’re more accurate in following prompts and editing parts of an image without changing the rest. You can generate both photorealistic and illustrated images.

One of the challenges of ChatGPT for images is that it’s such a common tool that’s it’s very recognizable. Especially for images with text, the default style is instantly detectable as ChatGPT from the paint slash with white text on it on the “whiskers” emphasizing text. A lot of what people perceive as “AI slop” posters is generated quickly with ChatGPT.

It’s possible with better prompting to get better results that don’t look so distinctively like ChatGPT, but it’s more work. I still generally prefer Nano Banana to either of the GPT Image models, but it’s much closer now.

Magnific: Multiple tools in a combined workflow

Magnific (formerly Freepik) is similar to Flora. It offers you a choice of multiple tools on a visual canvas where you can easily see your work and switch tools as needed. They’re regularly adding new features for creative professionals such as a brand kit to save your colors and other brand details.

I tried both Magnific and Flora, and they’re both great options. Personally, I find Flora’s canvas to be a little smoother to move around; it’s easier to switch between panning on the canvas and adding nodes. But if you’re interested in this kind of tool, it’s probably worth trying each one for a month. Depending on your specific workflow or how you collaborate with others, Magnific might be the better option.

Recraft: Brand consistency, text accuracy, icons, and vector images

Recraft is a tool that should definitely be on your list to try if you need consistency in branding or need to generate vector images. Many image generators create images that look like vectors but aren’t actually SVGs; Recraft generates true vector images so it’s easier to scale and edit them elsewhere. They have a tool for generating icons that lets you generate up to six icons at a time, all with a consistent style and color palette. Their text accuracy is also much higher than other tools.

I don’t think their photorealistic images are as good as Nano Banana or Midjourney, but it’s a solid choice for illustrated images. You can use the built-in styles or create your own. It even has options to share styles within teams, which makes it a better option for organizations with multiple designers.

Brushless: Vector images and icons with consistent styles and colors

Brushless is another great option for vector images and icons. They have several illustration styles that are ready to go. I think their built-in flat icon style works well for training purposes, especially when you need to generate specialized icons for presentations or highlighting important concepts. The line art style is good for simple illustrations where you don’t want to distract learners with overly complex images (and AI images can be overly complex and distracting). You can set your color palette to match your branding and use reference images to create your own custom styles.

Napkin: Images and visual organizers to explain concepts

Napkin works differently than a lot of the other AI image generation tools out there. Instead of prompting for images, you paste your text such as bullet points or a paragraph of explanation. Napkin interprets that text to make an image to explain it. The result is something like PowerPoint’s SmartArt but better. You get icons for main points and diagrams to show connections and structure illustrating your concepts.

Ideogram: Image editing

Ideogram was one of the first AI tools to figure out how to render text accurately. Ideogram generates some interesting illustrations, so sometimes I use it to compare how it does with the same prompt as other tools. Ideogram has image editing tools that can be useful to refine and extend images, even from other sources. Ideogram’s most recent update focuses on editing just a portion of an image without regenerating the entire image. Most AI tools drift over the course of successive edits because they regenerate everything. If you need a background to stay the same while you edit a central object or character, Ideogram is worth trying. Their lowest paid plan also include unlimited slow credits, which means you can keep generating without limits (just not very quickly).

Hands-On AI Image Workshop

Want to learn how to generate higher quality AI images—visuals that are good enough to actually use in a course? Part of the trick with AI image generation is that even if you start with a good prompt, you still may need to iterate a few times to refine it. Even though I’ve presented on AI images multiple times, it’s impossible for me to give participants enough time to really practice that iteration process in a one-hour webinar.

Registration is now closed for the workshop, but you can sign up for the waitlist to be notified when this workshop is offered again.

Learn more about the AI Image Workshop

These are my opinions

None of this is sponsored; it’s all based on my own experiences. In a few cases, I have gotten some extra free credits with specific tools in order to test them or in exchange for providing feedback on the tools. I have paid subscriptions to Flora and Midjourney, and I get access to a number of other image generation tools through my subscription to Poe.

Your experiences may be different. Like all AI tools, the image generators are sometimes unpredictable in what they can do effectively and where they fail. You may find that different tools work better for your specific needs.

For all of these tools, check the terms of use. Most explicitly allow commercial use of images on paid plans, but not necessarily on free plans. Some tools will make your generated images public, especially on a free plan. Some will train their AI on your images, including uploaded reference images.

More tools?

Obviously, I didn’t cover every AI image generation tool currently available in this post; this is based on what I’ve personally tried.

• Same Prompt, Different AI Image Models
• Consistent Character Images Step by Step using Flora and Nano Banana
• Updating Scenario Character Images with Flora
• Speed Up Character Image Creation with Flora
• AI Images with Consistent Style in Midjourney
• Testing Freepik Spaces for Character Image Generation (It was Freepik when I tested it, but Magnific now.)
• Nano Banana (Gemini) Character Image Experiments
• Frustrations with ChatGPT Image Generation
• How to Generate Icon Sets with AI using Midjourney, Nano Banana, ChatGPT, and Brushless

Originally published 11/4/25. Updated 4/28/26, 10/12/26.

---

Upcoming events

Learning Architecture: From Content to Context. October 21. Learning Planet Institute.

DevLearn

Register for DevLearn by October 2 for the Advanced Rate. Save an extra $100 with code CHRISTY.

Branch Smarter, Not Harder: Naming Conventions, Variables, and Bottlenecks in Storyline

• November 3, 2026 at 9:20 AM
• CE01: Storyline & Rise Pro Lab

Cohesive by Design: Generate Consistent AI Icons, Illustrations & Characters

• November 4, 2026 at 10:00 AM
• BYOD (Bring Your Own Device)

Buzz Discussion: Video & Media

• November 4, 2026 at 3:45 PM

The post Comparing AI Image Generation Tools appeared first on Experiencing Elearning.

Step 1: Reference image

The first step to generating a set of consistent character images is generating a reference image. Sometimes I initially generate a character on a blank background for my reference image, but this time I just started with an image of the character in a scene. For a larger set of images, a full body reference image or a character sheet from multiple angles is helpful. I knew this was going to just be a small set though; I was experimenting with camera angles for a blog post.

I used my standard image prompt framework to specify the image style, subject, action, setting, and details. All of the images in this post were generated in Flora with the Nano Banana 2 model.

Editorial photo, Puerto Rican man in his 20s with a beard trimmed close, wearing a dark orange shirt and blue jeans, black glasses, sitting on a bench at a park looking at his phone, low camera angle

Results: As you can see, this image didn’t quite work. What’s going on with that wooden half bench back or fence in front of him? I like the character, but the physics doesn’t make sense.

Using the initial image as a reference image by attaching it to the prompt, I asked for a new image.

Pan out to a wide angle establishing shot of the park with this man sitting in the bench viewed from farther away

Results: Just panning out and changing the scene got rid of the weird wooden half bench in front of it. It changed several other details in the image as well: he’s no longer smiling, there’s now a section of green grass where people are sitting instead of trees. It’s still the same person with the same outfit though; the character consistency is good.

I wanted to see what this would look like with more grass instead of his bench being on a paved area.

Extend the grass to the bottom of the image so the grass is under the bench. Keep everything else the same.

Result: This gave me a weird patch of grass underneath. I didn’t like this iteration, so I discarded it and decided to stick with the previous one.

Step 2: Change the action

With my initial character reference ready, I could start generating additional images of this character. I used my very first image as the character reference here since it was a closer image. I changed the action and the camera angle. Because I attached the reference image to the prompt, all I needed to say was “this man,” and Nano Banana maintains the details.

Create a close shot, side angle, profile view of this man talking and explaining something, head and shoulders only. 

Result: I liked how the character turned out here. His pose looks fairly natural, and his skin texture looks fairly realistic even in this close up. Because I used that very first image as my reference, you can still see the weird wooden half bench in the background, but at this angle it just looks like he’s standing near a bench.

Step 3: Change the camera angle

Next, I wanted an image where I changed the camera angle. I wanted to show him talking to another character, but with the camera behind him. I used the image of him talking as my reference image. This means I’m only changing one thing: the camera angle.

Create an over the shoulder image showing the back of this man's head while he's talking. 

Results: The camera angle change worked on the first try. I’m happy with the consistency of the character here.

Step 4: Add another character

Now, I needed another character in the scene so it’s clear who he’s talking to.

Zoom out to show that the man is talking to a Chinese woman who is listening with a neutral expression. She is wearing a blue shirt.

Results: Success in one try! The AI panned out the camera to give more space for the second character while maintaining the first character.

I might have been able to do steps 3 and 4 together, but I find that I often get better results when I limit the edits to one major change at a time.

Step 5: Change the setting

I also wanted an image of this character walking. For my first try, I kept the scene in the park.

Create a tracking side angle image of this character walking on a paved trail in a park, afternoon sunlight

Results: If I only needed a single image, this one might have worked OK. But when you see it side-by-side with the image of him sitting on the bench, you realize that the background is the same. I didn’t tell the AI to choose a different part of the park, so it created an image by removing the bench and keeping the character in the same location.

Rather than trying to get an image in this park, I decided to change the scene entirely and put him walking on a street.

Change the background to be a quaint main street of a small town in Florida

Results: The character consistency is good, but the setting has multiple problems. What’s with the weird vintage cars, especially the brown one in the back? And the name of the restaurant is the…”Florida Cracker Cafe”? Um, that’s certainly an interesting choice that the AI made. This is a great example of why you need to check your AI images, including the background details. I decided to leave the greenery in front of the restaurant, but I often iterate images to tell the AI to remove the proliferation of potted plants.

In my prompt for changing the text, I put the exact words I wanted on the sign in quotation marks. I made two edits at once here. If that had failed, I would have gone back and split up the changes across two edits.

Change the name of the "Florida Cracker Cafe" to "Sunny Crepes and Coffee". Remove the cars on the street.

Result: This one looks much better. I could still do more with the other signs in the background. It depends how you’re using an image how much you need to zoom in and inspect it. This image series was for a blog post banner, so I knew I wasn’t going to use them in a large format. In a small size, the background text is probably OK as is. If this was a hero image in a course, I would spend more time polishing those details.

Step 6: Review all images

After finishing the entire image set, I looked at them all together one more time to make sure I didn’t need to make any further adjustments. Here’s what the whole set looks like in Flora. I generated 9 images and kept 4. In the screenshot below, you can see my workflow, moving generally left to right. Each connecting line shows where I used a reference image.

Bonus images

I also generated two more images later in response to someone’s question about images of people opening doors and windows. Both of these images have some issues, but opening windows was particularly challenging to get right. Because the AI image models don’t generate images based on actual physics, they get these sorts of details wrong regularly.

Edit and iterate to improve your AI images

A lot of AI images look really obviously AI. Partly, that’s because people generate something and just accept the first result. Better initial prompting and providing design guidelines can improve that first result, but you still need to edit and iterate. I hope this worked example of my step-by-step process of creating consistent character images helps you learn to edit and iterate your own images more effectively.

AI Image Workshop October 14

If you want more practice and guidance on this process of editing and iterating, sign up for my AI image workshop, From First Try to Finished. You’ll get six rounds of hands-on practice, much of which includes this kind of image refinement like I showed in this post. We’ll debrief each round of practice to talk about what worked and what didn’t, and I’ll provide feedback and coaching on how to improve your results. You’ll get 3 hours of specific tips I’ve learned through doing it myself plus time to immediately apply what you learn.

Registration closes Tuesday, October 13.

The post Consistent Character Images Step by Step appeared first on Experiencing Elearning.

Accessible color

Accessible Color Choices Are About So Much More Than Just Contrast – Sheri Byrne-Haber’s Blog

This article is a deep dive into accessible color choices for potential issues such as high contrast repeating stripes causing migraines or saturated red triggering seizures. This includes a list of color issues not regulated by standards but that may still cause problems (such as cultural differences in colors). h/t Kayleen Holt

APCA Contrast Calculator

This contrast checker uses a different calculation than the standard WCAG color contrast checker. It recognizes a difference between light text on a dark background and dark text on a light background. Sometimes color pairs that meet the WCAG can still be hard or tiring to read, and this calculator may be especially useful for those pairs.

A Deep Dive into Contrast Themes | Digital Accessibility Services

Contrast Themes are an accessibility feature in Windows that overrides the default colors used to provide custom choices for better accessibility. This is beyond doing a light and dark theme, but a way for the user to adapt the app or website in a way that works for them. This article gives specific tips for better compatibility with Contrast Themes. For example, if the focus state would change background color but not outline, using a transparent outline instead of outline: none lets the Contrast Theme provide an outline in a user-selected color.

AI images

Welcome to Magic: The Editor – by Humble Nations

Midjourney’s new editor is now available. You can prompt for edits with natural language, more like prompting edits in Nano Banana. This article includes a bunch of examples of editing prompts for changing the style of images, plus a few others like changing camera angle, character pose, and prompting layouts from sketches.

GPT-Image2 Prompt Gallery

A collection of hundreds of examples of images and prompts created with ChatGPT. Filter the list by category and style. The examples are sometimes uneven in quality; some of these have that very obviously ChatGPT look to them. But there are some creative ideas too, and it’s helpful to see examples of prompts to see how to describe different visual styles and elements.

Why A.I. Struggles with Negative Words | Otherwords

If you’ve ever tried to generate an image with AI and asked for “no plants” in the office, only to get a bunch of plants in the image, you’ve seen how much trouble AI has with negative language. This video explains why negative words are hard for AI to understand.

Real or AI? – Test Your AI Image Detection Skills

Can you identify which images are real and which ones are AI? I did terribly on this quiz the first time I tried: less than 50% right.

AI video

SLICE: how we made a 2-minute AI short film with Seedance 2.5

This is a great example of a “show your work” post on what it takes to generate high-quality AI videos. The prompts to create the characters and scene and to generate the video clips are included. The amount of detail needed to prompt in Seedance is significant; the prompt for the first 30-second clip is 700 words long. Check the notes at the end about what failed and how he worked around the problems too.

Remove Text from Video Online – AI Video Text Remover

I’ve never personally had a need to do this, but I can see how this tool might be useful. If you have a video with burned in “open” captions, this AI video editing tool says it can remove the text. The pricing options include buying a credit pack, so if you only have an occasional need for this you can buy credits instead of adding yet another monthly subscription.

Working with AI

The AI Workflow Redesign Method: How the Top 6% of Users Get Real Returns from AI

Dr. Philippa Hardman explains her process for analyzing a workflow to determine how to redesign it to get more value out of AI.

Psychological Stamina and other #NerdStuff – Usable Learning

Julie Dirksen explains the concept of psychological stamina. Even if you have the knowledge and skills to do a certain task, how long can you keep doing it? If the behavior requires vigilance over time, like watching for hazards on the road while driving, how long can you maintain that level of mental focus?

Diligence for reviewing outputs is a key element for successful use of AI (as I may have mentioned a few times before).

—Julie Dirksen

AI environmental impact

AI vs. Streaming: Energy, Water and Hidden Costs

Josh Penzell created a calculator to help people compare the energy, water, and other environmental costs of using AI in comparison to streaming. One insight I had from this tool is that AI uses a lot more direct on-site water. That’s probably where some of the really high numbers of AI water use come from. But when you look at the total operational water including the electricity use, then streaming uses more water than AI. All of the source data is provided so you can dig into it yourself.

Tools for instructional designers

The ID Toolbox: free tools for instructional designers

A collection of free utility tools for instructional designers. I will definitely use the Caption Line Splitter, which rewraps captions based on the number of characters and lines. The collection includes other utilities for accessibility, QA, calculating development time, identifying which text will overflow when localized, and more.

Hands-On AI Image Workshop

Want to learn how to generate higher quality AI images—visuals that are good enough to actually use in a course? Part of the trick with AI image generation is that even if you start with a good prompt, you still may need to iterate a few times to refine it. Even though I’ve presented on AI images multiple times, it’s impossible for me to give participants enough time to really practice that iteration process in a one-hour webinar.

Registration is now closed for the workshop, but you can sign up for the waitlist to be notified when this workshop is offered again.

Learn more about the AI Image Workshop

The post Accessible Color, AI Images and Video: ID Links 9/29/26 appeared first on Experiencing Elearning.

Use reference images

My first lesson learned was to use reference images. I already knew that, to some extent, because I use reference images for character images. I used those same character reference images for all of the videos you’ll see in this post.

However, I didn’t use a reference image for the setting. While I did have images I could have used for the first frame, I’m still not completely happy with what I’d gotten previously. I decided to see how the different tools did at setting the scene without a reference image. That was OK for this experiment, but I think for further development I’d want to have at least one reference image for the setting, if not a storyboard with multiple images.

Instead of a reference image, I included a description of the room in my prompt. I include a description of art on the walls because otherwise the AI tools often fill in other details. I often get unrelated text on a whiteboard or charts on a screen, and I didn’t want those here. (Again, if I’d used a reference image for the room, that would have fixed the problem.)

The dialogue comes from the opening passage of my project management scenario.

Setting: Three people @Jake @Samantha @Alex meeting in an office conference room, all sitting around a table. Laptops and coffee mugs on the table. Light gray walls, overhead lights, abstract corporate art on the walls.

@Jake : "Alright team, we're a week behind schedule on the Healthtrack project, and the client still hasn't provided the data integration requirements we requested three weeks ago."

@Samantha: "Without those requirements, we can't properly design the system architecture. We risk making assumptions that could lead to costly rework down the line."

@Jake "We can't afford to keep falling behind. We should make our best educated guesses based on our experience and move forward."

@Alex "I'm with Samantha on this. If we don't get the integration requirements right, it could severely impact the user experience and data flow."

This first example video was generated in Google Omni 1.1 Flash. I’ve had decent luck with this model for generating b roll videos.

• Model: Google Omni 1.1 Flash
• Video length: 10 seconds
• Cost: $1.20
• Cost/sec: $0.12

All costs noted are my actual costs as calculated in Flora; I did math to determine the cost per second.

Give enough time to include the dialogue

I immediately realized one of my errors: that dialogue was too long for the generation time. The video is 10 seconds, but I had more dialogue than could fit. The AI trimmed my script to fit it in rather than using it verbatim. That would be fine for some uses, but that’s not what I wanted for this scenario.

For my next attempt, I trimmed it to just the first line of the script. I hoped that would give it enough time to keep the dialogue accurate. And…well, you can see for yourself. It was closer, but it still wasn’t quite right. I also adjusted the description of the room; I decided I didn’t like the abstract art.

Setting: Three people @Jake @Samantha @Alex meeting in an office conference room, all sitting around a table. Laptops and coffee mugs on the table. Light gray walls, gray chairs, light wood table, a clean whiteboard on the wall. Overhead florescent light.

@Jake : "Alright team, we're a week behind schedule on the Health track project, and the client still hasn't provided the data integration requirements we requested three weeks ago."

• Model: Google Omni 1.1 Flash
• Video length: 6 seconds
• Cost: $0.72
• Cost/sec: $0.12

Watch for character positions changing

One of the other problems in this video is that Alex shifts position. At the beginning, he’s sitting next to Samantha. Partway through, he magically transports to sit next to Jake. This is another problem I probably could have solved with reference images and a storyboard. I’ve even seen a demo where someone blocked the character positions in Blender for a rough 3D model and then used that to keep each character in the same place around a table. Keeping the characters and objects consistent from scene to scene is a challenge unless you’re directing it.

Some models look more AI than others

I wanted to test several models to be able to compare the results. I used the same prompt again with a different model, MiniMax. These results were even worse; this looked and sounded really obviously AI. The character and dialogue accuracy was lower. Check out how Jake’s background suddenly switches to the studio photo background rather than the conference room background. MiniMax was fast and reasonably cheap, but it’s not the right model for this task.

• Model: MiniMax H3 Max
• Video length: 8 seconds
• Cost: $0.768
• Cost/sec: $0.096

Video generation costs can add up quickly

Next, I tested Seedance. This is a higher quality model, but it’s also slower. Each generation took several minutes, where the previous videos tool under a minute to generate. I have had some good results with Seedance, but it’s also about four times more expensive than the Google or Minimax models. With Seedance, I generated an initial clip of 8 seconds. Then, I used the Extend video function in Flora to generate a second clip for the next clip with Samantha’s response. I stitched the two clips together in Flora.

• Model: Seedance 2.5
• Video length: 21 seconds
• Cost: $3.914 + $6.337 = $10.251
• Cost/sec: $0.488

You can see the Seedance clips combined below. The transition is weird; I should have prompted for the camera angle to change to point at Samantha instead of starting zoomed out and pushing in again. But because Seedance is so expensive, I was reluctant to generate another clip. If this was a real project and not for my blog, I would have had to pay the $6 for another generation.

While Seedance is higher quality (and I know I could improve my results with more detailed prompts and direction), the cost is significant. A 2-minute video would cost about $58 in generation. Knowing that some clips wouldn’t work on the first try and would need to be regenerated, a more realistic estimate for a 2-minute video might be about $75-$80. Maybe it’s because I’m used to how cheap image generation is (images cost 5-7 cents on Flora), but I was surprised at how fast the costs added up.

Voice quality and consistency concerns

AI voice overs have dramatically improved in quality in the past few years. However, in these AI generated videos, you probably noticed some issues. For example, in the Seedance clip above, Samantha has weird, overly dramatic pauses in her line. I’ve also heard issues in keeping the voice consistent for characters across multiple clips.

In order to generate enough videos for a full interactive video scenario or a longer conversation, I think I’d need to generate the audio separately in ElevenLabs or WellSaidLabs. That would give me higher quality and more control over the generation. Plus, that would fix the consistency issue; as long as you use the same voice for each character, you maintain the same sound throughout.

However, bringing in audio also means dealing with lip syncing in the video tool, and that creates a different set of challenges. How accurate is the lip syncing? How many generations does it take to get it right? After you generate clips, how much manual editing is needed?

Reflections on AI videos for training

This is a sample project for my blog and portfolio, so I’m not persisting through challenges the same way I would if this was a real client project. Right now, I feel like the AI video tools like this are good for generating short b roll clips. I’m already using AI videos for that purpose in actual explainer videos now.

For more complicated videos, it’s going to take a lot of time, iteration, and cost. There’s no magic where you drop a script in, press a button, and get a fully formed video with multiple characters, dialogue, camera angles, and consistent background out. It’s possible to generate higher quality videos with AI (check out how the 2-minute animated video Slice was created), but it takes quite a bit of work. I’ve seen some 700+ word long prompts for Seedance; that’s a lot of time directing the AI that I didn’t spend for these samples.

When my clients have asked me about AI video generation over the past two years, I’ve been telling them to wait another 6 to 12 months and then check in again. At this point, I think it can be done, but we have to be realistic about what it takes. All of these models are cheaper than hiring actors for a half day shoot, but it’s expensive and difficult enough that I’d need to scope it realistically.

Will you know that all of these are AI-generated videos? Yes. But getting the quality good enough to be useful for training scenarios doesn’t necessarily mean it has to be indistinguishable from using human actors. In fact, I think sometimes we’re better off using illustrated or animated styles that don’t pretend to be real people. You can still get the value of a conversational example or interactive video with something illustrated.

AI video tool comparison

Here’s my summary of the three AI video tools I tested.

Hands-On AI Image Workshop

Want to learn how to generate higher quality AI images—visuals that are good enough to actually use in a course? Part of the trick with AI image generation is that even if you start with a good prompt, you still may need to iterate a few times to refine it. Even though I’ve presented on AI images multiple times, it’s impossible for me to give participants enough time to really practice that iteration process in a one-hour webinar.

Registration is now closed for the workshop, but you can sign up for the waitlist to be notified when this workshop is offered again.

Learn more about the AI Image Workshop

The post Lessons Learned while Generating AI Videos appeared first on Experiencing Elearning.

Typical compliance training: Push

Let’s say you’re creating training for managers on providing reasonable accommodations for disabilities. A typical elearning compliance course on reasonable accommodations would start with a history of the ADA, ADAAA, Civil Rights Act, etc. (Readers outside the US, substitute your own laws about disabilities.) You might compare how the laws have evolved over time, define the terminology, and list some common reasonable accommodations you could provide.

All of that is “pushing” content to learners. The learners are treated as passive receptacles for content. You as the instructional designer control what content is delivered, in what order, and how quickly. The learners don’t make any decisions, and they don’t have any reason to dig deeper into the content.

Alternative compliance training: Pull

You could flip the whole course around though. Instead of pushing content to learners, you let them “pull” what they need. The trick is that you have to give them a reason to need the information.

In the example below, Rosa asks her manager, Cindy, for time off after a surgery. This is a plausible situation managers might find themselves in where the right answer might not be obvious. The managers have to make a decision: to grant the time off or not.

In this scenario, you could just offer the two choices: grant the time off or not. However, I’m deliberately putting them in this situation to give them a reason to look up the policy. Therefore, I have two more choices below: “Ask HR” and “Review Policy.” If learners choose “Ask HR,” they’ll see a simulated conversation with an HR specialist explaining the policy and providing advice. Either way, they’re “pulling” the policy information because they have an immediate need for it.

“It’s easiest to pay attention to content that you can use right away. Use strategies like test-then-tell, scenarios or problem-based learning to create an immediate use for the learning content.”

Julie Dirksen, The Science of Attention and Engagement for Learning

“Pull” options

You might choose to only have one option for explaining the policy rather than two like the above example. Either just reading it or asking another character for advice might be enough. If reading the policy is the only option, it’s helpful to include a plain language explanation. This is especially true if the original policy is written in very formal or legal language. You can provide the original and the explanation side-by-side, or you might just provide the explanation.

If your users will have a job aid when they actually do the task, use that job aid in the course so learners practice with that tool. If they won’t have a job aid in the real workplace, what would they do instead? Would they consult with HR or ask a manager? Figure that out, then build that into the scenario. As much as possible, make the way learners access policy information in your course similar to how they will access it on the job.

Knowing when policies apply

Another advantage to the pull approach is that it helps learners see when policies apply to different situations. This is especially helpful if your audience needs to be able to distinguish between similar situations. Maybe under most circumstances, “guideline A” applies, but there’s an exception where “guideline B” applies instead.

“Learners are motivated when they can see the relevance of what they are learning. If they learn new information in the context of real world problems, if they are shown a demonstration of skills they are expected to acquire (show), if they have the opportunity to apply these skills in the solution of additional real-world problems or the performance of additional real-world tasks (do), then they are much more likely to acquire, retain and be able to use the required skills.”

M. David Merrill, Finding e3 (effective, efficient and engaging) instruction

Another example: Cathy Moore’s Connect with Haji Kamal

Although Cathy Moore’s Connect with Haji Kamal isn’t compliance training, it also demonstrates the technique of having characters ask for advice. Learners need to “pull” information and actively seek it out rather than passively waiting for the course to “push” it to them. It’s the same mechanism, just a different kind of training.

Cathy’s original version is no longer available since it was built in flash, but Stephanie Harnett built The Return of Haji Kamal in Storyline with the original assets (and Cathy’s permission).

Try one-question mini-scenarios

Even with one-question mini-scenarios instead of branching scenarios, you can use this technique to motivate your learners to look up the policies themselves. Give learners a reason to seek out and immediately apply the information. That will make them more likely to remember those policies when similar situations happen on the job.

Image credits

• Characters from eLearning Art
• Document by useiconic.com from the Noun Project
• Conference room from Storyblocks

This compliance course example is also used in What’s Your Character’s Goal?

Originally published with the title “Motivating Learners to Look Up Compliance Policies Themselves” on 3/22/2016. Updated and republished with a new title 7/21/2020. Last updated 9/10/2026.

The post Create Motivating Compliance Training appeared first on Experiencing Elearning.

You’ll learn strategies for writing more effective image prompts to minimize bias and reflect more inclusive representation in your learning. You’ll get tips to more authentically represent your training audience by using AI images. While AI tools are improving all the time, they still have limitations that you need to be aware of. We’ll discuss some of the ongoing challenges with inclusive representation in AI image generation and options to minimize those issues. You’ll leave with a collection of sample image prompts, a prompt framework for better results, plus tactics to make your AI-generated images more inclusive.

Watch the recording

If the video isn’t embedded below, you can watch the presentation recording on YouTube.

Download the slides

Most of the time, I don’t share my slides for presentations. My slides aren’t all that useful on their own, so I build separate handouts with more comprehensive information. However, in this case, where the focus is often on both the inclusive AI images and the prompts to generate them, having the images of the slides is helpful.

AI still can’t show left-handed writing

One of the observations I shared in my session is that AI image generators still can’t show someone writing with their left hand. That’s partly because the majority of images of people depict right-handedness. That becomes the default prediction for the AI when showing writing, and I haven’t found any AI image model that can override that default.

For example, here’s Nano Banana’s result for this prompt:

Editorial photo, a left-handed woman writing in a notebook with her left hand in a charming coffee shop, focus on the hand, notebook, and table. An iced latte is on the table next to the notebook.

Is left-handedness the most pressing issue related to inclusive AI images? Of course not! But it’s an example of how AI predictions about the most likely results can amplify stereotypes in images. The same types of predictions happen with gender, race, ethnicity, nationality, hair, skin color, disabilities, assistive devices, body type, and more.

Generating images of a range of body types

AI images tend toward slender body types. Adding descriptive phrases like “average weight” or “slightly overweight” can help counter that. 

These four images all used the same prompt except changing the body type as shown.

Style: Candid iPhone photo
Subject: Greek woman, mid 30s, black wavy hair, olive skin
Body type: [Very thin, athletic; Average weight; Slightly overweight; Obese, heavyset]
Clothes: Blue and white floral shirt, tan slacks
Action: Laughing at a joke, pointing
Setting: On the sidewalk, outside a cafe
Lighting: Golden hour
No signs or text

More on inclusive AI images

• Disability Representation in AI Images
• Nonbinary Characters in Scenarios
• Considerations for Using AI Images Ethically
• Minimizing Bias in AI-Generated Images (My AIDC presentation last year)

---

Upcoming events

Learning Architecture: From Content to Context. October 21. Learning Planet Institute.

DevLearn

Register for DevLearn by October 2 for the Advanced Rate. Save an extra $100 with code CHRISTY.

Branch Smarter, Not Harder: Naming Conventions, Variables, and Bottlenecks in Storyline

• November 3, 2026 at 9:20 AM
• CE01: Storyline & Rise Pro Lab

Cohesive by Design: Generate Consistent AI Icons, Illustrations & Characters

• November 4, 2026 at 10:00 AM
• BYOD (Bring Your Own Device)

Buzz Discussion: Video & Media

• November 4, 2026 at 3:45 PM

The post Inclusive AI Images for Learning appeared first on Experiencing Elearning.

Conferences

In Defence of Conferences – by Tom McDowall

Tom McDowall reflects on how conferences serve different purposes depending on where you are in your career and what your professional goals are. Consider his questions when making choices about what’s worth your time and money to attend. The biggest and most popular conference might not be right for you, depending on your goals.

Ahead of booking or agreeing to go to anything, ask yourself two questions: What elements of my practice do I want to focus on? What do I want to deliberately improve over the coming twelve months? Once you know the answer to that, then and only then should you start thinking about: Which events in the calendar could support me on that journey?

—Tom McDowall

elearn Magazine: Writing (And Reading) Conference Session Descriptions

Clark Quinn reminded me of this article from 15 years ago about writing proposals to speak at conferences. Even though the article is older, the advice is evergreen, and it overlaps with some of the same key points I shared in my recent podcast interview on conference speaking. He also talks about titles and other aspects I didn’t address.

What makes a compelling audience experience? What will make them leave in a state of gratitude for the time spent with you?

You need to be answering three questions: Why should I care, how will this accomplish my goal, and why this speaker? In business, what’s the pain point I’m feeling, how will this session address it.

—Clark Quinn

Camera angles

The Psychology of Camera Angles: How Perspective Shapes Every Photo – PhotoWorkout

As I work with AI images and video more, I find myself needing to learn more about camera angles—how to describe what I want and how to be more deliberate in my choices. This article about the psychology of camera angles and how they affect how the viewer feels about an image.

The Ultimate Guide to Camera Angles & Shots (with AI Prompt Examples for Storytelling)

A guide to different types of shots plus camera angles. This includes examples so you can see the difference (although they’re not amazing AI-generated images, they still serve the purpose). The sample prompts give you examples of how to describe and ask for different results. There’s also some tips on combining shot types and camera angles (like close up and low angle) for different effects.

Videos

I hired an AI agent to edit my videos

Ross Stevenson explains how he uses Riverside’s AI features for editing videos to avoid the tedious parts of editing and polishing.

Seedance 2.5 animation prompts: the ultimate guide to 10 styles | Magnific Blog

While I feel fairly confident describing images in prompts, I know I have a ton more to learn about prompting for video, including for animation. This article gives examples of prompts in different animation styles. It’s helpful to see both the repeated patterns in the prompt structure (starting with the medium, listing numbered shots, describing emotions) and the specific keywords to convey different styles.

Scenarios

How to Design Better Branching Scenarios: Start With the Decision

This article by Garima Gupta has a lot of overlap with my own process for writing branching scenarios (e.g., asking questions to narrow down the specific behavior, identifying decision points first). I like her explanation of the “mental model” behind the choices to get more believable options.

A stronger approach is to make each choice represent a different way someone might genuinely interpret the situation. One manager might think, “I need to establish authority before this gets out of control.” Another might think, “They are upset, so I should probably leave the performance issue for another day.” Someone else might decide they need more information before responding. These are not random distractors. They represent different mental models.

The question I would use is: what is the least complex structure that still allows the learner to practise the thing that matters? Branching complexity should follow the learning need rather than become a goal in itself.

—Garima Gupta

Name Generator Tools

Wordineer has name generators organized by continent and country, primarily European and Asian names. You can generate first and last names and pick options like the type of surname and the meaning.

SCQA: What is it, how does it work, and how can it help me? – Analytic Storytelling

I’d run across this model before in business communication, but Jean Marrapodi brought it to my attention again recently. This is really a story framework for presentations or reports where you want to communicate information. It could work as an overarching pattern in an explainer video or training too. It’s less suited to interactive stories or branching scenarios, but you could adapt it to work there too.

Working with clients

Why Silence Scares Your Clients (And How to Fix It)

Clients get anxious when they don’t hear from you, even if you’re working hard and making great progress. Proactive status updates reduce client stress and make you easier to work with. This is a great approach for L&D freelancers and consultants, and very similar to the structure I use for my own weekly updates to clients. I learned this lesson myself early in my freelancing career.

Clients don’t judge your expertise purely by the quality of your final deliverable. They judge it by how safe they feel while waiting for it.

LinkedIn tips for job seekers

LinkedIn Content Strategy for Job Seekers: 5 Posts That Get You Noticed

Knowing how many folks in my network are looking for work, I thought this list of tips for job seekers for posting on LinkedIn would be helpful.

---

Upcoming events

Learning Architecture: From Content to Context. October 21. Learning Planet Institute.

DevLearn

Register for DevLearn by October 2 for the Advanced Rate. Save an extra $100 with code CHRISTY.

Branch Smarter, Not Harder: Naming Conventions, Variables, and Bottlenecks in Storyline

• November 3, 2026 at 9:20 AM
• CE01: Storyline & Rise Pro Lab

Cohesive by Design: Generate Consistent AI Icons, Illustrations & Characters

• November 4, 2026 at 10:00 AM
• BYOD (Bring Your Own Device)

Buzz Discussion: Video & Media

• November 4, 2026 at 3:45 PM

The post Conferences, Camera Angles, Videos: ID Links 9/1/26 appeared first on Experiencing Elearning.

This year is the final year of the survey; Jane is ending it after this year. She’ll publish the results and her analysis on Monday, September 7, 2026.

Tools I use to create learning experiences for others

I use these tools for creating learning experiences for others: Claude, Flora, Twine, Articulate 360, Affinity, SnagIt, and PowerPoint.

Claude

Claude was on my top ten list in 2024, but last year I primarily used Poe instead. I like how Poe lets me test lots of different models, but it lacks some of the features that modern LLMs have. For working on projects, it’s easiest to work directly in Claude on my desktop. I still use Claude in chat format for tasks like brainstorming, but I’m also starting to use Claude Cowork for more advanced work. I’ve been using it to vibe code practice activities in training, enhance scenarios I built in Twine, and other work. Claude can speed up the process of creating handouts and participant guides based on my PowerPoint slides, and I’ve used it to help organize and build content from multiple source files.

Flora

Last year, I listed Midjourney as my primary image generation tool. I still use Midjourney for my blog header images, but for creating learning experiences for others, I primarily use Flora now. Flora is an all-in-one canvas where you can generate images and videos. It includes all of the major models for AI image and video generation in a single visual interface where you can see your work at a glance or zoom in to focus on a single element. It also includes useful tools for editing media like cropping and separating images into layers. One of my current goals is to learn how to use Flora better; I know I’m not using all of its capabilities effectively yet.

Twine

Twine is my favorite tool for creating branching scenarios. After struggling to write scenarios and make them work in linear tools, it’s amazing how much faster I can develop multiple connected paths in Twine. Being able to generate a lightweight interactive prototype is critical for branching scenarios. Plus, it’s free and open source, with an active developer community working to extend its functionality and user communities for support.

Articulate 360

Most of the elearning content I build for clients is created in either Articulate Storyline or Rise, part of the Articulate 360 suite. Storyline is fairly easy to develop with, but flexible enough to do plenty with if you’re creative. I use Rise for some development as well, depending on the project.

Articulate Review saves me tons of time collecting feedback from clients and stakeholders.

Affinity

I use Affinity nearly every week to edit images for elearning and my blog. Affinity is a great replacement for Adobe Illustrator and Photoshop at a much more affordable price.

SnagIt

I use SnagIt all the time for quick screenshots. If I need to quickly show a colleague or client how to do something, or I need to show an error for troubleshooting, SnagIt is the perfect tool.

PowerPoint

For all that it is a much maligned tool, PowerPoint is still a regular part of my toolbox. I use it to create mockups of elearning layouts and occasionally for basic image editing. As I regularly speak at conferences and online events, I also use PowerPoint to create slides for those sessions.

Personal Development: My own continuous learning tools

Raindrop

I spend time nearly every day reading and learning online. Reading a lot is great, but I also need a way to find sources again when I need them. When I read something interesting, I bookmark it so it’s easy to find and refer to later when I need it. Raindrop is the online bookmarking tool I use for my own personal knowledge management to save and find resources. I also use these saved links to curate resources for blog posts every 4-5 weeks.

WordPress

WordPress has been my tool of choice for blogging for nearly 20 years. This is the place I do most of my personal reflective learning. Frequently, I don’t know what I really think about a topic until I write about it. Writing helps me connect ideas and clarifies my understanding.

In addition, my blog is a place where I try to help others learn. When I “work out loud” and demonstrate how I accomplished something, others can read and benefit from that. When readers email me or comment about how helpful something was, I know I’m meeting that goal too. In addition, clients find me through my blog. If they read something I wrote and find it helpful, they already trust my expertise before they even contact me.

Zoom

Zoom is a tool I could put as both a personal learning tool and one for delivering learning to others. It’s the tool used in several online communities and small groups that support my continuous learning. But I also use it for working with clients and SMEs as we collaborate on learning projects, and it’s the platform I use for coaching and teaching live online sessions.

Past top ten tools posts

Interested in how this list has changed over time? While I haven’t participated all 20 years that Jane has been collecting this data, I shared my top ten tools for learning in 2007, 2008, 2009, 2011, 2014, 2021, 2022, 2024, and 2025. Not a single tool from my list in 2007 is still on the list today, although I do still use some of them for work.

Don’t forget to add your vote for your top 10 tools for learning by August 27, 2026!

The post My Top Ten Tools for Learning 2026 appeared first on Experiencing Elearning.

Compliance training is often boring

As instructional designers, we often build a lot of compliance training. All those policies and regulations that affect our organizations need to be trained. Unfortunately, compliance training is often just a content dump with a narrator reading the policy, followed by some multiple choice questions to see if learners remember what they heard 5 minutes earlier.

This training can be so boring that organizations have to offer bribes (“You’ll be entered in a drawing!”) or threats (“Failure to complete this training may result in termination”) to cajole employees into completing the courses.  In many cases, companies don’t even really seem to care if employees’ behavior changes due to the training. They just want to check a box that says, “we provided training” to cover themselves legally.

If you’re training food production workers on personal hygiene policies, you could simply list the rules. However, just telling people the rules isn’t always enough to convince people to follow them. Have you ever driven faster than the speed limit—even when you knew what the limit was? Knowing the rule isn’t always enough.

Show a worst case scenario

Instead of focusing on just the policies and regulation in abstract, engaging compliance training focuses on when employees need to follow those policies and why they matter.

To show the “why,” start with an example of what can happen if they don’t follow the policies. In the case of food safety, it’s easy to imagine a worst case scenario with a nationwide food recall. In fact, almost 15 years ago, I built a mockup of a newspaper front page showing a headline about a “Nationwide Food Recall.” While now a news website or social media mockup looks more current, the same example warning feels sadly relevant in 2026.

(As a side note, I used to spend so much time manually building fake examples like this in Photoshop for elearning. This took me a few minutes and 3 iterations with AI. It’s much easier to generate these supporting visuals now!)

What could other worst case scenarios be?

• Ethics: A scandal that causes a company’s stock to drop or legal consequences
• Safety: An injury resulting in missed work, lost income, and a long recovery
• Security: A breach that results in data loss and all the ramifications from that

For any compliance training topic, there’s a consequence if the policy isn’t followed. That consequence can be your opening scenario that draws your learners into the story and gets them emotionally involved.

Compliance training with interactive video

A classic example of this technique is The Lab: Avoiding Research Misconduct. This is an interactive video you can play from the perspective of different characters. The story starts with “a very bad day,” where news reporters are interviewing a supervisor about misconduct. Right from the start, you see the consequences of poor decisions. As a learner, you get the opportunity to go back in time to see how those decisions were made and try to avert disaster.

You might not have the resources to hire actors and film scenarios in multiple locations like this, but you could still provide this kind of setup. It’s easy to mock up a newspaper headline like the one above or a fake website screenshot with trending news.

What if your worst case scenario would be internal, like an employee losing sales or being placed on a performance improvement plan? In that case, even a photo of an unhappy manager with voice over or text explaining the consequences can be effective.

Why the worst case scenario works

The worst case scenario gets learners attention because it shows them why the policy or regulation matters. Instead of the compliance training being just a box to check off, it’s teaching them how to be a hero and prevent a disaster.

It’s important to show these consequences and not just tell them. Simply telling people, “Failure to comply with personal hygiene policies could result in a food recall,” doesn’t have the same emotional impact as showing them a fake headline about a recall for contamination.

Show the “Why” and the “When”

Starting with a worst case scenario is the “why” for a policy. For tips on how to focus on the “when” policies apply, check out my post Creating Motivating Compliance Training. That post describes the difference between a “push” training where you give all the info to learners when you decide and a “pull” training where learners get the policy information they need, when they need it.

Originally published 3/10/2016. Updated 7/6/2020, 8/13/2026.

---

Upcoming events

Learning Architecture: From Content to Context. October 21. Learning Planet Institute.

DevLearn

Register for DevLearn by October 2 for the Advanced Rate. Save an extra $100 with code CHRISTY.

Branch Smarter, Not Harder: Naming Conventions, Variables, and Bottlenecks in Storyline

• November 3, 2026 at 9:20 AM
• CE01: Storyline & Rise Pro Lab

Cohesive by Design: Generate Consistent AI Icons, Illustrations & Characters

• November 4, 2026 at 10:00 AM
• BYOD (Bring Your Own Device)

Buzz Discussion: Video & Media

• November 4, 2026 at 3:45 PM

The post Make Learners Care about Compliance Training appeared first on Experiencing Elearning.

Watch the interview

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

Listen to the podcast

You can also listen to the podcast on Spotify. (We didn’t have any slides or visuals, so you’re not missing anything if you just listen.)

More podcasts

Check out my collection of over 25 podcast interviews on scenarios, ID careers, AI, and more.

---

Upcoming events

Learning Architecture: From Content to Context. October 21. Learning Planet Institute.

DevLearn

Register for DevLearn by October 2 for the Advanced Rate. Save an extra $100 with code CHRISTY.

Branch Smarter, Not Harder: Naming Conventions, Variables, and Bottlenecks in Storyline

• November 3, 2026 at 9:20 AM
• CE01: Storyline & Rise Pro Lab

Cohesive by Design: Generate Consistent AI Icons, Illustrations & Characters

• November 4, 2026 at 10:00 AM
• BYOD (Bring Your Own Device)

Buzz Discussion: Video & Media

• November 4, 2026 at 3:45 PM

The post Conference Speaking Tips for L&D Professionals appeared first on Experiencing Elearning.