AI Image to Video Experiments with Hedra

One of the overall uses for AI is converting from one modality to another: text to image, image to text, image to video, audio to text, etc. I’ve been experimenting with a tool called Hedra for converting images into short videos with audio. While these videos are fairly clearly AI-generated, I can see the potential here for working with scenarios.

Note: The examples below were mostly generated in October 2024. To see updated examples from July 2025, check out my most recent post on Hedra Character Video Generation.

Sample scenario dialogue based on a Midjourney image

For this sample, I generated a character image in Midjourney. I added a bit of script from my project management scenario. Hedra uses ElevenLabs for audio, so I picked one of the provided voices. On the free plan, there aren’t many choices, but the paid plan has more options for voices.

Then, I used Hedra to turn that Midjourney image into a video. Hedra animates from the static image, syncing the movements to the provided audio. It does hit the uncanny valley, and you’re not going to mistake this for actual video. You can see the results here. If the video isn’t embedded below, you can watch the sample on YouTube.

Hedra character image example

I created another sample by generating the character image directly in Hedra. To be honest, I wasn’t quite as happy with this one. I think Hedra’s image generation does better with illustrated and stylized characters than with fully photorealistic characters. I’ve seen some great samples in video game and anime styles. This is OK, but I don’t like the character as much. I see more artifacts around the edge of the character. You can see this example on YouTube if it’s not embedded below.

Same audio, different image

I remixed the video in Hedra with a different image. This time, I used a character image I had created in Midjourney rather than in Hedra. The audio is the same though. This is one of the nice features in Hedra–it’s easy to update a video by swapping out a new image or different audio.

Older experiment with Hedra: Frustrated customer example

For comparison, here’s the first sample I created when I first started experimenting with Hedra in July. For something I created in 15 minutes, it’s not bad overall. You can see the improvements Hedra has made in the last few months though, especially around blinking. This is a snippet of dialogue with a frustrated customer from my customer service chat simulation.

My process for this sample was similar to the first sample above. I started by generating an image in Midjourney. Then, I grabbed some text out of a customer service branching scenario I wrote a while ago. I specifically wanted some dialogue where the character shows frustration, since that emotion is often hard for AI tools.

I originally generated the audio directly in Hedra, but I decided I wasn’t happy with it. Therefore, I swapped it out with a different Elevenlabs voice and uploaded that. If the video isn’t embedded below, you can watch it on YouTube instead.

Uses and limitations

Hedra is designed for close up videos of a single character talking while looking at the camera. It won’t work for anything where you need people moving around or interacting with props. If you want to create a conversation between two characters, you need to create videos of each character separately and then stitch them together.

I probably wouldn’t use this with any of my client projects right now, but I can see the potential for using it with scenarios in the future. It would be easy enough to create a set of videos showing the dialogue for a branching scenario and then string them together in Storyline or another tool to add the interactivity.

This might be an interesting option for elearning developers and instructional designers looking for something different in their portfolios. I think the output would be sufficient for a portfolio sample.

On a free plan, you’re limited to 300 words per video and a max video length of one minute. The free plan is also watermarked and can’t be used for commercial purposes. The paid plans increase the video length, max video generation per day, plus allow commercial use. The Basic plan is $10/month, which makes it a fairly affordable option.

Have you tried Hedra?

Have you tried Hedra? As learning and development professionals, I think it’s smart to spend time regularly experimenting with AI tools. Even if you aren’t going to immediately use it in your work, there’s value in understanding what’s available now and what will be improving in the future.

Combined video

Because the videos above are all very short, they may not appear correctly. If you don’t see videos above, you can try the combined video with all of the samples below or watch on YouTube.

---

Upcoming events

Instructional Design Uncovered: A Community Conversation with Instructional Designers. September 10. ATD Research Triangle Area

Creating High-Quality AI Media: Prompting, Scripts, and Consistency. October 8. Register for the ATD AI Intensive.

Creative Solutions with Twine: Design, Streamline, and Refine Branching Scenarios. October 14. ATD Dallas Learning Technology SIG

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