9 Free AI Image-To-Video Tools: Tested
I feed the same two images to nine different AI video sites to see what happens.
Folks…this was inevitable.
In October last year, I looked at text-to-video sites.
A few weeks later, I tested text-to-image models.
Now, we’ve come full circle to the logical conclusion of this visual AI trilogy: image-to-video tools.
Lots of new AI video platforms have popped up in the meantime.
Most are free to use and offer image-to-video functionality.
So today, I’ll put nine of them to the test using the same starting images.
Let’s roll!
🎬 The contestants
Here are the nine AI video tools I’ll be testing.
(I highlight returning vs. new participants in brackets.)
Genmo (Returning)
Haiper AI (New)
Kling AI (New)
Luma Dream Machine (New)
Morph Studio (Returning)
Pika Labs (Returning)
PixVerse (New)
Runway Gen-3 Alpha Turbo (Returning but with a new model)
Vidu AI (New)
As you can see, a few familiar names are making a comeback along with plenty of new challengers.
🧪 The test
To make the comparison fair, they’ll all be animating the same two starting images rendered by Midjourney.
First, this steampunk violinist:
This image provides plenty of room to animate motion while focusing on finer details.
The prompt given to each tool will be this:
Steampunk robot violinist performing on stage
Our second image is this funky locomotive:
This will tell us how well the tools deal with illustrated images and changing scenery.
The accompanying text prompt is:
Train traveling through a surreal and whimsical landscape
Many of the tested tools offer advanced features like camera controls, motion brush, character reference, and so on.
For this comparison, I’ll avoid advanced options and stick to the default settings. This should keep a level playing field and make the starting point as similar as possible.
📽️ The results
Let’s see what each tool came up with.
1. Genmo
I featured Genmo in October last year.
Since then, the site has introduced many new features, including camera motion, visual FX presets, control sliders, and more.
Let’s go ahead and upload our images and text prompts, like so:
Time to see the results.
Steampunk violinist:
That’s…something.
It appears that Genmo doesn’t directly use our image as the starting frame. Instead, it uses the picture as vague inspiration to create a trippy and surreal clip.
Let’s see the next one.
Surreal locomotive:
You’d think that this image would be a shoo-in for Genmo’s already trippy output.
But while I love the steam animation, the rest of the video is quite janky.
Pretty cool if you’re after an artistic vibe.
Not so cool if you want to add realistic motion to an image.
Genmo at a glance:
Advanced features: Camera motion control, visual effects presets, motion intensity settings, looping video creation.
Video duration: 2, 4, or 6 seconds.
Free plan limitations: Watermark and fewer daily credits (100 vs. 1000).
Where to try: www.genmo.ai
2. Haiper AI
I haven’t tried Haiper before, so I have no expectations at this stage.
Let’s throw our images and prompts into the tool:
Here are the outcomes.
Steampunk violinist:
A surprisingly solid start.
Sadly, after two seconds, our violinist kind of spaces out and stares into the void instead of continuing to play.
But I like that Haiper has managed to keep the look and clothing consistent.
Not too bad.
Surreal locomotive:
Okay, so Haiper just isn’t a fan of movement at all.
Our locomotive is content to just sit there and watch the clouds go by while half-spinning some of its wheels.
Bliss.
Haiper AI at a glance:
Advanced features: Video-to-video, “extend” button, transition between keyframes (separate images), “high-fidelity” vs. “enhanced motion” modes.
Video duration: 2, 4, or 8 seconds.
Free plan limitations: 5 creations per day, 300 one-off credits, fewer concurrent creations, watermark, no commercial use, no private creations.
Where to try: haiper.ai
3. Kling AI
I’ve already used Kling as one of the three tools in the “teaser trailer” post as well as for the Sunday Bonus on making characters enter a scene.
I have high expectations for Kling, so let’s give it a go:
Here are the results.
Steampunk violinist:
Excellent!
The bow and even the slight finger movements look quite believable.
Even though this is just the default “standard mode,” the video quality is very high.
I’d love for the face to be animated as well, but that wasn’t part of my text prompt.
Definitely our best result thus far.
Surreal locomotive:
We finally have both the train moving and the steam pumping!
Sadly, the wheels decided that turning was optional. Also, the scenery is a bit too static.
But a decent result overall.
Kling AI at a glance:
Advanced features: End frame, creativity vs. relevance slider, standard vs. professional mode, camera controls, negative prompt (remove unwanted items).
Video duration: 5 or 10 seconds.
Free plan limitations: Watermark, fewer daily credits, no professional mode, limited camera controls, longer wait times.
Where to try: klingai.com
4. Luma Dream Machine
Luma was yet another one of my teaser trailer and Sunday Bonus tools.
What I’ve noticed is that Luma doesn’t do so well when trying to make characters’ limbs move convincingly, especially when walking.
But let’s see how it does with our close-up shot.
Here are the videos.
Steampunk violinist:
A decent generation, but the fingers of the bow hand end up doing something wonky toward the end. Apart from that, the video quality itself is excellent.
Surreal locomotive:
Damnit, Luma!
You were so close!
Traveling train? Check. Turning wheels? Check. You even nailed the subtle camera pan.
But why did our steam turn into a static cloud?
I guess Luma failed to recognize the steam as belonging to the engine.
Ah well. It’s still a pretty good result.
Luma Dream Machine at a glance:
Advanced features: End frame, looping videos, “enhance prompt” button, camera controls (via text directions), “extend video” feature.
Video duration: 5 seconds (with optional extensions).
Free plan limitations: No commercial use, watermark, limited credits (30 generations per month), low priority queue.
Where to try: lumalabs.ai/dream-machine
5. Morph Studio
Morph is another returning participant from my text-to-video comparison.
It now also offers lots of new bells and whistles like video style transfer, camera controls, etc.
Let’s add our image + text combos:
Here we go.
Steampunk violinist:
Oh.
That’s not good at all.
The violin breaks and repairs itself, I don’t know what the robot’s hands are doing, and it’s generally less of a fluid video than it is a stop-motion nightmare.
Surreal locomotive:
Choo-choo!
That steam is working really hard to distract us from the fact that the train itself isn’t going anywhere.
It’s okay, steam. You did your best.
Morph Studio at a glance:
Advanced features: Video style transfer, motion brush, camera controls, motion intensity controls, lip sync, and video background remover.
Video duration: 2 to 5 seconds.
Free plan limitations: Fewer credits, lower resolution (720p vs. 1080p), low priority queue, no commercial use.
Where to try: www.morphstudio.com
6. Pika Labs
Another returning veteran.
Let’s see if Pika can redeem itself after the subpar performance in the text-to-video challenge.
Here we go.
Steampunk violinist:
Aaaaaaah!
Is that robot playing the violin or trying to hypnotize me into revealing the password to override its safety protocols? (It’s “Password1234,” but don’t tell him!)
This was disappointing.
I generally have high hopes for Pika, but it has now failed me twice.
Surreal locomotive:
Why do you do this to me, Pika?
That’s three for three.
You’ve hurt me for the last time!
Pika Labs at a glance:
Advanced features: Lip sync, sound effects, style presets, camera motions, canvas extension, motion intensity sliders, and duration extension.
Video duration: 3 seconds.
Free limitations: No upscaling, lip sync costs credits, watermark, no video extension.
Where to try: pika.art
7. PixVerse
Another new entrant to check out!
Let’s give it a shot:
And the videos are in.
Steampunk violinist:
Oh wow.
That’s genuinely better than I’d expected.
Despite a bit of warping, the movements are believable and consistent, even though it feels like a slow-motion clip. The quality is slightly behind Kling but very decent.
Well played, PixVerse, well played!
Surreal locomotive:
“Wwweeeeeeeee!”
Noooo! Wrong way, train! Where are you going?!
That’s a huge shame, seeing how PixVerse animated the clouds and the moon nicely.
Love the motion, hate that it’s heading in a completely wrong direction.
PixVerse at a glance:
Advanced features: Character to video, magic brush, normal vs. performance motion mode, camera movement controls, seeds.
Video duration: 5 or 10 seconds.
Free plan limitations: Limited daily credits (more can be purchased).
Where to try: pixverse.ai
8. Runway Gen-3 Alpha Turbo
I’ve tested Runway back when it was Gen-2.
The full-fledged Gen-3 Alpha model is currently only available to paid subscribers.
But Runway recently released a pure image-to-video version called Gen-3 Alpha Turbo, which lets you use free credits.
Off we go:
Here are the videos.
Steampunk violinist:
The resolution and quality of the video are perhaps the best of the bunch.
But good luck making any music without the bow touching the strings, robot!
I do like the finger movements and the overall motion.
I just wish Runway knew to place the bow closer to the violin.
Surreal locomotive:
Yes!
That’s exactly what I had in mind: The camera pans to reveal more scenery as the train passes through it.
Too bad that Runway—just like Luma—failed to assign the steam to the train and instead invented its own.
But to be fair, our starting image doesn’t use conventional colors, so it’s an easy mistake to make.
Runway Gen-3 Alpha Turbo at a glance:
Advanced features: End frame. (Not many additional features for Gen-3 Alpha Turbo specifically.)
Video duration: 5 or 10 seconds.
Free plan limitations: One-off credits, watermark, no upscaling, 720p resolution.
Where to try: runwayml.com
9. Vidu AI
Our last new entrant.
On to add our images and texts:
And now let’s take a peek.
Steampunk violinist:
Another wow.
While it’s not the highest-fidelity video on the list, I think it has perhaps the most realistic and lifelike motions of all.
I accidentally ran the prompt twice, and the second video was equally solid:
Color me impressed, Vidu.
I didn’t know what to expect, but you did really well.
Surreal locomotive:
If only this clip was in reverse, it’d be practically flawless.
Alas, Vidu suffers the same fate as PixVerse and launches our locomotive backward.
Still, Vidu’s ability to animate motion and keep objects consistent was a positive surprise for me during this test.
Vidu at a glance:
Advanced features: Reference-to-video feature, “enhance prompt” option, speed vs. quality selection.
Video duration: 4 or 8 seconds.
Free plan limitations: No 8-second option, no “quality” option, limited credits, no commercial use, only one concurrent task, low-priority generations.
Where to try: www.vidu.studio
🏆 The verdict
First off, take everything below with a grain of salt.
After all, I’m basing my conclusions on just two starting images and simple text prompts. Some models may very well do better if you use their advanced features and add detailed descriptions of intended motion.
Having said that, here are the tiers based on today’s test.
🥇 Tier #1 (Solid frontrunners): Kling, Luma, and Runway
No huge shock here.
These are the bigger names in this space, and they mostly live up to their reputation.
They didn’t make any egregious errors in our test.1
While none of them are flawless, they do tend to have reliable output with coherent motion and also offer the highest-quality videos.
🥈 Tier #2 (Positive surprises): PixVerse and Vidu
These two really impressed me, especially with their realistic animation of our steampunk robot image.
I’m even tempted to give Vidu the “Best-Animated Robot” award.
On the downside, the quality and resolution of their videos lag behind our frontrunners and they both messed up the steam train’s motion.
Still, I’d keep a close eye on these two!
🥉 Tier #3 (Just okay): Genmo and Haiper AI
I like Haiper’s output quality, but it struggled to animate our scenes well enough today.
As for Genmo, the only thing keeping it above Tier #4 is the fact that it doesn’t attempt to continue a video from a starting frame like the other contestants. Instead, it reinterprets the image in a somewhat trippy way. So you can treat it as a sort of artistic alternative.
👎 Tier #4 (Disappointments): Morph Studio and Pika Labs
Morph Studio had perhaps the worst robot animation and a completely static train.
And Pika is consistently my biggest disappointment. Back in the day, I saw Pika as a fresh and promising challenger to Runway’s early dominance. But no matter what challenge I throw at it, Pika comes up short every time.
Maybe it’s just me, but I have yet to extract acceptable outputs out of Pika.
🫵 Over to you…
What do you think of these tools and my verdict? Do you have any clear favorites? Have I overlooked any obvious free sites in my comparison?
If you’ve worked with any AI video tools and have tips to share, I’d love to hear them.
Leave a comment or shoot me an email at whytryai@substack.com.
Except for maybe the “hover-bow,” ahem, Runway.
What a fantastic review! Good stuff.
What a fantastic review!
It's surprising that some lesser-known tools outperformed big names like Pika Labs. Not sure image to video AI tools are ready to replace traditional animation yet, but these are getting pretty good.