Overview
Video is Leonardo.Ai's dedicated animation tool, capable of breathing life into your generated or uploaded images or generating a video from a prompt.
Our platform now offers the Motion 2.0 model on paid plans, letting you generate 5 second clips with smarter motion from an image or simple text prompt. Plus, enjoy boosted frame rates for even smoother results, exclusive to Leonardo.
About Video
Bring any image to life: Animate generated or uploaded images in just a click
Enhanced motion control: Choose the amount of movement your animations have, or even specify the desired motion of your video with a prompt (only with Motion 2.0)
Text to video capability: Enter even a simple prompt and watch your image come to life (only with Motion 2.0)
Create with Privacy: Toggle Private Mode ON to keep the output hidden from the Community Feed or your Team (available on a paid plan only)
Whether you're a content creator, a filmmaker creating storyboards, visualizing pre-production assets, or just looking to express your imagination, Leonardo.Ai's Video features save valuable time and resources typically spent on video production and animation.
How to use Video
Videos can be created in the Video tool modal, which will pop up when clicking the Video icon on an image from your Library, AI Creation tool, the Community Feed or the Team Feed
Videos can also be generated via the Video tab in the AI Creation tool.
The final result will be displayed in your Library as a new generation.
(Note, improvements are coming soon for a more seamless Video creation experience!)
Generating a Video with Motion 1.0.
Motion 1.0 is accessible via the dropdown.
In your Library or the Community Feed, select an generation and click on the Image2Video button in the Image Details popup
Alternatively in the Image Generation page, hover over an desired image and click on the button.
In the Video modal, click on the Model dropdown and select Motion 1.0. If you would like to upload your own image, click on the Source Image to open the image selection popup.
Adjust the Movement Strength slider to control how much dynamism gets added to the end result.
Generate
Generating a Video with Motion 2.0, three ways.
Motion 2.0 is the new default video model that lets you direct your desired animation using the prompt bar.
Using Motion 2.0's Image to video capabilities via the Video tool modal (Accessible by clicking Image2Video in the image details popup of any image)
In your Library or the Community Feed, click on an generation.
Alternatively in Image Creation, hover over an image and click the
button.
If you would like to upload your own image, click on the Source Image to open the image selection popup.
Describe the image and your desired motion in the prompt bar to direct the animation
Generate
Alternatively:
In the AI Creation tool, select the Video tab.
Click on the button on the left side of the prompt bar and select Add Start Frame
Upload your image
Enter a prompt to describe the image and motion
Generate
Options:
Toggle Smooth Video ON for smoother results with boosted frame rate (exclusive to Leonardo)
Toggle Prompt Enhance ON to improve outputs
Toggle Private Mode ON to keep the output hidden from the Community Feed or your Team Feed
Using Motion 2.0's Text-to-video capabilities via the Video tab in the AI Creation tool
Select the Video tab
Enter your prompt
Generate
Here's how to access Video creation from around the platform:
For Image to Video
From the AI Creation tool
Hover over the desired image and click the button.
From the Community Feed and your Library
Select the desired image and click Image2Video.
For Text to Video
On the home page
Click on Video which can be found in the left sidebar or the toolbar in the middle top.
In the AI Creation tool
Navigate to AI Creation and switch to Video (located directly below the prompt bar)
Where to find your Video
The final result will be displayed in your Library as a new generation with an icon. You make click on the Video tab found on the top right to view all Video generations.
Prompting for Motion 2.0
Prompt Structure
It is important to note that the prompt structures you are used to for creating images would not be the same for video. The prompt structure for video can be something like the following:
Description of the scene (visual terms) + Description of the actions (such as what the characters do) + Additional details (such as camera movements).
Camera Movement
You may describe how the camera should behave in the prompt including the speed at which it moves, though the effects may not be consistent or 100% effective:
Dolly in / out - Moves in / out: The camera moves in or out of the scene.
Pull Back: The camera pulls (dollys) back.
Zoom in / out: The camera zooms in or out (This is somewhat different to a dolly)
Pan left / right: The camera rotates sideways depending on direction stated. (Note: the model may not always adhere to the direction stated)
Orbit around: The camera moves around an point.
Tilt: Tilts camera either up or down. (This does not work in most cases)
Tracking shot: To use this, it is essential to state what the camera should follow in the shot. (eg, The camera follows the woman in a slow tracking shot
)
Pull Focus / Focus Racking: It may be possible to shift the focus from one subject to another. To do this, describe how the focus should shift between the subjects in the prompt. It can be described as such: focus pull, the camera shifts focus on a man in the foreground after looking at a woman in the background.
Negative Prompting
Negative prompts can be inputted for Text to Video by enabling the Negative Prompt toggle found in Advanced Settings. This is useful for shifting the aesthetics and movements away from certain biases.
To use this, simply enter what you do not want to see. Avoid entering negatives such as no or without as this results in double negatives. (eg. No 3D render
should be entered as just 3D render
)
Frequently Asked Questions
Is Video a premium feature?
Is Video a premium feature?
Yes, Video creation tools are only available on a paid plan.
Can I still access the Motion feature?
Can I still access the Motion feature?
Yes, you can still access the original model used by Motion. To do so, open the Video modal and switch the model to Motion 1.0.
What happened to the Motion feature?
What happened to the Motion feature?
Motion is now part of Video. The original Motion feature used a model now known as Motion 1.0. To access the classic Motion model, open the Video modal and switch the model to the older Motion 1.0.
How many tokens does it cost to use Video?
How many tokens does it cost to use Video?
SVD: 25 Tokens
Motion 2.0: 250 Tokens
Why does Motion 2.0 cost more tokens?
Why does Motion 2.0 cost more tokens?
Motion 2.0 is an much more advanced model that requires significantly more GPU power to generate videos, therefore, costing more to generate with.
Is Relaxed Generation available for Video?
Is Relaxed Generation available for Video?
Yes. If you are on an Maestro Unlimited subscription, Relaxed Generation is available for Video, allowing you to generate unlimited videos.
How does unlimited video generation for Maestro users work?
How does unlimited video generation for Maestro users work?
On the Maestro Unlimited plan, you will be placed on the Relaxed Generations queue once you run out of tokens. This will allow you to continue generating videos at no extra cost.
What file formats are supported for uploading to Video?
What file formats are supported for uploading to Video?
The supported file formats are: PNG, JPEG/JPG and WEBP (up to 5MB)
How do I upload my own image to generate a Video?
How do I upload my own image to generate a Video?
To upload your own image to generate a Video, click on an image either in the Library, Community Feed or Image Creation feed to open the image details modal. Then click on the Image2Video button.
In the following Video modal, click on the Source Image to open the image selection modal which will allow you to upload the image.
What file formats are available for downloading?
What file formats are available for downloading?
Video generations are available only in .mp4 format.
Will the output resolution be the same as my original image?
Will the output resolution be the same as my original image?
Video will generate a smaller resolution video in comparison to the original resolution, if you have selected an high resolution image to animate. Aspect ratio will be maintained.
Motion 1.0 outputs are based on the original image aspect ratio but with a smaller resolution (With approximately a max of 1088px on one side). Video resolutions will vary based on image aspect ratio and size.
Motion 2.0 outputs are 480p resolution (720p coming soon!). Text to Video outputs are strictly in either 16:9 or 9:6 aspect ratio. Aspect ratio for Image to Video outputs are dependent on the original image.
What are the frame rates for Video generations?
What are the frame rates for Video generations?
For outputs generated with Motion 1.0: 24 FPS
For outputs generated with Motion 2.0: 16 FPS (Base) 32 FPS (Smooth Video enabled)
How do I remove the watermark on my video or motion generations?
How do I remove the watermark on my video or motion generations?
To generate a Video without a watermark, consider upgrading to a paid plan.
Questions about Motion 2.0
What is the Motion 2.0 model, and how does it improve the Video feature?
Motion 2.0 includes prompting along with decent prompt adherence, giving users greater control over the animation of the camera and various elements in the video. Motion 2.0 also brings about better stability in animating elements in the scene along with more realistic physics.
What are the key differences between the Motion 1.0 model and Motion 2.0?
Unlike Motion 1.0 which only offers Image to Video capability. Motion 2.0 offers both Image to Video capability with prompting and also Text to Video, allowing you to generate a video purely from prompting if desired.
Motion 2.0 also offers more versatility, being able to generate more dynamic and smoother animations and camera movements than Motion 1.0 while maintaining consistency of elements and also bring much better control through prompting, allowing users to do advanced effects such as shifting the camera focus from one subject to another in a scene.
Will Motion 2.0 enhance the smoothness of videos
Yes, toggle Smooth Video ON to generate much smoother video compared to just the base outputs from Motion 2.0 - thanks to Leonardo's boosted frame rates to make this possible!
How does Motion 2.0 handle complex animations, like dynamic lighting and physics?
Motion 2.0 has smarter motion and understanding of space, meaning things should move as you expect in real life and lights should better interact with the elements in the scene.
Can I adjust motion parameters like speed, transitions, or style?
You can direct style, transitions and determine speed, movements and camera actions through prompting when generating with Motion 2.0.
Are there any limitations or known issues with Motion 2.0 in Video?
Motion 2.0 may not accurately represent the motion of things as in reality and may also be inconsistent when showing an hidden angle of an element (notably for Image to Video). This is notable especially in action scenes.
Will older projects made with the previous model (Motion 1.0) still be compatible?
Yes, older projects will still be viewable in your Library.
Can I choose between Motion 2.0 and the older model, or is the upgrade automatic?
Yes, while Motion 2.0 is the default video generation model for premium users, the previously used Motion 1.0 is available via the dropdown.
Is Motion 2.0 available for free users, or is it a premium feature?
Motion 2.0 is available on paid plans only
Will this upgrade increase token usage for Video?
Yes, using Motion 2.0 costs 250 tokens due to the much higher computational costs (Leonardo offers the 14B model), in comparison to the 25 tokens used by Motion 1.0 generations.
Feedback
Video is getting better at Leonardo, and as such, we would love to know if you run into any issues or have any other general thoughts about these tools.
Please feel free to leave your feedback here.