Introduction
Gen-3 Alpha is the first of upcoming models that offer improvement in fidelity, consistency, motion, and speed over previous generations of models.
Gen-3 Alpha Turbo is a faster and more credit-efficient model in the Gen-3 Alpha family that generates faster at a lower cost. The Turbo model is available on all plan levels.
Keyframes allow you to configure both the starting and ending frames to create smooth transitions between them in a Gen-3 Alpha Turbo generation.
This article outlines how to use Keyframes on Gen-3 Alpha Turbo, prompting tips, the available settings, and more.
Spec Information
Spec | Gen-3 Alpha Turbo |
Cost | 5 credits per second |
Supported durations | 5 seconds 10 seconds |
Explore Mode on Unlimited Plans | Yes |
Platform availability | Web |
Maximum image size | 64mb |
Maximum Keyframe input | 2 images (First and Last frame) |
Output resolution | 1280x768 768x1280 |
Frame rate (FPS) | 24fps |
Step 1 – Selecting the Input Keyframes
Begin by navigating to Generative Video in your Dashboard.
From here, make sure the Gen-3 Alpha Turbo model is selected from the top left corner dropdown. You’ll see the keyframe selector available on models that support this functionality:
Drag and drop a new image or select an existing image from your Assets to configure your First Keyframe. Click Last and upload another image to add the final Keyframe.
You can swap the keyframe placement by select the ⇆ icon between the first and last frames.
When choosing Keyframe images, keep in mind that the ability to receive the desired transition will be highly dependent on the complexity of your input images:
- Two images that share a similar subject, scene, and style will offer more consistent, natural, and smooth results.
- Two images that greatly vary in subject, scene, or style may create more experimental or unexpected results.
With your images uploaded, you’re now ready to draft your prompt.
Step 2 – Drafting the Prompt
We strongly recommend including a text prompt before generating.
You can start Keyframe generations without a prompt, but including a clear description that outlines the desired style of motion will offer more controllability and set your generation up for success.
Try to keep your prompt focused on the motion needed to take your video from the first frame to the last frame.
Below are some examples of first and last frames, the prompt used, and their respective output:
First frame | Last frame | Prompt | Result |
individual blobs of liquid dynamically collide and fuse together to form a single goo creature. dynamic fluid, bouncy, reactive motion. the creature looks around. melting liquid. motion-reactive fluid | |||
leaves grow on the tree | |||
A jellyfish made of cloth floating inside a room |
Step 3 – Generating the Video
After uploading your keyframes and drafting your prompt, you’re now ready to generate your video.
Select the desired duration from the dropdown menu next to the Generate button.
When choosing a duration, it may be helpful to once again consider the amount of difference between the two frames.
More complex transitions, such as cases where the Last frame is completely different from the First frame, may benefit from the longer 10s duration. This would give the generation more time to smoothly transition between the two inputs.
Alternatively, choosing a 5s duration for completely different keyframes may result in more abrupt changes.
Click the Generate button once you feel content with your chosen settings.
Your generations will be scrollable through your session as you continue to generate. You can also access completed videos in your Assets, where they will save to the Generative Video folder by default.