Image to Video is a powerful AI-driven feature that automatically transforms your existing studio images into engaging motion content. It creates short videos from your retouched stills, eliminating the need for costly video shoots while preserving the same quality, color grading, and styling as your original images.
➕ Add-On: Image to Video is an add-on feature. If you're interested in having it enabled for your studio, please reach out to your Customer Success Manager for more information.
Enable Connector
Before you can use Image to Video, ensure a supported connector is enabled for your Studio. This can be verified in Studio Settings under Integrations → Connectors.
For a full overview of Cloud Automation connectors and their specific subfunctions, please see our dedicated article on the subject here. Currently, the following Connectors support Image to Video.
 Creative Force AI |  Fal AI |  Gemini |  Kling AI
|
Default AI Models
Once the AI connector is enabled, you can set up the standard AI model for your studio.
In "Creative Force AI" connector settings, navigate to the Image to Video tab → then select your preferred AI model from the dropdown menu between multiple powerful AI models: Kling 2.5, Kling 3.0, Google’s Veo 3.1 (Multi-Image), and Google’s Veo 3.1 (Single-Image)
The settings available in the connector configuration and at the Workflow level will automatically adjust based on your AI model selection:
Model | Description | Supported Format | Supported Durations |
Kling 2.5 | Optimized for single-image input. | Uses the aspect ratio of the primary image. | Currently supports 10 or 5-second video outputs. |
Kling 3 | Optimized for multi-image input (up to 4 assets).
Excellent for 360º video outputs.
Allows segmented (multi-shot) videos, rather than one continuous view. |
Uses the aspect ratio of the primary image. |
Supports video lengths between 3 and 15 seconds. |
Veo 3.1 - Multiple Images) | Optimized for fast video generation.
Supports multiple image inputs (up to 3 assets).
Excellent for 360º video outputs. |
Currently supports 16:9 and 9:16 aspect ratios. | Currently defaults to 8 seconds only.
4 and 6-second outputs coming soon. |
Veo 3.1 - Single Image) | Optimized for fast video generation.
Supports single image input.
Higher product and model accuracy than Veo 3.1 - Multiple Images. |
Currently supports 16:9 and 9:16 aspect ratios. |
Currently supports 8, 6, or 4-second video outputs. |
Prompt Configuration
After the standard AI model selection, you can configure the available settings at the studio level accordingly and define how the videos are generated:
Setting | Function |
Prompt | This serves as a creative guide for the AI when generating the video from your image. Since this is configured at the studio level, we recommend keeping the prompt general.
You’ll have the option to refine it further for each specific Workflow if needed. |
Format | You can choose from three aspect ratios: 1:1 (square), 16:9 (landscape), or 9:16 (portrait), depending on your intended use case and the AI model selected. |
Duration | The video length can be set to a number of pre-determined lengths, depending on the AI model selected. |
Resolution | Choose the desired resolution for the output video. |
Output Quantity | Designate the number of video assets that should result from each conversion. |
Negative Prompt | Determine any specific callouts for the model to avoid.
e.g., glitches, blur, bad proportions. |
CFG Scale | Set a 0 to 1 scale (in .1 or .5 increments, depending on the model) for how closely the model should follow your directions, 0 being the most abstract, and 1 being the most absolute.
This allows the user to designate a relative range of creative liberties that can be taken to produce the output. |
📝 Note: The above studio-level settings can be overridden at the Workflow level by enabling the 'Allow Runtime Override' option under each respective setting.
Image to Video Tester
Using the Image to Video Tester function, you can now pre-validate prompts and test potential outputs before publishing them to your live Workflow builds.
🛠️ Permissions: To use the tester, users need to be in a role with 'View' or 'Edit' permissions for Connectors.
In order to switch between different AI models within the tester, the user will need 'Edit' Permissions.
To test your Image to Video setup, select "Tester" at the bottom of the Connector menu under the "Image to Video" tab:
In the next screen, you will see configuration options similar to those in the previous menu, including Prompt, Format, Duration, and Output Quantity.
📝 Note: Using the Image to Video Tester is free, but we will share an expected credit cost in the configuration menu to estimate potential costs during production.
After selecting the desired output options, select a pre-configured prompt from the Prompt Template Library, or write your own in the Prompt text box.
To assign an asset, select the area under 'First Frame.' From here, an additional menu will appear, which allows you to upload an asset from your hard drive or select a pre-existing asset from an in-progress or completed Production.
When using assets from an existing Production, and if using a model that supports multiple asset inputs, up to 4 assets can be selected in the menu.
After selecting all the required configuration options and uploading your asset, select 'Generate' and the system will begin to process your request.
⚠️ Important: Depending on the request, processing may take several minutes to complete.
While your request is processing, the screen can be safely closed via the "Return to Latest Settings' button, and other edits can be made to the prompt configuration.
This way, multiple image-to-video generation tests can be executed at once.
All executed prompts can be accessed by navigating the furthest right-hand menu column under 'Video Tests.'
Supported File Types
While the AI models that power Image to Video only accept specific file types and sizes, these limitations won't impact you. If the images for products using Image to Video don't meet the AI model specs, we will use the full-resolution preview JPEG that is created for all assets uploaded to Creative Force instead.
This means you can generate videos from any file format you work with - whether it's a PSD, TIFF, or other format - without worrying about compatibility issues. Creative Force automatically handles the conversion behind the scenes.
Workflow Integration
When working with Image to Video powered connectors, it is recommended to use a Generative Workflow to support the outputs. To use a Cloud Automation connector in your Productions, add a Cloud Automation step to your Workflow and select the specific connector from the connector grid.
With the connector selected, select 'Image to Video' as the sub-function in the next slide-out menu. You can further customize the Image to Video AI settings independently from the general studio settings. To do this, simply click on your Image to Video step, then click the settings icon.
Here, you'll find the same settings defined at the studio level, which you can adjust to be specific to your Workflow.
After the Image to Video step, you can also add a Cloud Automation QC step to review the AI-generated video and either accept or reject it.
Cloud QC
If a Cloud Automation QC step is added to the Workflow, once video generation is complete, it can be viewed in the new Cloud Automation QC Kanban board. This works like other Kanban boards with the “To Do”, “Doing”, and “Done” steps.
From there, you can preview the generated videos, approve them for delivery, or reject those that need to be regenerated. A full-screen video viewing option is also available for a closer look.