We're excited to introduce our new Multi-Image Video feature on ActiveCast, which allows you to combine multiple images to generate a single video featuring different scenes, characters, products, and locations.

Each AI model supports a specific number of images per video. Check the model limits below to find the best option for your project. You can also refer to our article on video specifications supported by each AI model for more details.

Although these features complement each other, they serve different purposes.

The number of images you can combine depends on the AI model you select. Seedance 2.5 is the most advanced model that supports the largest number of images, allowing you to use up to 30 photos in a single video. Other models have different limits.

AI models available on ActiveCast and how they differ

Here’s a breakdown of the supported image limits for each model.

Note: If you add more than 11 images, the remaining images will be hidden from view. To display them, click “+X more”, where X indicates the number of additional images.

To collapse the list again, click “Show less.”

After selecting an AI model, you’ll see how many images you can add. For example, Seedance 2.0 may display “1 of 9 for this model.”

Adding images is easy. You can use either of the following methods:

Drag an image directly into the Add to Video tab, located at the top of the editing settings panel on the right side of the starting image.

Click Add to Video and choose one of the four available options:

Note. Every image added to this section can be used in the generated video. If you don’t specify what the AI model should do with each image, it may interpret the references incorrectly or produce unexpected results.

Once an image has been added, you can manage it using the options below the image:

You can rename any image except the starting image.

Note. If you add several images and then switch to an AI model that supports fewer images, your video may not turn out as expected. Before generating the video, remove any images that exceed the selected model’s limit.

Once you’ve added your images, it’s time to describe how they should be used in your video.

Your prompt should clearly explain what happens in each scene, how the characters or objects move, and how the video transitions from one image to another.

Pro tip: You can use an AI assistant, such as ChatGPT or Gemini, to help you write a detailed video prompt.

Because you’re combining multiple images, it’s especially important to tell the AI model what to do with each one.

When writing your prompt manually, you can reference an image by inserting its label.

There are two ways to do this:

The starting image is labeled “Starting frame.” Make sure to use the correct image labels throughout your prompt, so the AI model can associate each instruction with the intended image.

If you use ChatGPT or another AI assistant to generate your prompt, include the label of every image you want to reference. This helps ensure that the resulting prompt correctly identifies each visual reference.

Here are examples of prompts used to create our video examples.

The man holds the laptop and looks at it from all angles. Then he walks to his desk, sits down and opens the laptop. We can clearly see the website from [image 4] on the laptop screen. He clicks the “make your first video free” button. The screen in [image 5] is displayed. He clicks on the image on the top left of the image grid and the pop-up in [image 5] is shown. He clicks on “activate image” button and the screen in [image 6] loads.

Then we zoom in to the photo of the lady on the screen in [image 7] and she talks: “ActiveCast by promo.com. Reality is the best prompt”.

You can preview the result here:

"Woman from [starting frame], woman from [image 1], woman from [image 2] and woman from [image 3] are walking together on location from [image2], smiling and chatting naturally in a bright, modern setting. Use smooth tracking-camera movement, realistic body motion, natural expressions, and warm commercial lighting.

At some point they walk different ways. As the women gradually walk in different directions, transition into a full-screen layout divided into four equal vertical panels, separated by three thin vertical lines. Each panel follows one woman independently.

First panel — Woman from [starting frame]: She walks energetically, then happily jumps while holding the bag from [image 4] .

Second panel — Woman from [image 1] : She walks backward with a playful smile while holding the pen from [image 5].

Third panel — Woman from [image 2] : She runs with lively energy while holding the cup from [image 6] .

Last panel — Woman from [image 3] : She slowly walks toward the camera while holding the bottle from [image 7] .

Keep all four panels synchronized in time, with each woman remaining clearly recognizable. Preserve the original products’ colors, shapes, proportions, and details.

All four women suddenly stop moving at the same moment.

In the first two panels, the woman from the [starting frame] reaches across the vertical dividing line and hands the bag from [Image 4] to the woman from [Image 1]. In return, the woman from [Image 1] reaches across the same boundary and hands the pen from [Image 5] to the first woman.

Make the exchange fluid, friendly, and physically believable. Keep both women in their respective panels while their hands and products cross the dividing line naturally.

Next, the woman from [Image 2] hands the cup from [Image 6] across the boundary to the woman from [Image 3]. The woman from [Image 3] reciprocates by handing the bottle from [Image 7] to the woman from [Image 2]. Ensure the correct products are exchanged and clearly visible in the appropriate hands.

Dialogue and closing

Keep the four-way split screen.

The women in the first two panels look toward each other, smile, and speak naturally in sync with the dialogue:

“Sharing is caring.”

Then the women in the last two panels smile and speak in sync with the dialogue:

“Our products designed just for sharing.”

Use clear, natural English pronunciation, accurate lip synchronization, and friendly, confident delivery. Display no extra dialogue.

Visual style and technical requirements

Premium lifestyle-commercial aesthetic, realistic human movement, natural facial expressions, consistent character identities, smooth camera tracking, clean lighting, sharp product details, and seamless split-screen transitions. Maintain four equal vertical panels separated by exactly three thin vertical lines throughout the split-screen scenes. Keep the dialogue easy to understand and the products unobstructed.

Avoid distorted hands, duplicated products, incorrect exchanges, identity changes, flickering, inconsistent clothing, unnatural backward walking, and garbled speech. End on a clean, visually balanced four-panel composition with all four women smiling."

Once your prompt is ready, you can add narration to your video and select narrators for the relevant scenes.

Note: You can include narration instructions directly in your prompt.

When using MultiScene Video generation, you can select speakers only from the characters shown in your Starting Image. Any additional voices will be treated as narrators.

For detailed instructions, please refer to our article on how to add narration and select narrators.

Can I select narrator for my Active Stock video?

Next, choose your preferred Resolution, Aspect Ratio, and Duration.

For the best results, we recommend enabling SmartSync toggle, which automatically adjusts the video length to better match your content.

Note. The number of credits required to generate a video depends on several factors, including its duration, resolution, and the AI model you select. Longer videos, higher resolutions, and more advanced AI models generally require more credits.

Once you’ve configured your settings, generate your video and review the result. When you’re happy with it, you can download it.

If your video contains multiple Shutterstock images, additional credits will be deducted when you download it. This is due to Shutterstock’s licensing requirements. The number of credits required depends on the specific images used.

And that’s it! You’re ready to combine multiple images and create engaging, multi-scene videos with our Multi-Image Video feature.

If you have any questions, feel free to contact us via in-app chat or email at [email protected].

We look forward to seeing your brand thrive with ActiveCast videos!