Use the model dropdown menu to select Kling 3.0 or Kling 3.0 Omni as the video model.
Last updated on
May 6, 2026
Learn how to generate videos in Firefly Boards using partner models.
While working in Firefly Boards, you can generate videos and place them directly onto the canvas. You can choose from Adobe models like Firefly Video or partner models such as:
When you select a partner model to generate a video, you'll be prompted to confirm that you're using a model not developed by Adobe, along with other relevant information. Please review the details and select OK to start generating videos.
Note
The availability of video generation settings depends on the video model selected.
Before you begin, create a new board, then select Generate video at the bottom of the page to start generating a video.
Select the Sample from canvas option, and then use the dropper tool to select an image and add sub-prompts.
Select the Effects option to apply Popular, Lighting, Color, Subject, Scene, or Style effects.
Select the Video option and use the dropper to choose a video from the canvas and use as a composition reference. This reference guides the generated video’s structure, depth, edge arrangement, and overall composition.
You can also set the starting or ending frame of your video by selecting Sample from canvas directly, or by selecting First frame or Last frame, and then:
- Use the Sample from canvas tool, select an image from the canvas, and further select Use as first frame or Use as last frame.
- Select the Your device option to upload an image from your local device as the start or end frame.
Select Add shot to add and define the shots for your video. You can add a maximum of 5 shots per video generation.
In the Prompt field for each shot, enter a text prompt that best describes the actions happening in your shot.
Select the Aspect ratio from the following options:
- Widescreen
- Square
- Vertical
Select the Resolution from 720p or 1080p.
Select the Duration option and move the slider to set the duration to a maximum of 15 seconds. Kling 3.0 and Kling 3.0 Omni allow you to set the duration shot by shot; you can move the slider for each added shot to do so.
If you select the settings icon , you can enter a seed number that helps start the process and controls the randomness of what the AI creates. If you use the same seed, prompt, and control settings, you can generate similar video clips.
To use additional generation settings, select the Generation settings icon next to the Duration option.
Select Generate .
Note
Once you've placed the video on your canvas, select the video, open the More menu , and then select Open in Firefly video editor (beta) to open it directly in the video editor in a new project. You can also select multiple media files; the selected media is automatically added to the timeline in the video editor, in the same order you selected them.
Before you begin, create a new board, then select Generate video at the bottom of the page to start generating a video.
Select the video model as Marey.
If you have images that you want to use as the first and last frames of the generated video, add an image under the First frame and Last frame, respectively.
These uploaded images for the first and last keyframes serve as fixed points, providing guidance to ensure the video starts and ends with them.
If images have already been added to the canvas and you want to use one as the first frame, select the Sample from canvas option, then use the eyedropper tool to choose the image.
Alternatively, you can also use the Upload image reference option to upload a reference image.
Select the aspect ratio for your generated video—Landscape, Portrait, Square, or Widescreen.
To use additional generation settings, select the Generation settings icon next to the Aspect ratio options.
Add a text description in the prompt bar.
Select Generate.
Note
Once you've placed the video on your canvas, select the video, open the More menu , and then select Open in Firefly video editor (beta) to open it directly in the video editor in a new project. You can also select multiple media files; the selected media is automatically added to the timeline in the video editor, in the same order you selected them.
Before you begin, create a new board, then select Generate video at the bottom of the page to start generating a video.
Select the video model as Ray2, Ray3, and Ray3.14.
If you have images that you want to use as the first and last frames of the generated video, add an image under the First frame and Last frame, respectively.
These uploaded images for the first and last keyframes serve as fixed points, providing guidance to ensure the video starts and ends with them.
If images have already been added to the canvas and you want to use one as the first frame, select the Sample from canvas option, then use the eyedropper tool to choose the image.
Alternatively, you can also use the Upload image reference option to upload a reference image.
Select the preferred aspect ratio for your generated video from the Aspect ratio drop-down.
To use additional generation settings, select the Generation settings icon next to the Aspect ratio options.
Add a text description in the prompt bar.
Select Generate.
Before you begin, create a new board, then select Generate video at the bottom of the page to start generating a video.
Select the video model as Runway Aleph.
Under Composition, select the Video field to activate the eyedropper tool. Then, select the video on the canvas you'd like to use as a reference. This will help you generate a new video that matches the reference video's composition.
You can include an image as the video's opening frame. This helps establish the first frame and set the narrative direction of the video right from the start.
Select the aspect ratio for your generated video—Landscape, Portrait, Square, or Widescreen.
To use additional generation settings, select the Generation settings icon next to the Aspect ratio options.
Note
The option to choose an aspect ratio is disabled if a video composition is added.
Add a text description in the prompt bar.
Select Generate, and once the video is created, drag it onto the canvas.
Before you begin, create a new board, then select Generate video at the bottom of the page to start generating a video.
Use the Model dropdown menu to select from Runway Gen-4 and Runway Gen-4.5.
Select the Sample from canvas or Image (required) option, then select the image from the canvas with the eyedropper tool. From the context menu, select Use as image reference, and optionally add a sub-prompt to the main prompt.
Note
The Image option isn't available for Runway Gen-4.5. However, you can select the Sample from canvas icon to extract sub-prompts and enrich the generated output.
Select the aspect ratio for your generated video—Landscape, Portrait, Square, or Widescreen.
Note
Runway Gen-4.5 maintains Widescreen as the default Aspect ratio.
To use additional generation settings, select the Generation settings icon next to the Aspect ratio options.
Add a text description in the prompt bar.
Select Generate, and once the video is created, drag it onto the canvas.
Before you begin, create a new board, then select Generate video at the bottom of the page to start generating a video.
Select the video model as Sora 2 and Sora 2 Pro.
If images have already been added to the canvas and you can select the Sample from canvas option, then use the eyedropper tool to choose the image as a reference.
Alternatively, you can also use the Upload image reference option to upload a reference image.
Select the aspect ratio for your generated video—Widescreen or Portrait.
To use additional generation settings, select the Generation settings icon next to the Aspect ratio options.
For Sora 2 Pro, enable the Audio option to generate a video that includes synchronized sound.
Add a text description in the prompt bar.
Select Generate.
Before you begin, create a new board, then select Generate video at the bottom of the page to start generating a video.
On the Firefly homepage, select Ideate and then Create a board.
Select Generate video at the bottom of the page.
Select the video model as Veo 2, Veo 3.1, or Veo 3.1 Fast.
Add an image under the Image option if you want to use it as the starting frame of the generated video.
If images have already been added to the canvas and you want to use one as the first frame, select the Sample from canvas option, then use the eyedropper tool to choose the image. From the context menu, select Use as image reference, and optionally add a sub-prompt to the main prompt.
Alternatively, you can also use the Upload image reference option to upload a reference image.
Select the aspect ratio for your generated video as either Portrait or Widescreen. For Veo 3.1 Fast, it will be by default will be landscape.
Enable the Audio option to generate synchronized sounds or music for the generated video.
Note
Veo 3.1 and Veo 3.1 Fast are the only models that offers the ability to generate audio along with your video.
- Sub-prompts: You have to option to browse through a range of sub-prompts from lighting to styles. When you select the preview thumbnails of the sub-prompts, they get added to the prompt bar.
- Seed: You can add a seed number that helps start the process and controls the randomness of what the AI creates. If you use the same seed, prompt, and control settings, you can generate similar video clips.
Add a text description in the prompt bar.
Select Generate.
Turn text into art with Adobe Firefly
Create beautiful images and video clips from text prompts using generative AI.
