On the Adobe Firefly homepage, select Generate from the left panel then select Generate video.
Last updated on
Jun. 19, 2026
Learn how to use Kling models to generate videos using text prompts, reference images, and shot detailing.
When you use the Generate video feature, you can choose Kling video models, including versions Kling 2.5 Turbo, Kling 3.0, and Kling 3.0 Omni. These models offer advanced video generation capabilities, including improved motion consistency, more realistic visuals, greater control over camera movement, and better scene composition. Based on the model you select, you can choose from various settings and controls, allowing you to tailor the output to your creative needs.
Note
Chinese models like Kling are only available to individual subscribers, not to creators on teams or enterprise plans.
When you select a partner model like Kling to generate a video, you'll be prompted to confirm it, along with other relevant information. Please review the details and select OK to start generating videos.
In the General settings section, select Kling 2.5 Turbo from the Model dropdown menu for video generation.
Select the Aspect ratio from the following options:
- Widescreen (16:9)
- Square (1:1)
- Vertical (9:16)
Note
The Resolution is set to a default of 1080p, Frames per second to 24 FPS, and Duration to 5 seconds.
Set the starting frame of your video, under the Frames section, select First to add a start image. If you wish to further modify keyframe images, select:
- Crop Image: If the keyframe image doesn’t match the aspect ratio, hover over the thumbnail to activate the image tools and select the Crop Image icon . You can move your cursor over the preview and adjust the crop as needed.
- Edit Image: If you wish to edit the first or last frame image, hover over the thumbnail to activate the image tools and select the Edit Image icon . When the edit with text prompts page opens, you can easily add or modify the details of your image and Save it to get back to the Generate image page.
- Remove Image: To remove an image from the first or last frame, hover over it and select the Remove Image icon .
In the Advanced section, you can use the Seed option to 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.
In the Prompt field, enter a text prompt.
Select Generate .
On the Adobe Firefly homepage, select Generate from the left panel then select Generate video.
In the General settings section, select Kling 3.0 or Kling 3.0 Omni from the Model dropdown menu for video generation.
Select the Resolution from 720p or 1080p.
Select the Aspect ratio from the following options:
- Widescreen (16:9)
- Vertical (9:16)
Note
The Frames per second is set to a default of 24 FPS.
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. You can also change the duration by selecting the duration icon from the prompt bar.
Kling 3.0 and Kling 3.0 Omni let you generate audio alongside your video. Enable the Audio option to generate synchronized sounds, music, or dialogues for the generated video.
Set the starting frame of your video, under the Frames section, select First to add a start image. If you wish to further modify keyframe images, select:
- Crop Image: If the keyframe image doesn’t match the aspect ratio, hover over the thumbnail to activate the image tools and select the Crop Image icon . You can move your cursor over the preview and adjust the crop as needed.
- Edit Image: If you wish to edit the first or last frame image, hover over the thumbnail to activate the image tools and select the Edit Image icon . When the edit with text prompts page opens, you can easily add or modify the details of your image and Save it to get back to the Generate image page.
- Remove Image: To remove an image from the first or last frame, hover over it and select the Remove Image icon .
In the Advanced section, you can use the Seed option to 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.
In the Prompt bar, enter a text prompt that best describes the actions happening in your video. You can also select the Multi-shot toggle to add a prompt for and describe multiple shots.
In the Prompt field for each shot, enter a text prompt that best describes the actions happening in your shot.
Define and add reusable elements to your prompt to ensure consistency and control in your generated videos.
Select Generate .
Define and add shots
To add multiple shots to your video, select the Multi-shot toggle in the prompt bar.
- Select Add shot from the top of the prompt bar to create a new shot and describe it. Then, from the Duration drop-down menu, move the bar to set the length for each of these shots. You can add up to 5 shots for each video generation.
- Select the Auto toggle that appears after activating multi-shot to auto-calibrate the number of shots and their lengths.
Select Elements > + Create elements > Create new to open the New element panel.
Select the upload icon to upload a reference image or video from your device. Use a front-facing visual of the element for better results.
In the Element name field, enter a name for the element.
Set the element Type by selecting Character, Item, or Location.
Select the add icon under the Add angles section and upload up to three images to improve multi-angle consistency for the element.
In the description box, provide details to define the element's appearance and attributes. You can also specify the attributes that you'd want the model to ignore.
Select Create to save the element for use in your prompt. To add this element to your prompt, select Elements > Element name.
Turn text into art with Adobe Firefly
Create beautiful images and video clips from text prompts using generative AI.
