On the Firefly homepage, select Create from the left panel and then Edit video (beta).
Last updated on
May 6, 2026
Learn to use the Kling 2.5 Turbo, Kling 3.0, and Kling 3.0 Omni video models to generate videos from text prompts in the Firefly video editor.
Turn your ideas into videos using partner models in the Firefly video editor (beta). With the Kling 2.5 Turbo, Kling 3.0, and Kling 3.0 Omni models, you can generate high-quality video clips from a starting image and add them directly to your timeline.
Open a project or create a new one to access a timeline.
Select the Generate media icon in the right panel, then select the Video panel if needed.
In the Prompt field, enter a text prompt that best describes what you want to generate.
Select the Model dropdown menu under General settings, then select Kling 2.5 Turbo.
Select the aspect ratio for your video—Widescreen (16:9), Square (1:1), or Vertical (9:16).
Note
You cannot change the Resolution, Frames per second, and Duration of the video generated with Kling 2.5 Turbo, which are set at a default of 1080p and 24 FPS and 5 seconds, respectively.
To add a first frame for the video generation, go to the Frame section, select First, and upload an image from Your device or Adobe cloud storage.
Tip
- After selecting First, use the Current frame option to use the frame where the playhead is positioned as the start frame of the generated video. For best results, ensure your first frame images are visually compatible with the action you describe in your text prompt.
- If the keyframe image doesn’t match the aspect ratio, hover over the thumbnail to activate the Crop Image icon . You can move your cursor over the preview and adjust the crop as needed.
In the Advanced settings, 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.
Select Generate to generate the video.
Drag the generated video from the Generation history panel onto your video timeline.
Your generated video is now part of your project and can be edited, trimmed, or combined with other media clips in the timeline.
On the Firefly homepage, select Create from the left panel and then Edit video (beta).
Open a project or create a new one to access a timeline.
Select the Generate media icon in the right panel, then select the Video panel if needed.
In the Prompt field, enter a text prompt that best describes what you want to generate.
Select the Model dropdown menu under General settings, then select Kling 3.0 or Kling 3.0 Omni.
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 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 or ending frame of your video, under the Frames section, select First to add a start image, and select Last to add an end image. To add an end frame, you first need to add the first frame.
Tip
- After selecting First or Last, use the Current frame option to use the frame where the playhead is positioned as the start frame of the generated video. For best results, ensure your first frame images are visually compatible with the action you describe in your text prompt.
- If the keyframe image doesn’t match the aspect ratio, hover over the thumbnail to activate the Crop Image icon . You can move your cursor over the preview and adjust the crop as needed.
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.
Select Generate .
Turn text into art with Adobe Firefly
Create beautiful images and video clips from text prompts using generative AI.
