Generate videos using Kling

Last updated on Oct 28, 2026

Learn how to use the Kling 2.5 Turbo, Kling 3.0, and Kling 3.0 Omni video models to generate videos from text prompts in Timeline.

   Timeline is a beta feature in Adobe Firefly, now available for testing and feedback.

Turn your ideas into videos using 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. It transforms text prompts and images into production-ready video clips, combining generation, editing, and narrative control into a single workflow.

What you can create

With Kling, you can create:

  • Narrative brand storytelling: Develop multi-scene campaign concepts with consistent characters, dialogue, and pacing.
  • Dialogue-driven social content: Create episodic, story-led videos with synchronized voice and character continuity.
  • Concept trailers and short films: Previsualize cinematic sequences with structured shots, environments, and timing.
  • Explainer videos with voice: Produce multi-scene videos with synchronized narration to communicate ideas clearly.

Play this 5-second video to understand how Kling lets you create narrative brand storytelling

Generate videos using Kling

On the Firefly homepage, select Video > Edit multi-track video.

Select the Generate media   icon in the right panel, and then select the Video panel.

In the Prompt field, enter a text prompt that best describes what you want to generate.

  Prompt example: Set the salad bowl down on the table.

Select the Model dropdown menu under General settings, and then select Kling 2.5 Turbo, Kling 3.0, or Kling 3.0 Omni.

Firefly video editor with Generate panel open, Kling 2.5 Turbo selected, and video settings visible.
Select the Generate media icon to open the Generate media panel.

Based on the model selected, use the following options: 

Model name

How to use the options

Kling 2.5 Turbo

  • Aspect ratio: Select Widescreen (16:9), Square (1:1), or Vertical (9:16).
  • Frames section: Select First, and upload an image from Your device or Adobe cloud storage to add a first frame for the video generation.
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, 24 FPS, and 5 seconds, respectively.

Kling 3.0 or Kling 3.0 Omni

  • Resolution: Select 720p or 1080p.
  • Aspect ratio: Select Widescreen (16:9), Square (1:1), or Vertical (9:16).
  • Duration: Select the dropdown menu, and then drag the slider to set the duration.
  • Audio: Turn on the Audio option to generate synchronized sounds, music, or dialogues for the generated video.
  • Frame section: Select First to add a start image, and select Last to add an end image, and set the start and end frames of your video. To add an end frame, you first need to add the first frame.
Note

The Frames per second is set to a default of 24 FPS.

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 consistent with the action described 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 hover over the preview and adjust the crop as needed.

In the Advanced settings, add a seed number in the Seed field to control the randomness of what AI creates. If you use the same seed, prompt, and control settings, you can generate similar video clips.

Select Generate to generate the video. Your generated video is now part of your project and can be edited, trimmed, or combined with other media clips in the timeline.

Drag the generated video from the Generation history panel onto your video timeline and edit it further.

Best practices to create multi-scene videos with Kling

  • Break concept into clips: Start with a concept or a script and break it into short clips, structure prompts by scene, and then combine them into multi-scene sequences.
  • Use text and reference images: Generate initial shots using text and reference images. For better control, combine reference images, elements, and tags. Add audio or dialogue where needed.
  • Refine with Prompt to edit: Use Prompt to edit   to refine rather than regenerate, and use keyframes to guide motion and transitions.
  • Maintain consistency and iterate content: Use consistent character descriptors, reference images, or Elements, and iterate on pacing, tone, and continuity.
  • Export or extend into longer sequences: Export completed clips for editing or sharing, or generate and combine additional clips to continue the story and create a longer sequence.