Generate videos using text prompts

On the Adobe Firefly homepage, select Video from the left panel, then select  Generate video.

Under the General settings section, by default, the model used will be Firefly Video. However, if you're generating a video for the first time, the default will be Veo 3.1.

To change the video generation model, use the Model dropdown menu and select from Adobe or partner video models.

Select the resolution to define the quality of the generated video.

Use the Aspect ratio dropdown menu to set a specific aspect ratio for the generated video.

The Frames per second for all generated videos is set to a default of 24 FPS across Adobe and partner models.

If you would like to generate a video that aligns with an existing video's outlines and composition, upload a reference video in the Composition section.

In the Camera section, use the Motion reference option to upload a video and extract its camera movements, including pans, zooms, tilts, and motion paths, which will guide the generation.

If you upload a motion reference video, the following camera options get disabled:

• Shot size
• Camera angle
• Motion

To manually specify the framing of the main subject within the video, use the Shot size dropdown menu to select an option.

• None: Default shot size.
• Extreme close up: Zoom in to emphasize minute details, often on a single feature like an eye or a hand.
• Close up shot: Focus tightly on a subject’s face or a specific detail, highlighting important elements.
• Medium shot: Frame the subject while providing enough context to the environment and surroundings.
• Long shot: Include the entire subject within their environment, providing context and background.
• Extreme long shot: Capture a broad view of the scene and show the relationship between the subject and the surroundings.

Use the Camera angle dropdown menu to select from the available options:

• None: Default camera angle.
• Aerial shot: A high-altitude view, like from a drone or a helicopter.
• Eye level shot: A shot at the same height as the subject.
• High angle shot: A view from above the subject, looking down on it.
• Low angle shot: A view from below the subject, looking up at it.
• Top down shot: A view directly above the subject, looking straight down.

Select from the available camera Motion options to guide the camera's movement within the generated video:

• Zoom in: Move the camera lens closer to the subject, making it appear larger as the video proceeds.
• Zoom out: Move the camera lens away from the subject, making it appear smaller as the video proceeds.
• Move left: Rotate the camera horizontally to the left side.
• Move right: Rotate the camera horizontally to the right side.
• Tilt up: Shift the camera vertically upward.
• Tilt down: Shift the camera vertically downward.
• Static: Keep the camera fixed in one position without any movement.
• Handheld: Simulate the effect of handheld camera footage, creating a shaky or unstable appearance.

If you want to specify the visual style for the generated video, you can either write a descriptive prompt that clearly outlines everything in the video, including the desired style or look, or choose a style preset from the Style section.

Hover over the style preset thumbnails to preview their effects. Select a thumbnail to specify the identified style for the video generation.

In the Advanced section, to generate videos with transparent backgrounds, enable the Transparent background option.

You can also 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.

Enter a text prompt in the Prompt field.

Select Generate .

Hover your cursor over the generated video, and select one of the following options: