Skip to main content
Gen AI brings image, video, and audio generation into Premiere Copilot. Describe what you want, optionally provide reference media, adjust the available settings, and save the result directly into your project workflow. The available inputs and settings change automatically depending on the type of generation you select.

​
Quick Start

1

Choose a media category

Select Image, Video, or Audio.
2

Choose a generator

Pick an option that supports the kind of result and inputs you need.
3

Add the prompt

Describe the subject, action, style, framing, light, and mood as clearly as possible.
4

Add reference media (optional)

Upload a file or capture the required image, video, or audio directly from the active timeline.
5

Set the output folder

Choose where completed generations should be downloaded.
6

Generate

Check the estimated price, launch the generation, and follow it in the history panel.

​
Media categories

​
Reference media

Some generations work from text alone. Others require one or more reference files. The interface displays only the inputs that are relevant to the selected option. You can:
  • Browse for a local image, video, or audio file.
  • Capture the current timeline frame for an image input.
  • Export a short timeline section when a video reference is required.
  • Export the selected audio when an audio reference is required.
  • Provide several reference images when the option supports a list.
Place the playhead on the cleanest representative frame before using timeline capture. Avoid frames with motion blur, transitions, or temporary overlays.

​
Writing a useful prompt

Describe the visible or audible result, not the process:
  • Image: “Studio product photograph of a black camera on brushed steel, soft side light, dark neutral background.”
  • Video: “Slow push-in toward the cabin, light snow moving across frame, stable cinematic camera, dusk.”
  • Audio: “Short dry mechanical camera shutter, close and detailed, no ambience or voice.”
For edits, say what must change and what must remain untouched. For animation, describe both the movement of the subject and the movement of the camera.

​
Dynamic settings

Settings vary by generation and can include aspect ratio, output size, duration, number of results, strength, seed, or other controls. Hover over a setting when a description is available.
A higher duration, resolution, or number of results can increase the estimated price and processing time. Check the estimate again after changing settings.

​
History and files

Every request appears in the history with its prompt and progress. Completed results are downloaded to the selected output folder. Failed items keep their error message so you can adjust the inputs and try again. Pin frequently used generation options to keep them easy to find.

​
Common pitfalls

  • A required input is empty: add every reference field shown by the interface.
  • The captured frame is wrong: move the playhead, then capture it again.
  • A local file was moved during processing: keep source files in place until the request finishes.
  • The output folder is unavailable: select a local writable folder.
  • A vague prompt produces generic results. Describe subject, action, framing, light, and restrictions.
  • Reference media and prompt conflict: state clearly which elements of the reference must be preserved.
Start with one clear result and modest settings. Once the composition or motion is right, increase quality or duration for the final generation.