Generate Video (beta) on Firefly Web App

Whether you’re a professional video editor, motion graphic designer, working in an agency, or running your own company, you’re constantly trying to tap into new ways to explore your vision — faster, better, and more efficiently. For the last decade, you’ve given us incredible feedback on how you want AI to reduce tedium and amplify your storytelling. And that feedback has continued to guide us over the past few months as we developed the Firefly Video Model to be compelling and creator friendly.

Since we unveiled the model in September, we’ve given early access to some of our top community leaders — and they are already generating incredible Text-to-Video and Image-to-Video creations that push the boundaries of generative video and human ingenuity! Our community is ideating and exploring faster, adding new elements to existing footage, and filling gaps to express creative intent better than ever.

We know that creating with confidence is critical to you and your clients or collaborators. Just like our other Firefly generative AI models, Adobe Firefly Video model is designed to be commercially safe and is only trained on content we have permission to use — never on Adobe users’ content.

Let’s look at how you’ve been using generative video in creative new ways!

Text-to-Video (beta) in Adobe Firefly

With Firefly Text-to-Video, you can use text prompts, a wide variety of camera controls, and reference images to generate B-Roll that seamlessly fills gaps in your timeline.

Missing shots are no problem for your timelines now! With detailed prompting, you can generate a compelling insert shot to use in your final project.

Visualizing creative intent for difficult-to-capture or expensive shots is challenging for teams working on tight budgets and quick turn arounds. Using Adobe Firefly to visualize and plan these shots before going into VFX or back to set for pick-up shots helps to streamline communication between production and post-production.

We’ve heard from many of you that filling gaps in your timeline where visual effects shots are planned to be added later helps to gain creative buy-in as you craft your story. No more “insert shot here” placeholders needed. You can more easily express the intent to help guide the visual effects work.

There is a lot of excitement from our community over the ability to add visual depth to existing content by using Firefly Video to generate atmospheric elements like fire, water, light leaks, and smoke. Generating these elements on a black or green background means you can then layer them over existing video using blend modes or keying inside Adobe’s tools like Adobe Premiere Pro or Adobe After Effects.

Composited in Premiere Pro with the Screen blending mode:

Communicating intent to animators and motion designers or ideating before you dive into your own creative processes saves time spent on iterations to find the right style.

Image-to-Video in Adobe Firefly

With Image-to-Video, you can also utilize a reference image alongside your text prompt. You can easily create a complementary shot for existing content, such as a close-up, by uploading a single frame from your video.

Or create new b-roll from still photography, breathing new life into your library of existing images.

You can even change the original motion or intent of your shot in some cases. For example, if your clip has a specific action and you’re an editor who wishes to pitch a reshoot to a director, you can help to visualize how the update will help the story while maintaining the same look.

Before

After

Prompt: A gloved astronaut hand enters the shot and unplugs one of the yellow cables. Cinematic.

Prompting in Adobe Firefly

With Firefly Video Model, you have rich camera controls like shot size, angle, and camera motion for more precise generations. But the more detailed your prompts, the better! With more depth and description, the model can better help you generate what’s in your mind.

Explore different perspectives rapidly by updating your prompts. You can utilize “seeds”, a unique identifier, to quickly iterate from a successful prompt to refine your work. Seeds maintain a consistent starting point so you can quickly try new variations without starting from scratch.

Try using this structure in your prompts:

Shot Type Description + Character + Action + Location + Aesthetic

• Use as many words as possible to be specific about lighting, cinematography, color grade, mood, and style.
• Be clear and descriptive. Avoid ambiguity.
• Define actions and use specific verbs and adverbs.
• Use lots of descriptive adjectives.
• Include temporal elements like time of day or weather.
• Bring in camera movements as necessary.
• Iterate!

Learn more about best practices for writing generative video prompts.

Our commitment to creator-friendly AI innovation

Adobe is committed to taking a creator-friendly approach and developing AI in accordance with our AI Ethics principles of accountability, responsibility and transparency. We have over a decade-long history of delivering hundreds of intelligent capabilities into applications that millions of people rely upon and we’re continuing to integrate technology into our tools in a way that is respectful and supportive of the creative community.

Our Firefly generative AI models are trained on licensed content, such as Adobe Stock, and public domain content — and are never trained on customer content.

In addition, we continue to innovate ways to protect our customers through efforts including Content Credentials with attribution for creators and provenance of content. Adobe is determined to be a trusted partner for creators in the era ahead. We co-founded a global coalition called the  Content Authenticity Initiative (CAI), which now has more than 2,500 members from across industries working together to promote transparency in digital content.

We’ll attach Content Credentials to assets produced using Firefly so that people who work with or view the content can see how it was made and whether AI was involved. This ensures we establish a transparent chain of trust from creation to dissemination online.

We can’t wait to see what you create. Join the waitlist to be next in line to gain access to Adobe Firefly Video Model.