Designed to be commercially safe and to be integrated into Adobe workflows all across Creative Cloud, Adobe has shared a preview of its upcoming FireFly Video Model—the latest generative AI video offering from the makers of Premiere Pro and After Effects.
As we’ve seen in the past from Adobe with its popular Generative Fill tool in Photoshop, generative AI has been on Adobe’s roadmap for some time. Adobe Firefly in particular has been around for several years now and has found many different—albeit smaller—iterations within Premiere Pro and After Effects.
Yet this generative AI offering has been coming for a long time. With the generative AI video arms race still very much going on (despite being a bit at a standstill currently as we still wait for OpenAI’s Sora to be released) this latest preview from Adobe does forecast a powerful new technology from a major player that could bust the gates of generative AI in mainstream video editing wide open.
A Preview of Adobe’s Firefly Video Model
Dubbed as the beginning of a “new era of video editing,” by Adobe, this new Firefly Video Model does indeed sound quite capable in terms of what it can do. Adobe’s Firefly Video Model is currently set to include three main features:
- Text to Video — capabilities to generate video from text prompts; access a wide variety of camera controls such as angle, motion, and zoom to finetune videos; and reference images to generate B-Roll that seamlessly fills gaps in your timeline.
- Image to Video — capabilities to bring still shots or illustrations to life by transforming them into stunning live-action clips.
- Generative Extend — a new Firefly-powered feature integrated into Premiere Pro, is designed to tackle several editorial challenges, including extending insufficient frames at the beginning or end of a clip, giving you extra footage to hold on a shot for another beat or to cover a transition, or creating seamless audio edits by generating “room tone” where none exists.
And if you check out some of the samples below, it’s going to be quite impressive, to say the least. However, Adobe has been pretty direct in its messaging stating that the company “believes AI can be a tool for, not a replacement of, human creativity and that generative AI should be developed responsibly.”
A Respect for Creator Rights
In a separate post, Adobe shared more info about the company’s approach to generative AI and its focus on providing the world with more tools and resources to enable creative endeavors. And it sounds like Adobe has really done their outreach within the video editing community to get feedback regarding how they’re leveraging these generative AI video models into their video editing workflows.
And, just as they’ve shared regarding their other Firefly generative AI models, Adobe has once again announced that video editors will be able to “create with confidence knowing the Adobe Firefly Video Model is designed to be commercially safe and is only trained on content we have permission to use” — and never being used on Adobe users’ content.
If you’d like to read more about Adobe’s new Firefly Video Model, as well as possibly sign up for the waitlist, check out the full page on Adobe’s site here.
Author: Jourdan Aldredge
This article comes from No Film School and can be read on the original site.
