DIY Photography

Your one stop shop for everything photo-video

  • News
  • Inspiration
  • Reviews
  • Tutorials
  • DIY
  • Gear
Search

Submit A Story

Adobe is bringing Generative AI to video with Premiere Pro and After Effects

Oct 11, 2023 by John Aldred Leave a Comment

  • Share
  • Tweet
  • Flipboard
  • WhatsApp

Adobe Generative AI for Video

We all knew it was only a matter of time before Adobe started implementing its Firefly-powered generative fill-type features in its video products. I have to admit, I didn’t think it’d be quite so little time, but it looks like it’s coming soon.

At Adobe MAX, Adobe is showing off a sneak peek of some new features coming to Creative Cloud. Amongst them is “Project Fast Fill”, which brings Firefly generative AI features to Premiere Pro.

Unfortunately, there’s no video of the new features in action yet – although they’re expected to come at some point before the end of Adobe Max. As they become available, you can view them here. Adobe has also released no images to go along with these announcements yet, so I’ve illustrated this article with images created using Adobe’s new Firefly 2 engine.

Adobe Generative AI for Video

Adobe Premiere Pro – Project Fast Fill

So, what’s new? Well, the big one is Project Fast Fill. This is essentially the same generative AI that powers Photoshop’s Generative Fill feature, except much more advanced – and hopefully a lot quicker. Naturally, being a feature for Premiere Pro, this one is targeted towards video. Adobe says that it may also be coming to Adobe After Effects.

Project Fast Fill brings the power of Firefly generative AI to video for the first time. Leveraging Generative Fill technology – which Adobe Photoshop already uses to ease the addition, removal, or expansion of content in images with simple Firefly-powered text prompts – Project Fast Fill offers an early look at what human-prompted generative AI could enable inside Adobe video editing tools including Premiere Pro and After Effects.

Adobe Blog

As mentioned, Adobe hasn’t released a video showing exactly how it works yet, but that’s coming in the next day or two. The concept of generative AI for video is intriguing. There’s obviously a lot of opportunity for potential abuse here. Adobe will have to keep a very close eye on that to make sure it doesn’t happen.

Adobe Generative AI for Video

Of course, there are plenty of legitimate reasons for using generative AI with video, too. Perhaps you’re shooting a period piece and need to remove a satellite dish off the side of a house in the distance. Or clean up a bit of trash from your footage that you weren’t able to clean up on set.

Exactly what capabilities generative AI in Premiere Pro or After Effects will have remains to be seen. It’s still in the early prototype days and it may be a little while off being implemented just yet. But hopefully, when Adobe releases the Sneaks video for this feature, we’ll learn a lot more.

Other audio & video Sneaks from Adobe MAX

Adobe Generative AI for Video
This is what Adobe Firefly 2 thinks Adobe MAX looks like

Amongst all of the other things, three other features are being demonstrated for audio and video use. The first is called “Project Dub Dub Dub”, and it’s designed to help automate the dubbing process.

The idea behind it is a concept we’ve seen before. But it’s designed to help you overdub your footage, perhaps with audio from a different take or a dub over a completely different language. It uses the audio to modify the footage to make your actor’s mouth look like they actually spoke the words.

Another is “Project Scene Change”. This lets you take footage from two different cameras pointed at a scene from different viewpoints and then create seamless, smooth motion between the two of them. This is going to be a very interesting one to play with!

Adobe Generative AI for Video
Hey, Firefly 2 can kinda do hands now! At least they have the correct number of fingers.

Finally, “Project Res Up”, which as the name suggests, is for increasing the resolution of your video footage. It uses a diffusion-based upsampling technology to increase the resolution of the shot. This could be extremely useful for slow-motion shots when limited to 1080p for those high speed in a 4K project.

Plenty of other Sneaks at Adobe MAX

There are plenty more Sneaks besides this one, but I felt this justified its own post, as it’ll be the first video editing application to incorporate generative AI directly into the software itself.

Currently, pretty much all AI tools capable of generating video are dedicated apps. You have to export your clip from your editor, run it through this dedicated tool and then import it back in. Soon (maybe), you’ll be able to do it all directly within Premiere Pro and After Effects.

But other features are coming to Photoshop, including “Project Stardust”, allowing you to more easily select many items from complex scenes, as well as some pretty major AI-powered 3D and design tools.

You can see the list on the Adobe blog, and be sure to keep an eye on the Adobe Max website for the upcoming videos. As to when they’ll actually come to our desktops, though, is anybody’s guess.

Note: All images in this post were generated using the current beta release of Adobe Firefly 2.

FIND THIS INTERESTING? SHARE IT WITH YOUR FRIENDS!

  • Share
  • Tweet
  • Flipboard
  • WhatsApp

Related posts:

New Premiere Pro and After Effects updates add native ProRes RAW support and GPU rendering Surprise! Adobe Stock creators aren’t thrilled with Adobe’s “ethically sourced” generative AI tool Adobe releases update for Premiere Pro to stop it blowing up your MacBook Pro speakers Advanced video stabilisation with Premiere and After Effects

Filed Under: news Tagged With: Adobe, Adobe After Effects, Adobe Creative Cloud, Adobe Firefly, adobe premiere pro, Artificial Intelligence, Gen AI

John Aldred: from diyphotography.net

About John Aldred

John Aldred is a photographer with over 20 years of experience in the portrait and commercial worlds. He is based in Scotland and has been an early adopter - and occasional beta tester - of almost every digital imaging technology in that time. As well as his creative visual work, John uses 3D printing, electronics and programming to create his own photography and filmmaking tools and consults for a number of brands across the industry.

« The Nikkor Z 600mm f/6.3 VR S is Nikon’s lightest super-telephoto lens
First AI contest reveals its winners. Is real art dying? »

Submit A Story

Get our FREE Lighting Book

DIYP lighting book cover

* download requires newsletter signup

Recent Comments

Free Resources

Advanced lighting book

Learn photography

Recent Posts

  • Rode acquires US pro audio company Mackie
  • Panasonic Lumix G9 II to get 12-Bit raw over HDMI for BRAW and ProRes RAW
  • This 3D printed stereoscopic macro lens is the weirdest camera rig you ever saw
  • OBSBOT Tail Air review – a streaming studio the size a soda can
  • Everything you need to know about the photographer-agent relationship

Udi Tirosh: from diyphotography.netUdi Tirosh is an entrepreneur, photography inventor, journalist, educator, and writer based in Israel. With over 25 years of experience in the photo-video industry, Udi has built and sold several photography-related brands. Udi has a double degree in mass media communications and computer science.

Alex Baker: from diyphotography.netAlex Baker is a portrait and lifestyle driven photographer based in Valencia, Spain. She works on a range of projects from commercial to fine art and has had work featured in publications such as The Daily Mail, Conde Nast Traveller and El Mundo, and has exhibited work across Europe

David Williams: from diyphotography.netDave Williams is an accomplished travel photographer, writer, and best-selling author from the UK. He is also a photography educator and published Aurora expert. Dave has traveled extensively in recent years, capturing stunning images from around the world in a modified van. His work has been featured in various publications and he has worked with notable brands such as Skoda, EE, Boeing, Huawei, Microsoft, BMW, Conde Nast, Electronic Arts, Discovery, BBC, The Guardian, ESPN, NBC, and many others.

John Aldred: from diyphotography.netJohn Aldred is a photographer with over 20 years of experience in the portrait and commercial worlds. He is based in Scotland and has been an early adopter - and occasional beta tester - of almost every digital imaging technology in that time. As well as his creative visual work, John uses 3D printing, electronics and programming to create his own photography and filmmaking tools and consults for a number of brands across the industry.

Dunja Djudjic: from diyphotography.netDunja Djudjic is a multi-talented artist based in Novi Sad, Serbia. With 15 years of experience as a photographer, she specializes in capturing the beauty of nature, travel, and fine art. In addition to her photography, Dunja also expresses her creativity through writing, embroidery, and jewelry making.

Copyright © DIYPhotography 2006 - 2023 | About | Contact | Advertise | Write for DIYP | Full Disclosure | Privacy Policy