woman in front of a rainbow cloud image created with object aware editing

Adobe Fast Tracks Artificial Intelligence to All Creative Applications

Adobe has jumpstarted a sweeping movement to artificial intelligence — now including major new generative AI technology into its video, audio, photo and 3D creation software.

At Adobe’s annual MAX conference held Oct. 10 -12th in Los Angeles, the company showcased eleven new generative AI capabilities across photo, video, audio, 3D, design, photographic and fashion design applications.

The company previewed Project Stardust, a generative AI-powered editing engine that lets users move or remove objects simply by clicking on them. There are also new generative fill applications for video, 3D and dynamic display models. These tools offer infinite styling possibilities based on other works for image workers with less creation skills.

Project Stardustenables users to select, edit and even delete complex elements in any image, making image editing more intuitive, accessible and time efficient for any user. For example, the technology lets users select persons in a photograph, move them to a different place in the composition and fill in the background where they were previously standing.

Ordinary users can also change elements like the color of a person’s clothing or the position in which they’re standing – treating any flat images like a file with layers.

Adobe’s suite of applications has changed more rapidly in the past year than since their original introduction. “This year we highlight new ways generative AI and 3D technologies can supercharge creative expression, reimagining what Adobe tools make possible,” said Gavin Miller, vice president and fellow of Adobe Research.

With Firefly, Adobe’s family of creative generative AI models, the range and scope of new applications scales beyond image generation. AI can have a major impact on video, audio, animation and motion graphics workflows. Users without A/V training can master these processes and cut production time from days to minutes.

In video and audio applications, Firefly generative AI is brought to video for the first time in text prompts in Premiere Pro and After Effects video editing tools. Project Dub Dub Dubautomates the video dubbing process, making a historically labor and cost intensive task as easy as clicking a button.

Project Dub Dub Dub uses AI recording or the audio track of a video to be automatically translated to all supported languages while preserving the voice of the original speaker. It can be temporally aligned with the original dialog and is ready to publish. 

Project Scene Change allows video editors to composite a subject and scene, from two separate videos captured with different camera trajectories. Project Res Up is a tool that converts video from low- to high-resolution using diffusion-based upsampling technology.

Video stories can be crafted with the same editing and trimming tools used by cinematic professionals. Quickly insert and add clips from bins or drag clips between multiple timelines, use three- and four-point editing and create “J” and “L” cuts with ease. Trim and tighten with tools such as ripple, roll, slip and slide. Use built-in templates and transitions for video. Use color grading and correction to maintain a consistent look throughout a video.

Two new AI-enabled audio technologies are now in the Adobe Premiere video editing app. Auto-generate the transcript and highlight text to add clips to the timeline — then refine, reorder and trim clips — similar to editing a text document. For further refinement, clear all awkward pauses with bulk deletion and use filler-word detection to remove unwanted filler words, like “ah” and “ugh.”

If an audio clip has excessive background noise, distortion or another sonic problem, hit an AI-powered Enhance Speech button to remove distracting background noise and improve the quality of the dialog. In a MAX demo, a clip had a lot of background noise from a background party. The AI cleaned up the audio perfectly with one push of a button.

New AI-based image generation models make it possible for the image generator to interact with large 3D objects. Project Poseable can create a 3D rendering from text input, take depth and perspective into consideration and re-align the object.

Project Neo enables creators to incorporate 3D shapes into 2D designs — without requiring technical expertise in 3D creation tools. Today, creators of 2D designs such as infographics, posters or logos are often limited in their ability to incorporate 3D elements given the complexity of those workflows, which can require years of experience. Project Neo enables neophytes to embrace simplified 3D design within 2D tools and methods. Project Primrose blurs the line between technology and fashion, demonstrating the potential for flexible textile.

A suite of generative AI tools helps anyone along their creative journey, from transforming initial ideas – often represented as rough doodles or scribbles – into polished and refined sketches. They allow further experimenting with color palettes, style variations and different backgrounds. 

Finally, in Photoshop, there’s a powerful new object-aware editing tool that revolutionizes image editing and moves or removes objects simply by clicking on them. Users can select, edit and delete complex elements in any image – enabling them to select persons in a photograph, move them to a different place in the composition and fill in the background where they were previously standing.

Editors can change elements like the color of a person’s clothing and the position in which they’re standing – treating any image like a file with layers. This AI-powered tool also makes it simple to remove reflections from photos.

Adobe also upgraded Premiere Pro social and video publishing features, adding Facebook, TikTok and YouTube integrations. The software includes project templates designed specifically for social media and new export presets with direct integration for posting to popular video and social media platforms.

Though Adobe kept insisting at MAX that artificial intelligence is there only to assist the creative process, there is also little doubt it will also enable the process for many less than creative users. The skills necessary for entry will be lowered.

Like it or not, Adobe made clear that its future is AI. There is no stopping it. It’s here today and getting more powerful by the month.


Tax Incentives Won’t Solve Hollywood’s Problems
“Taking the wrong boy was a lucky break. In other words, this …
LOTR Cinematography: Lighting Techniques Explained
How does lighting shape storytelling in The Lord of the Rings? From …

Enjoying the news? Sign up for the Creative COW Newsletter!

Sign up for the Creative COW newsletter and get weekly updates on industry news, forum highlights, jobs, inspirational tutorials, tips, burning questions, and more! Receive bulletins from the largest, longest-running community dedicated to supporting professionals working in film, video, and audio.

Enter your email address, and your first and last name below!

Sign up:

* indicates required

Responses

We use anonymous cookies to give you the best experience we can.
Our Privacy policy | GDPR Policy