Adobe 'Project Fast Fill' And 'Project Stardust' Make Image And Video Editing An AI Childsplay

Adobe Firefly

Adobe is going full throttle, and AI is its focus.

Piggybacking the generative AI hype that was kickstarted by the introduction of OpenAI's ChatGPT, Adobe jumped in to the bandwagon by introducing Firefly, an AI purposefully designed to power its design tools.

After bringing the AI tool to Photoshop, and embedding it to Illustrator, this time, Adobe is experimenting with both image and video design.

Calling it 'Project Stardust' and 'Project Fast Fill', the tools allow users to easily add or remove objects with the power of AI, in images and videos, respectively.

Announced during the company’s MAX conference. Project Stardust has the ability to for still photos, swap in clothing accessories on people, or remove tourists from the background, and more.

"Create natural, photo-realistic results of anything you can imagine with AI-based auto-masking, harmonization, synthesis and more," said Adobe, adding that with the AI has "human-level understanding of objects and scenes" to allow users create things they way they think.

Powered by generative AI, all users need to do is enter a text prompt.

"Super low learning curve and open-ended creativity let you explore your ideas fearlessly," added Adobe.

As for Project Fast Fill, the AI tool allows users to move around people or objects inside videos.

Adobe said that these generative AI features are made possible by the company’s updated Firefly AI models.

And not only that, because Adobe is working on its AI editing tech for other purposes as well.

On its announcement, Adobe has what it calls:

  • 'Project See Through' that makes it simple to remove reflections from photos.
  • 'Project Dub Dub Dub' which can help users automate video dubbing process.
  • 'Project Scene Change' to composite a subject and scene, from two separate videos captured with different camera trajectories, into a scene with synchronized camera motion.
  • 'Project Res Up' to easily converts video from low- to high-resolution using diffusion-based upsampling technology.
  • 'Project Poseable' which can interact with large 3D objects, including poses from photos of real people.
  • 'Project Neo' that can incorporate 3D shapes in 2D designs.
  • 'Project Glyph Ease' that can automate the process of creating glyphs.
  • 'Project Draw & Delight' as a suite of generative AI tools that helps users transform initial ideas - often represented as rough doodles or scribbles - into refined sketches.

There is also the 'Project Primrose', which showcases the potential of flexible textile displays, with the ability turn clothes into creative canvases.

"This interactive dress can offer infinite style possibilities, displaying content created with Adobe Firefly, After Effects, Stock,and Illustrator," said Adobe.

Published: 
16/10/2023