Adobe today previewed an array of generative AI (Artificial Intelligence) powered innovations, including Project Stardust, an object-aware editing engine that could revolutionise photo, video and graphic designing.
Project Stardust streamlines image editing with GenAI, affording its users an effortless means to select, transform and even delete intricate components in any image. The tool allows users to modify a photograph's elements, change the colour of clothing or relocate figures within a photo, treating flat images like multi-layered files. Adobe suggests this intuitive engine could make graphic designing far more efficient, accessible and user-friendly.
"Adobe Sneaks are a can’t-miss, fan-favourite moment at MAX every year, and for good reason – nothing is more inspiring than brilliant employees demonstrating cutting-edge technologies that might power future Adobe products", Gavin Miller, the vice president and fellow of Adobe Research explained. Alluding to the showcased products, he added, "Our passion for creators is at the heart of each Sneak, and this year’s showcase highlights exciting new ways generative AI and 3D technologies can supercharge creative expression, reimagining what Adobe tools make possible."
Adobe's latest innovations for its Firefly tool, a suite of commercially available creative, generative AI models, also received noteworthy mentions. The innovations have broadened the applications of generative AI beyond image creation and are set to decrease post-production timelines significantly.
One of the notable tools for image manipulation is Project See Through. This AI-driven technology conveniently eliminates glass reflections from photos, often a common nuisance that ruins image quality.
Further, Project Fast Fill and Project Dub Dub Dub are set to transform the realm of video and audio. Project Fast Fill leverages Adobe Photoshop's Generative Fill technology that allows human-prompted generative AI capabilities within Adobe's video editing tools, such as Premiere Pro and After Effects. In contrast, Project Dub Dub Dub simplifies the traditionally challenging video dubbing process with AI-enabled automatic translation of original dialogues into various languages.
Expanding the scope of design and development beyond 2D, Adobe also previewed Project Poseable and Project Neo. These projects simplify 3D image generation and enhance the integration of 3D shapes in 2D designs, respectively. Additionally, there was Project Primrose, blending tech and fashion by turning clothing into an interactive display. These next-generation technologies are expected to open up new creative possibilities, making complex design projects more accessible.
Finally, streamlining glyph design, Adobe introduced Project Glyph Ease. Beginning with a hand-drawn letter shape, the AI automatically generates a complete set of glyphs, matching the input lettering style. The tool is expected to make customised lettering more accessible and reduce the complexity associated with glyph design dramatically.