Editor's note: This post is part of the AI Decoded Serieswhich demystifies AI by making the technology more accessible and showcases new hardware, software, tools, and accelerations for RTX PC users.
Adobe Creative Cloud applications that take advantage of NVIDIA RTX GPUThey are designed to enhance users’ creativity, allowing them to work faster and focus on their craft.
These tools integrate seamlessly into creators’ existing workflows, enabling increased productivity and delivering power and precision.
Look towards the light
Generative AI Create new data in formats such as images or text from existing data. Efficiently visualize and generate content to match what a user describes and help open new avenues for creativity.
Adobe Firefly is Adobe’s family of creative generative AI models that deliver new ways to ideate and create, while helping creative workflows with generative AI. They are designed to be safe for commercial use and were trained, using NVIDIA GPUs, on licensed content such as Adobe Stock Images and public domain content where the copyright has expired.
Firefly features are integrated into Adobe's most popular creative applications.
Adobe Photoshop has the following features: Generative fill tool, which uses simple descriptive prompts to easily add content from images. With the latest reference image feature currently in beta, users can also upload a sample image to get image results closer to the desired outcome.
Generative Expand allows artists to extend the edge of their image with the Crop tool, filling larger canvases with new content that is automatically blended with the existing image.
RTX-accelerated neural filters like Photo Restoration enable complex adjustments like colorizing black-and-white photos and AI-powered style transfer. The Smart Portrait filter, which enables non-destructive editing with filters, is based on the work of NVIDIA Research.
Adobe Illustrator’s new Generative Shape Fill beta, based on the latest Adobe Firefly vector model, enables users to accelerate design workflows by quickly filling shapes with details and colors in their own styles. With Generative Shape Fill, designers can easily match the style and color of their own artwork to create a wide variety of editable and scalable vector graphics options.
Adobe Illustrator Generative Recoloring This feature allows creators to type a text message to explore custom color palettes and themes for their vector artwork in seconds.
NVIDIA will continue to work with Adobe to support advanced generative AI models, with a focus on deep integration into applications used by the world’s leading creators.
Making moves on video
Adobe Premiere Pro is one of the most popular and powerful video editing solutions.
Its RTX-accelerated Enhance Speech tool uses AI to remove unwanted noise and improve the quality of dialogue clips so they sound like they were professionally recorded. It’s up to 4.5x faster on PCs with RTX.
Auto ReframingAnother Adobe Premiere feature, it uses GPU acceleration to identify and track the most relevant elements in a video, and intelligently reframes video content for different aspect ratios. Scene edit detection automatically finds the original edit points in a video, a necessary step before the video editing stage begins.
Visual effects
Separating a foreground object from a background is a crucial step in many compositing and visual effects workflows.
Adobe After Effects has a new feature that uses a matte to isolate an object, enabling features like background replacement and selectively applying effects to the foreground.
Using the Broken brush With this tool, artists can draw strokes in representative areas of foreground and background elements. After Effects uses that information to create a segmentation boundary between foreground and background elements, allowing for cleaner cuts with fewer clicks.
Creating 3D product photography
Substance 3D Collection is Adobe’s solution for creating, texturing, and rendering 3D materials, enabling users to quickly create incredibly photorealistic 3D content, including models, materials, and lighting.
Visualizing products and designs in the context of a space is an engaging experience, but finding the right environment for objects to live in can be time-consuming. Substance 3D Stager's Generative background This feature, developed by Adobe Firefly, solves this problem by allowing artists to quickly explore generated backgrounds to compose 3D models.
Once an environment is selected, Stager can automatically match the perspective and lighting to the generated background.
Creating materials with AI
Adobe Substance 3D Sampler, also part of the Substance 3D Collection, is designed to transform images of surfaces and objects into photorealistic physically rendered (PBR) materials, 3D models, and high dynamic range ambient lights. With the recent introduction of New generative workflows powered by Adobe FireflySampler makes it easier than ever for artists to explore variations when creating assets for everything from product visualization projects to the latest AAA games.
Sampler’s Text-to-Texture feature allows users to generate tiled images from detailed text cues. These generated images can then be edited and transformed into photorealistic PBR materials using the machine learning-powered Image-to-Material feature or any of Sampler’s filters.
Image-to-Texture also allows for the creation of tiled textures from reference images, providing an alternative way to generate variations from existing visual content.
Sampler's Text to Pattern feature uses text cues to generate tile patterns, which can be used as base colors or inputs for various filters, such as the Fabric Weave filter for creating original fabric materials.
All of these generative AI features in Substance 3D Collection, powered by RTX GPUs, are designed to help 3D creators ideate and create faster.
Photo-tastic features
Adobe Lightroom AI Raw details This feature produces sharper details and more accurate representations of edges, improves color reproduction and reduces artifacts, enhancing the image without changing its original resolution. This feature is useful for large displays and prints, where fine details are visible.
super resolution Helps create an enhanced image with similar results to Raw Details, but with twice the linear resolution. This means that the enhanced image will be twice the width and height of the original image, or four times the total pixel count. This is especially useful for increasing the resolution of cropped images.
For faster editing, RTX-accelerated, AI-powered masking tools like Select Subject, which isolates people in an image, and Select Sky, which captures the sky, allow users to create complex masks with the click of a button.
Visit Adobe AI Features Page for a full list of AI features that use RTX.
Looking for more AI-powered content creation apps? Consider NVIDIA Streamingthat transforms any room into a home studio, free for RTX GPU owners.
Generative AI is transforming gaming, video conferencing, and interactive experiences of all kinds. Find out what's new and coming by subscribing to the AI Decoded Newsletter.
