Adobe Firefly
Adobe Firefly is a web app and family of generative artificial intelligence models for creative production. Its capabilities include text-to-image and text-to-video.[1] It is part of Adobe Creative Cloud, and also powers features in other Creative Cloud apps, including Photoshop's Generative Fill tool.[2] Its video models are currently being tested in an open beta phase, and its image generation tools are available via subscription.[3][4] Adobe Firefly is developed using Adobe's Sensei platform.[citation needed] Firefly is trained with images from Creative Commons, Wikimedia and Flickr Commons as well as 300 million images and videos in Adobe Stock and the public domain.[5][6][7] This dependency only on training data for which Adobe owns the license or which is public domain has led them to describe the models' output as "commercially safe".[8] Firefly for Enterprise was released on June 22, 2023.[9] HistoryAdobe Firefly was first announced in September 2022 at Adobe's MAX conference. It was initially released as a public beta in March 2023,[10] and is currently available to all Adobe Creative Cloud subscribers. Adobe Firefly is built on top of Adobe Sensei, the company's AI platform. Sensei has been used to power a variety of features in Adobe's creative software, such as object selection in Photoshop and image auto-enhancement in Lightroom. Firefly expanded its capabilities to Illustrator, Premiere Pro, and Express, particularly for generating photos, videos and audio to enhance or alter specific parts of the media. NVIDIA Picasso runs some Adobe Firefly models.[11] Google planned to use Firefly in Bard (now Gemini) as its AI image generator, but ended up using their own Imagen model.[12] Mattel, IBM, and Dentsu have also partnered with Adobe.[13] The demo showed a capability for generating variations of photos.[14] In April 2025, Adobe released Adobe Firefly Image 4 and Firefly Image 4 Ultra Model in Adobe Firefly Web Application.[15][16] References
|
Portal di Ensiklopedia Dunia