Adobe today unveiled the expansion of its Firefly range of creative generative AI models into video at Adobe MAX, the world’s largest creativity conference. In addition, they have added improvements to their Image, Vector and Design models, as well as a notable increase in the adoption of Firefly by leading brands and companies.
The Firefly Video Model, now in limited public beta, is the first video model designed to be commercially secure. Since its initial beta launch in March 2023, Firefly has generated more than 13 billion images, an increase of more than 6 billion in the last six months.
“The use of this system in our creative applications has been adopted massively, and it is inspiring to see how the creative community has used it to push the limits of what is possible,” says Ely Greenfield, Chief Technology Officer of Digital Media at Adobe. “We’re excited to offer creative professionals even more tools for ideation and creation, all designed to be commercially secure.”
New possibilities powered by Firefly
The Firefly video model (beta) expands Adobe’s family of generative AI models, which already includes an image model, a vector model, and a design model, making the app the most comprehensive model offering for teams. creatives. It is currently available through a limited public beta to receive initial feedback from a select group of creative professionals, which will help refine and improve the model.
A year after its release, it has been integrated into Photoshop, Express, Illustrator, and Substance 3D, among others, and supports various workflows in Creative Cloud applications. Firefly can also support text prompts in more than 100 languages, allowing users around the world to create stunning content with a design that is safe for commercial use.
Enhancements to Firefly models include 4x faster image generation and new capabilities built into Photoshop, Illustrator, Adobe Express and now Premiere Pro
New Firefly features in Creative Cloud available today
- Generative extension (beta) for perfectly synchronized video editsPowered by the Firefly video model and now available in the beta version of Premiere Pro, Generative Stretch lets you extend clips to fill gaps in your footage, smooth transitions, or hold shots longer for perfectly timed edits.
- Text to Video and Image to Video (beta) for improved user controls and stunning video clips: Powered by the Firefly Video Model and now in limited public beta in the Firefly web app, creators can access the new Text to Video and Image to Video features. With Text to Video, video editors can generate video from text prompts, access a variety of camera controls such as angle, pan and zoom to adjust videos, and reference images for generating B-Roll that They perfectly fill in the gaps in a video timeline. Image to Video features allow creators to bring still images or illustrations to life by transforming them into stunning live-action clips.
- Improvements in Firefly Image 3 to render faster: With the latest evolution of the Firefly Image 3 model, creators of all levels can create images in seconds with results up to 4 times faster than previous models, available today in the Firefly web app.
- Generative workspace (beta) in Photoshop: Powered by Adobe Firefly, the Generative Workspace in Photoshop allows designers to ideate, brainstorm, and iterate concepts simultaneously to achieve their vision, while producing stunning visuals faster and more intuitively than ever.
- Firefly Vector Model (beta) Advances in Illustrator: Adobe Illustrator introduced Generative Shape Fill (beta), Replacement Color Generation, and Text to Pattern earlier this year, all powered by the latest version of Firefly Vector Model (beta), empowering designers to come up with or Quickly add detailed vectors in your own style to existing illustrations and designs. With the latest version of Firefly Vector Model, creators can further control the density of elements in the same pattern to change the concentration of elements.
Large-scale content creation with new offers for companies
Additionally, at Firefly Services, the company introduced new offerings that enable production workflows to scale. This includes Voiceover and Lip Sync, now in beta, which uses generative AI for video content to translate spoken dialogue into different languages, maintaining the original voice sound with lip sync accordingly.
Additionally, “BulkCreate, powered by Firefly Services” is now also in beta and will allow creative professionals to edit large volumes of images more efficiently, simplifying tasks such as resizing or removing the background.
Drive responsible innovation with Adobe Firefly
The system powers generative AI tools designed for creative needs, use cases and workflows. Adobe has trained its Firefly generative AI models with licensed content, such as Adobe Stock and public domain content. Additionally, Adobe’s AI capabilities are developed in accordance with the company’s AI Ethics principles of responsibility, commitment, and transparency.
Since founding the Content Authenticity Initiative in 2019, Adobe has promoted the widespread adoption of Content Credentials as an industry standard to ensure the transparency of digital content, now supported by more than 3,700 members. Content Credentials, which act as a “nutrition label” for digital content to show how it was created and edited, are applied to certain features powered by Firefly in Creative Cloud to indicate the use of generative AI.
Price and availability
The Firefly Video Model is in limited public beta at firefly.adobe.com.
