Adobe's AI Firefly Video Model enters public beta, offering some impressive new video generation and editing features integrated with Creative Cloud apps, plus new tiered subscription plans.
Following announcements and unveilings at Adobe MAX last year, Adobe has taken its new AI Firefly Video Model into public beta. It’s initially available in both a new Firefly web application with Generate Video (beta) and in Adobe Premiere Pro with Generative Extend (beta).
At heart, Generate Video allows creatives to do a range of new things: generate video clips from a text prompt or image, use camera angles to control shots, create professional quality images from 3D sketches, craft atmospheric elements and develop custom motion design elements. At (beta) launch it supports 1080p resolution to start, with both a lower resolution ideation model for high-speed iteration and a 4K model for pro-level production work coming soon.
Here’s the sizzle reel for a whistlestop tour.
There’s a new business model as well with new Firefly plan offerings at tiered price points. More on that in a bit.
Everything integrates with Adobe Creative Cloud applications including Photoshop, Premiere Pro, Express and more as you would expect. And, of course, following Adobe’s established USP Firefly is billed as safe for commercial use, providing creators confidence to use it for production-ready content.
Generate Video (beta). A range of controls provide new levels of precision to fine-tune any shot with detailed camera settings. Adobe’s list mentions sweeping aerial views that frame subjects exactly as envisioned, from dramatic close-ups to expansive long shots, and dynamic movement by selecting from multiple motion paths. Users can also lock in the first and last frames of a shot to preserve visual continuity, keep colors and character details consistent and more.
You can do a lot with 5 seconds. Prompt: "Large and very dense white smoke waves slowly swirling, on a pure black background for compo."
Scene to Image (beta) lets you create professional quality images from 3D sketches and reference shapes. Using a lightweight 3D sketching tool, you will be able to transform artwork into high resolution images, build structure references directly within Text to Image and create precise visual guides using 3D tools. Users can change 3D image angles and perspectives to get the perfect output.
Translate Audio and Video does just what it says on the tin, and allows you to translate spoken dialog into subtitles in multiple languages while maintaining an authentic voice. Adobe says editors will be able to quickly and easily translate videos and audio files with voice, tone, cadence and acoustic match. Translate Audio and Video supports translations in over 20 languages at launch.
We had to play this a couple of times to work out what's going on here
In under two years, Firefly has been used to generate over 18 billion assets globally – an uptick of 50% over the past few months. Using all that processing power costs, and while Creative Cloud subscribers will receive what the company says is a ‘limited taste’ of video and audio generative features starting today, the main aim is to move users onto specific price plans that cover the new features.
The Firefly Standard plan has been designed for creators looking to ideate. With early pricing on February 12, it offers 2000 video/audio credits per month and up to 20 5-second 1080p video generations, at $9.99 for the monthly plan. We’re going to have to play with it all a bit before we work out how far those credits go
Firefly Pro plans also have what Adobe refers to as early pricing and offer 7000 video/audio credits per month and up to 70 5-second 1080p video generations. This costs $29.99 for the monthly plan.
Above and beyond this, Adobe says a Firefly Premium plan will also be coming soon for professionals looking to generate video content on a regular basis to provide even more audio and video capacity for high-volume creators and teams. Pricing and availability of that is firmly TBA.
tl;dr
- Adobe's AI Firefly Video Model is now in public beta, featuring video generation and editing tools integrated with Creative Cloud apps and new tiered subscription plans.
- The Generate Video (beta) feature allows users to create video clips from text prompts or images, control camera angles, and develop custom motion design elements, supporting 1080p resolution at launch with plans for 4K support soon.
- Scene to Image (beta) enables the generation of professional-quality images from 3D sketches, while Translate Audio and Video offers subtitle translations in over 20 languages, maintaining natural voice characteristics.
- Firefly Standard and Pro subscription plans provide video/audio credits and video generation opportunities, with early pricing at $9.99 and $29.99 monthly, respectively, and a Firefly Premium plan for high-volume creators set to be announced later.
Tags: Post & VFX AI Adobe
Comments