Adobe Firefly launches its AI video model in beta with new features & subscription plans

Adobe Firefly has launched its AI-powered video generator, Generate Video, in a public beta release. This tool allows users to create 1080p, five-second video clips using Text-to-Video and Image-to-Video functionalities. Users can customize videos by tweaking style, camera angles, motion, and shooting distances. The output is now rendered at 1080p and 24 FPS, an improvement from the previous 720p quality. Generating a clip takes at least 90 seconds, which is shorter than OpenAI’s Sora's processing time for longer clips.

Adobe plans to enhance Generate Video with a faster, low-resolution ideation model and a high-resolution 4K version. The tool integrates with Adobe's Creative Cloud through the redesigned Firefly web app, facilitating AI asset editing in Adobe Photoshop, Adobe Premiere Pro, and Adobe Express. Firefly's training on public domain and licensed content ensures commercially safe outputs, addressing copyright concerns for filmmakers.

Firefly also introduces new paid features such as Scene to Image for creating reference images and Translate Audio and Video for AI-powered dubbing in over 20 languages. Adobe now offers two subscription plans: Firefly Standard at $9.99 per month for 2,000 video/audio credits and Firefly Pro at $29.99 per month for 7,000 credits. Both plans provide unlimited access to Firefly imaging and vector tools.