Adobe has added new enhancements to its Firefly Video Model through improved motion fidelity and advanced video controls plus additional generative AI partner models.
The new additions enable users to generate dynamic landscapes, whether they be natural vistas or urban environments, complete with atmospheric elements like weather patterns and particle effects, and both 2D and 3D animation. Users can choose to output their content in a format that best suits its end usage by easily selecting vertical, horizontal or square aspect ratios to match mobile, widescreen, or social applications. They can also upload a reference video, describe their vision, and Firefly will generate a new video that transfers its style the resulting composition. They can also take advantage of presets like claymation, anime, line art, or 2D to instantly set the tone. Generate Sound Effects (beta) makes it easy to create custom sounds, like a lion’s roar or ambient nature sounds, to enhance the visuals. Just type a simple text prompt to generate the sound effect you need; and like other Firefly generative AI models, Generate Sound Effects (beta) is commercially safe.
Text to avatar (also offered in beta format), lets users turn scripts into engaging, avatar-led videos in just a few clicks. The results can be customised with a colour, image or video plus an accent to suit the video. Keyframe cropping will automatically select how the video will be cropped when the first and last frames are uploaded, based on fitting it to a selected format. Composition Reference and Style Presets are additional tools for improving storytelling. Click here to explore the new features in Firefly and stay up-to-date with the latest developments.
