Skip to main content

Adobe releases its first commercially safe Firefly video generating AI

Firefly video still shot of an Icelandic horse
Adobe Firefly

Following on the success of its IP-friendly Firefly Image model, Adobe announced on Wednesday the beta release of a new Firefly Video model, as well as two subscription packages with which to access its audio and video generating abilities. Generate Video, according to the announcement post, “empowers creative professionals with tools to 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.”

The model will initially be able to generate video in 1080p resolution to start, though the company plans to release a 4k model for professional production work in the near future. Like the image generator, Firefly Video is trained exclusively on Adobe stock, licensed, and public domain content, making its outputs usable in commercial applications without fear of them running afoul of copyright or intellectual property protections. And, unlike Grok 2, there’s minimal chance of it outputting racist, offensive, or illegal content.

Recommended Videos

Firefly Video will be accessible both through Adobe Premiere Pro (as the Generative Extend tool) and through a new web application , Firefly.Adobe.com. Users will be able to generate video clips from both text prompts and reference images, as well as add atmospheric effects and custom motion design elements. They’ll even be able to lock in the first and last frames of a clip, “to preserve visual continuity, keep colors and character details consistent.”

The new Scene to Image feature allows users to “seamlessly render production-ready assets” using a 3D sketching tool, converting a creator’s concept art into high resolution images and structure references that can then be used to iterate a generated video clip. Firefly Video can also generate audio to translate spoken dialog into any of 20 languages.

Adobe is rolling out a pair of subscription plans alongside Firefly Video, either of which will grant you full access to the new model. The $10 per month Firefly Standard plan offers 2,000 video/audio credits per month worth as many as 20 5-second video generations at 1080p. The $30 per month Firefly Pro plan, on the other hand, provides 7,000 video/audio credits per month which will get you up to 70 5-second clips at 1080p. Adobe also revealed that a “Firefly Premium” plan is in the works, geared towards professionals looking to generate high volumes of video and audio, though there’s no word yet on what it might cost or when it will be released.

Adobe Firefly Video Model Coming Soon | Adobe Video

Adobe first teased the Firefly video model in April of last year before providing a preview of its capabilities in September. It enters an increasingly crowded market with competition from both premium and free-to use models alike, such as Kling AI, Meta’s Movie Gen, and OpenAI’s Sora.

Andrew Tarantola
Andrew Tarantola is a journalist with more than a decade reporting on emerging technologies ranging from robotics and machine…
The best AI tools of 2024: all the generative AI apps you need to try
Talking with Perplexity chatbot on Nothing Phone 2a.

ChatGPT opened the floodgates. But many people don't realize there's a whole world of generative AI tools and applications out there, just waiting to be explored.

Whether you’re struggling to overcome a case of writer’s block, lack the artistic aptitude to do your imagination justice, or just need a hand crafting efficient computer code, generative AI can help augment and streamline both your professional and creative endeavors. Yet, amid the seemingly endless variety of AI assistants currently on offer, finding the right one for your needs can prove a daunting task. So, let's delve into some of the most impressive AI tools that are pushing the boundaries of innovation, including the best AI chatbots, the best AI image generators, and much more.
The best AI tools for image generation
Midjourney

Read more
OpenAI’s Sora was leaked in protest over allegations of ‘art washing’
An AI image portraying two mammoths that walk through snow, with mountains and a forest in the background.

OpenAI's unreleased Sora video generation model was leaked Tuesday by a group protesting the company's "art washing" actions, per a post from X user @legit_rumors.

The group, calling themselves Sora PR Puppets, reportedly had gained early access to the Sora API. Through that, they leveraged authentication tokens to create a front-end interface enabling anyone to generate video clips with the model. While the project only remained online for around three hours before Hugging Face (or possibly OpenAI itself) revoked access, several users managed to publish their creations to social media sites.

Read more
Get ready for AI-dubbed YouTube videos
YouTube logo on top-left corner of home screen

YouTube has reportedly started rolling out a new AI-empowered translation feature for its content creators, one that will automatically redub a video's contents into one of nine languages without changing the speaker's voice.

According to a post from X user @levelsio, "YouTube will now auto dub videos in English, Spanish, Portuguese, German, French, Italian, Hindi, Indonesian and Japanese" and "will use AI to take the original voice but change the language."

Read more