The AI field was quite dull, and boring, and kind of slow-paced. But things have changed.
It all stared when OpenAI introduced ChatGPT as a AI chatbot tool. The AI is able to do a wide range of tasks with human-like capabilities, including writing poetry, technical papers, novels, and essays.
After it managed to captivate the internet, the rest is history.
OpenAI has made other tech companies to race and create their own versions of generative AI, and as for Adobe, it's generative AI is called 'Firefly'.
After releasing the Firefly as a text-to-image generative AI model, this time, Adobe is announcing 'Firefly Text-to-Video.'
In a blog post:
"Missing shots are no problem for your timelines now! With detailed prompting, you can generate a compelling insert shot to use in your final project."
During Adobe Max, the company's annual creative conference, Adobe shows that it's joining other big tech companies and startups in trying to capitalize on demand for the emerging technology.
Adobe first announced its Firefly video tool in September, and according to the company, "our top community leaders" that have been given early access are already generating "incredible Text-to-Video and Image-to-Video creations that push the boundaries of generative video and human ingenuity."
This time, Adobe is releasing the tool to the public in beta on Firefly web app.
It's also integrated into Premiere Pro, where users can use it for generative extend, a feature that lets users create new video clips, including video and audio.
It's supposed to help creators when they need a few extra frames, want to smooth out a transition or hold onto a shot for longer.
With Firefly Text-to-Video, users can use text prompts, a wide variety of camera controls, and reference images to generate B-Roll that seamlessly fills gaps in your timeline.
"Missing shots are no problem for your timelines now! With detailed prompting, you can generate a compelling insert shot to use in your final project," said Adobe.
Use cases, for example, include visualizing creative intent for difficult-to-capture or expensive shots.
Traditionally, this is challenging for teams working on tight budgets and quick turn arounds. Using Adobe Firefly's AI, the team can visualize and plan these shots before going into VFX or back to set for pick-up shots helps to streamline communication between production and post-production.
This is possible because the AI can be used to both create a new video from scratch, or modify existing videos through various of possible customizations.
On top of that, the Firefly Video is also an Image-to-Video model, meaning that it can create AI-generated video from just one reference image, and a text prompt.
"You can easily create a complementary shot for existing content, such as a close-up, by uploading a single frame from your video," said Adobe.
Or create new b-roll from still photography, breathing new life into your library of existing images.
The creative industry has been rocked by the advance of generative AI, which has become increasingly commonplace in creative software.
While this benefits creators, it also becomes an increasingly a controversial topic due to the fact that these AIs are trained using copyright content.
As a result, some creative artist are already taking legal actions against AI companies, particularly around copyright infringement concerns, others are trying to discern what uses, if any, there are for AI in creative spaces.
For Adobe, the company is trying to play safe, with a bit of fire.
Adobe said that its Firefly Video shall be the first publicly available commercially safe video model, trained on Adobe Stock and other public databases. In the app, Firefly can also transform reference images into B-roll footage and handle 2D and 3D animation.
"We know that creating with confidence is critical to you and your clients or collaborators. Just like our other Firefly generative AI models, Adobe Firefly Video model is designed to be commercially safe and is only trained on content we have permission to use — never on Adobe users’ content,." Adobe said.