Japan Technology

Adobe Firefly introduces “Firefly Video” model with video generation function, beta version available in late 2024 – GIGAZINE



Adobe’s generative AI feature setAdobe FireflySoon, we will be releasing a new video generation feature called “Firefly VideoIt has been revealed that a new model will be added.

Bringing generative AI to video with Adobe Firefly Video Model | Adobe Blog
https://blog.adobe.com/en/publish/2024/09/11/bringing-gen-ai-to-video-adobe-firefly-video-model-coming-soon

Adobe – Adobe Previews Its Upcoming Firefly Video Model
https://news.adobe.com/news/news-details/2024/Adobe-Previews-Major-Advancements-to-its-Upcoming-Firefly-Video-Model/default.aspx


Adobe Firefly Video Model Coming Soon | Adobe Video – YouTube


Adobe has been working closely with the video editing community to evolve its Firefly Video model, a video generation model. With feedback from the community in mind, Adobe is developing new workflows that leverage the model with creators’ rights in mind, empowering editors to invent and explore their creative vision, fill gaps in the timeline, and add new elements to existing footage.

Firefly Text-to-Video allows you to generate videos from text prompts. When generating videos, you can set various camera controls, use reference images, and seamlessly fill gaps in the timeline.B-rollIt is possible to generate


Below is an example of a video and prompt generated by “Firefly Text-to-Video”. Note that all of the videos listed as examples were generated within 2 minutes.

“Cinematic closeup and detailed portrait of a reindeer in a snowy forest at sunset. The lighting is cinematic and gorgeous and soft and sun-kissed, with golden backlight and dreamy bokeh and lens flares. The color grade is cinematic and magical.”

“Slow-motion fiery volcanic landscape, with lava spewing out of craters. the camera flies through the lava and lava splatters onto the lens. The lighting is cinematic and moody. The color grade is cinematic, dramatic, and high-contrast.”

“Miniature adorable monsters made out of wool and felt, dancing with each other, 3d render, octane, soft lighting, dreamy bokeh, cinematic.”

The Firefly Video model is particularly good at generating videos of the natural world, for example when a creator feels that they don’t have enough shots to create a scene, they can generate inserts with camera motion of landscapes, plants, animals, etc.

“Footage of a camera on a drone flying over a desert with wind blowing over the dunes creating waves in the sand below.”

“Drone shot going between the trees of a snowy forest at sunset golden hour. The lighting is cinematic and gorgeous and soft and sun-kissed, with golden backlight and dreamy bokeh and lens flares. The color grade is cinematic and magical.”

In addition, it is possible to output new footage by referring to the original footage.Original footageThe video is based on the above and also uses the text prompt, “Detailed extremely macro closeup view of a white dandelion viewed through a large red magnifying glass.”

“Firefly Image-to-Video” makes it possible to generate videos based on input images.

Base Image


A video based on the image above, output with the text prompt, “Zoom out of the galaxy to reveal that it is contained inside the pupil of a human eye, detailed macroscape.”

Coming to the beta version of Premiere Pro later this year, a new feature called “Generative Extend” will let you extend clips to fill gaps in footage, smooth out transitions, or hold shots longer for perfectly timed edits.

All Adobe Firefly video creation capabilities leveraging the Firefly Video model are designed to be safe for commercial use and will be available in beta in the second half of 2024.

Copy the title and URL of this post

Avatar

Vasundhara Mali

About Author

Leave a comment

Your email address will not be published. Required fields are marked *

You may also like

Japan Technology

It turns out that TikTok’s algorithm may be actively suppressing criticism of the Chinese government

It has been revealed that searching for terms such as “Uighur” and “Tiananmen Square” on TikTok is likely to result
Japan Technology

Even Apple has difficulty centering text in app layouts

Software engineer Martin Wojcik pointed out that the UI of Apple’s native Calculator app on macOS is misaligned. It is