Connect with us

Camera

Adobe introduces AI-generated video, integrated into Premiere

Published

on

Adobe introduces AI-generated video, integrated into Premiere


Adobe’s Firefly video generation panel.

Screenshot: Adobe

Adobe has announced Firefly Video, an AI model that can generate video footage that the company says is designed “to be commercially safe” and to “not infringe on others’ IP.” Some of the generative AI features are being integrated into the company’s editing software, Premiere Pro.

Premiere Pro is also getting several updates unrelated to the AI features; click here to jump to the section about those.

Perhaps the most useful feature Adobe showed off in its keynote address at its Max conference is Generative Extend. The feature is meant to continue video or audio clips after the end of the actual recording or cut, generating a few extra seconds of footage or room tone to help fill in gaps. The plan is to build it into Premiere Pro, so you can extend your footage straight from your timeline. Like most of Firefly’s video abilities, the feature will be launched as a beta.

You can generate new footage to fix eyelines, fill in gaps, or help smooth out a J/L cut, straight from the timeline.

Image: Adobe

There will initially be a few limitations: the most notable is that the beta version can only generate 720p or 1080p 16:9 video at framerates between 8 and 30fps. It also only works with 8-bit and SDR video.

The company also showed off Firefly’s ability to ‘animate’ still images, turning them into video, though that feature will launch on the web version of the tool, not in Premiere. The tool can also generate video assets along with actual footage. The company showed Firefly-generated light leak artifacts that were added to a conventionally-shot video, as well as AI-generated animation and text graphics.

‘Filmic’ light leaks generated by Firefly that could then be composited on top of existing footage. AI-Generated Image: Adobe

Of course, Firefly Video can also generate footage whole-cloth based on text prompts from the user. The UI gives people several ways to control the video that’s generated, letting them pick an aspect ratio and frame rate, as well as specify what kind of framing, angle, and motion they want. However, Adobe says its customers are generally more interested in how generative AI could help them edit human-created content than using the tech to create something from scratch.

Adobe stresses that it has trained the model “responsibly,” using “licensed content” from Adobe Stock and the public domain. Representatives for the company said it was not trained on data scraped from the web or customer data, practices that have been controversial with other generative AI models.

The company also says that footage generated or edited with Firefly will automatically have Content Credentials attached, tagging it as being created with AI. However, similar to images created using the system, it currently falls to the user to manually check a video’s veracity, as most platforms don’t interpret the Content Credentials metadata.

Premiere Pro updates

Image: Adobe

Adobe also announced that it’s adding a new ‘context-aware properties panel,’ which will attempt to surface the most useful tools based on what you’re currently working on.

The company has also updated the Frame.io panel, saying that the new version will make it easier to track reviews and approvals. On that note, Adobe also announced that Canon, Nikon, and Leica are adding support for Frame.io’s Camera-To-Cloud feature, which lets cameras automatically upload footage to the service without needing to manually offload it to a computer. There are currently no details on which camera models will support it.

Premiere is also getting a performance bump, with the company promising that it’ll be able to export to ProRes up to three times faster. The app is also getting a bit of a redesign, which the company says will make it feel “modern and more consistent.”


We’re attending Adobe Max, so keep an eye out for demos of some of these features. If you want to follow along live, check out our Instagram page.





Source link

Continue Reading
Click to comment

Leave a Reply

Camera

DJI's new dual-camera Air 3S drone gets a larger sensor and LiDAR

Published

on

By

DJI's new dual-camera Air 3S drone gets a larger sensor and LiDAR


Photo: DJI

DJI has announced the Air 3S, an update to its existing dual-camera Air 3 model that upgrades the primary camera to a larger Type 1 sensor and adds features that promise to make the drone easier to operate at night. DJI is positioning the Air 3S as “perfect for travel photography.”

The main camera on the Air 3S gains a 50MP Type 1 (13.2 x 8.8mm) CMOS sensor and features a 24mm equiv. F1.8 lens. That’s an upgrade from its predecessor, which utilized a smaller Type 1/1.3 (4.8 x 3.6mm) CMOS sensor with a marginally faster F1.7 lens. The telephoto camera remains unchanged between the two models, using a 48MP Type 1/1.3 sensor and featuring a 70mm equiv. F2.8 lens.

In addition to stills, both cameras can capture up to 4K/120p or 4K/60p when shooting HDR. All video can be captured in 10-bit, even in regular color mode, and D-Log M and HLG modes are available. The maximum ISO has been raised to 12,800 (3200 when shooting D-Log M). However, DJI says the Air 3S includes a new, more advanced video encoding algorithm that reduces video file size by over 30% without compromising image quality.

DJI claims both cameras can capture up to 14 stops of dynamic range and says the new main camera should capture even more detail than the camera on its more expensive Mavic 3 Pro model.

The DJI Air 3S is similar to its predecessor, the Air 3, but it gains a larger Type 1 (13.2 x 8.8mm) CMOS sensor on its main camera.

Image: DJI

Beyond the cameras, DJI has added several appealing features to the Air 3S:

A new Free Panorama mode enables users to create panoramic shots by stitching together images across a manually selected subject area. This works with either camera, but DJI suggests the best results will come from using the telephoto camera, which reduces distortion.

The Air 3S also includes features designed to make it easier and safer to fly at night, including Nightscape Obstacle Sensing, with the Air 3S becoming the first DJI drone to feature forward-facing LiDAR. Additionally, the drone includes downward-facing infrared sensors and six vision sensors (two each at the front, rear and bottom). According to DJI, this combination of sensors provides the Air 3S with “nightscape omnidirectional obstacle sensing,” which should allow the drone to automatically identify and navigate around obstacles for safer nighttime photography.

This technology also enables DJI’s next-gen Smart RTH (return-to-home) feature, intended to allow the drone to return safely to its takeoff location, even at night.

The Air 3S is available with either DJI’s RC-N3 controller, which requires a smartphone to monitor the camera feed and aircraft status, or the RC 2 controller (above), which includes a built-in 700-nit 5.5″ 1080 screen.

Image: DJI

The Air 3S also includes real-time vision positioning and map construction technology, designed to allow the drone to memorize a flight path and to return safely when adequate light is available, even in areas without satellite coverage.

The new model also features DJI’s ActiveTrack 360 subject tracking but introduces a new subject focusing feature designed to keep a subject in sharp focus, even during manual flight or when a subject moves off-center. This should allow a pilot to focus on creative decisions like composition or camera movement while ActiveTrack keeps the subject in focus.

There are a few hardware specs worth noting as well. The Air 3S weighs 724g (1.6 lbs), just 4g more than its predecessor, and is rated for 45 minutes of flight time. It includes DJI’s O4 video transmission system that transmits 10-bit video at up to 1080/60p and 42GB of built-in storage. A new Off-state Quick Transfer feature allows files to be transferred from the drone to a smartphone or a computer even when powered off.

Finally, for the privacy-conscious, a new Local Data mode completely disconnects the drone from the internet, ensuring that all data stays only on the device. DJI likens this mode to airplane mode on a smartphone.

The Air 3S is available in several packages. The Fly More combo shown above includes the RC 2 controller, ND filter set, two additional batteries (for a total of three), a charging hub, extra props and a shoulder bag, will retail for $1599.

Image: DJI

The charging hub that ships with the Air 3S supports PD fast charging and features a power accumulation function. It allows users to transfer the remaining power from several depleted batteries into the battery with the most remaining power – something anyone who has had to use drones in remote locations without a charging station is likely to appreciate.

Price and availability

The DJI Air 3S is available for purchase in several configurations: the drone with the RC-N3 controller, which requires a smartphone to monitor the camera feed and flight status, will retail for $1099. A Fly More combo with the RC-N3 controller, ND filter set, two additional batteries, a battery charging hub and shoulder back will retail for $1399. Finally, a Fly More combo with DJI’s RC 2 controller, which includes a built-in 700-nit 5.5″ 1080p screen, ND filter set, two additional batteries, charging hub and shoulder pack, will retail for $1599.



Source link

Continue Reading

Camera

Canon announces new RF L lenses are coming on October 30

Published

on

By

Canon announces new RF L lenses are coming on October 30


This teaser image, released by Canon, shows its existing RF L-series lenses, the RF 24-105mm F2.8 L IS USM Z and the RF 35mm F1.4 L VCM alongside three new mystery lenses.

Image: Canon

Canon has announced plans to introduce new lenses to its hybrid RF-L series on October 30. No additional details were provided.

However, a teaser photo released with the announcement offers some hints. It shows five lenses, including the two previously announced RF L-series lenses: the RF 24-105mm F2.8 L IS USM Z, a fast wide to moderate telephoto zoom, and the RF 35mm F1.4 L VCM prime lens. The implication is that we can expect to see three new lenses, possibly a zoom and a couple of smaller primes.

The RF 24-105mm F2.8 L IS USM Z was the first lens in Canon’s RF L series of hybrid lenses. Unlike any EF or RF lens before it, it includes a manual aperture ring.

Image: Canon

According to Canon, its RF L-series of lenses are designed to meet the needs of both still photographers and video shooters, borrowing design elements from both its existing RF lenses as well as technology from the company’s broadcast and cinema lenses.

Previously announced RF L lenses include manual aperture rings, something that hadn’t previously appeared on Canon EF or RF lenses, and include support for stepless aperture control, a feature desired by filmmakers. The lenses are also designed to minimize focus breathing.

We’ll hold our breath until Canon provides more details at the end of the month.



Source link

Continue Reading

Camera

Nikon says future firmware will add Content Credentials to Z6III mirrorless camera

Published

on

By

Nikon says future firmware will add Content Credentials to Z6III mirrorless camera


When you use DPReview links to buy products, the site may earn a commission.
Photo: Richard Butler

One of the announcements to quietly sneak out of Adobe’s annual MAX conference this week in Miami comes from Nikon, which announced that it is currently developing firmware to add a feature called Content Credentials, which is based on the standards developed by the Coalition for Content Provenance and Authenticity (C2PA), to the Z6III mirrorless camera.

“Nikon is committed to developing solutions, including compliance with C2PA standards, with the goal of protecting individuals and enterprises in the imaging industry, and ultimately society, from any unfavorable results caused by fake images and/or unauthorized use of images,” states the company’s official press release. “Our aim is to implement a mechanism that preserves original, unaltered image data recorded using the camera, making it easier to verify the authenticity of images and protect the rights of photographers.”

Nikon has been working on content authenticity since at least 2022, revealing earlier this year that it’s working with Agence France-Presse (AFP) to test a digital watermark function as an additional layer to the C2PA digital signature. Nikon also reiterated the importance of content authenticity when DPReview visited Nikon headquarters for an interview in February in which we discussed the challenges of generative AI.

In an interview at Nikon’s headquarters in Tokyo earlier this year, Yusuke Adachi, an executive from Nikon’s Imaging Business Unit, reiterated the importance of having a system to validate the authenticity of images.

Photo: Dale Baskin

“We believe that generative AI can leave a positive impact on both cameras and the industry as a whole, but at the same time, it’s been causing issues such as fake images or fraudulent use of images, which leads to the issue of credibility and confidence,” Yusuke Adachi, an executive from Nikon’s Imaging Business Unit, told us. “In order to grapple with these issues, we’ve been working on technology to record histories of captured images. Right now, we’re in the demonstration phase to verify and validate the efficacy of these functions we’re trying to deploy together with AFP (Agence France-Presse).”

According to Nikon, the firmware currently under development for the Z6III should reflect the results of testing the system’s practicality as part of a news agency workflow and is expected to be released to some news and other agencies in mid-2025. Nikon did not indicate when these features may be available to non-agency photographers.



Source link

Continue Reading

Trending