Logo Logo
deutsch
directory schraeg
Knowledge

Hardware
Actioncam / 360°· Camcorders· Cinema-Kamera· Kamera(technik)· Kamera-Zubehör· Kameradrohnen· Lenses· Smartphone-Kamera· Video-DSLM/DSLR
Software
Compositing· Color correction· DV Editing
DV-Movies

HowTo
Filmmaking· Generative KI
Misc
Audio· Live-Streaming· Sonstige
/// News
Meta Emu Video / Edit - improves consistency in generative AI videos

Meta Emu Video / Edit - improves consistency in generative AI videos

[07:37 Mon,20.November 2023   by ]    

The field of generative AI continues to develop at a rapid pace and Meta has recently emerged as one of the driving forces. One field of particular interest to slashCAM is of course video generation, for which Meta has now introduced a new model called Emu.

Even though generative images can be impressively flawless in themselves, credible animations that appear consistent throughout have not yet been achieved. At the same time, there is also the fundamental problem that changing a text input (a so-called prompt) often changes the entire image content and not just a selective part. Emu now wants to offer new, interesting solutions to both problems at the same time.



Emu Video is based on diffusion models and has a standardized architecture for video generation tasks that can react to a variety of inputs: Text only, image only and both text and image. The process consists of two stages; first the generation of images conditioned on a text prompt, and then the generation of videos conditioned on both the text and the generated image.

In most cases, the generated video is not quite what you had in mind. However, since not everyone has the time or inclination to deal intensively with prompt engineering, it would be much easier if you could just enter change requests afterwards without changing the basic properties of the video. And this is exactly where Emu Edit comes into play.

emu_edit



Emu Edit should be able to carry out edits using subsequent instructions. This should enable tasks such as local and global editing, removing and adding a background, color and geometry transformations, recognition and segmentation and much more.

Unlike other models, Emu Edit attempts to only change affected pixels that are relevant to the editing request. In contrast to many generative AI models, Emu Edit follows the instructions as precisely as possible and tries to ensure that pixels in the input image that have nothing to do with the instructions remain untouched.

This has been achieved using a special training data set containing 10 million synthesized samples, each of which contains an input image, a description of the task to be performed and the target output image. Once again, it appears that good data is far more valuable than pure computing power.

Looking at the results, it is fair to say that this is another milestone in AI development. All the videos shown are amazingly consistent temporally and the samples for Emu Edit really leave the basic style of the videos untouched.

As we've mentioned many times before, generative AI for moving images is evolving with seven-mile boots. And the transformation of these models to photorealistic footage is certainly less than 12 months away. With this in mind, get ready for 2024...



deutsche Version dieser Seite: Meta Emu Video / Edit - verbessert Konsistenz in generativen KI Videos

  

  Vorige News lesen Nächste News lesen 
bildNoch mehr Black Friday-Deals 2023 für Foto+Video – Teil 2 mit Sony, Smallrig, MSI, WD, TopazAI u.a. bildWerden die Oscars 2024 ein analoges Filmfest?


related news:1E0Meta Emu AI image generator - free online, but currently only in the USA 7.December 2023
SDXL-Turbo - New AI algorithm accelerates stable diffusion dramatically 6.December 2023
PIKA 1.0 announced - Generative AI videos with amazing quality 29.November 2023
The next step is here: AI trains AI (and no longer needs humans) 28.November 2023
Insta360 Ace Pro - Action Cam with 8K sensor, Leica optics and lots of AI 24.November 2023
Stable Video Diffusion - Free AI diffusion model for video generation presented 23.November 2023
Boris FX: Continuum gets AI functions - denoiser and upscaler 21.November 2023
alle Newsmeldungen zum Thema KI


[nach oben]
















Archiv Newsmeldungen

2023

December - November - October - September - August - July - June - May - April - March - February - January

2022
December - November - October - September - August - July - June - May - April - March - February - January

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

2004

2003

2002

2001

2000






































deutsche Version dieser Seite: Meta Emu Video / Edit - verbessert Konsistenz in generativen KI Videos



last update : 10.Dezember 2023 - 19:12 - slashCAM is a project by channelunit GmbH- mail : slashcam@--antispam:7465--slashcam.de - deutsche Version