Welcome to WednesdAI – Pixel Dreams’ weekly update with top stories from the rapidly evolving world of Artificial Intelligence.
This week saw some huge strides being make in the world of AI filmmaking. Let’s dive right in…
Subscribe to the brand new WednesdAI YouTube channel!
Make a Full Narrative Film with LTX Studios
LTX Studio helps you go from simple ideas into captivating narrative video clips with consistent styles and characters.
Watch the announcement video:
Develop scripts, storyboards, and short clips from text prompts. This tool offers unparalleled flexibility in storytelling, allowing for easy manipulation of scenes, characters, and narrative elements. Designed with professionals in mind, LTX Studio addresses the industry’s demand for efficient, cost-effective solutions for story development and planning.
Read the full story at TechCrunch.
Evolutionary Leap in AI Video Lip Sync
Two technologies showcase the potential for creating more dynamic and realistic video content.
Alibaba’s EMO (Emote Portrait Alive) directly converts audio into video frames, eliminating the need for complex 3D models, capturing natural facial expressions and movements associated with speech or song.
Pay special attention to the facial expressions in the following examples:
Pika Lip Sync supports text-to-audio conversions and the use of pre-recorded tracks, offering customization in voice style and ensuring the characters’ mouth movements align with the spoken words.
Watch Pika Labs’ announcement video:
YouTuber HitPaw compares the two:
Read the technical paper for Emote Portrait Alive.
Read Pika Labs’ article on Pika Lip Sync.
Figure’s Humanoid Laborbots get ChatGPT
ChatGPT takes a step toward its final form as OpenAI partners with AI startup Figure to develop and infuse advanced AI capabilities into the startup’s humanoid robots.
With a team comprising some of the brightest minds from Boston Dynamics, Tesla, and Google DeepMind, a groundbreaking commercial agreement with BMW, and a huge influx of cash, Figure is at the forefront of bringing humanoid robots into everyday use, promising to redefine our interaction with technology and addressing critical workforce challenges.
Watch it make a coffee:
Watch it do warehouse work:
Meet Figure and learn about their work in robotics in this episode of S3:
Get immersed in the world of Figure.
Empowering Finance Professionals
Microsoft introduces Copilot for Finance, transforming financial workflows with AI-driven efficiency.
Microsoft’s Copilot for Finance is revolutionizing the way finance teams operate by integrating AI into daily tasks, thus addressing the critical challenge of balancing operational duties with strategic growth initiatives. By automating repetitive, time-consuming tasks within Microsoft 365 applications, this new tool enables finance professionals to devote more time to providing real-time insights and guiding future business strategies. With its capacity to connect to financial systems like Dynamics 365 and SAP, Copilot for Finance offers workflow automation, guided actions, and recommendations, significantly reducing the manual workload. This innovation not only streamlines financial operations but also empowers teams to contribute more significantly to business development, marking a significant shift in how finance departments influence organizational success.
Read Microsoft’s official announcement.
This Week’s Best Sora Videos
While we patiently wait for our turn to play with it, our eyes are glued to social media where we see new videos being generated by Sora all the time.
YouTuber Marques Brownlee was invited to create three videos. Here’s the results:
Prompt 1: A medium sized friendly looking dog walks through an industrial parking lot. The environment is foggy and cloudy. Shot on 35mm film, vivid colors.
Prompt 2: A young professional product reviewer in a well lit video studio is surrounded by gadgets and technology, sitting in front of a computer with two displays. He’s holding a cinema camera as he ponders what video to make next. He is in focus, while the background is slightly blurred for cinematic effect
Prompt 3: A timelapse closeup of a 3D printer printing a small red cube in an office with dim lighting.
And here is a clip that looks straight out of a sci-fi thriller! Prompt: “an alien blending in naturally with new york city, paranoia thriller style, 35mm film” :
“fly through tour of a museum with many paintings and sculptures and beautiful works of art in all styles”
AI Andy showcases all of the latest Sora videos to hit the web:
The images accompanying the news items in this article were generated in Midjourney using the following prompts:
Join us every Wednesday for WednesdAI – a Pixel Dreams production
