Google Introduced LUMIERE - A Space-Time Diffusion Model for Realistic Video Generation

Lumiere is a text-to-video diffusion model that excels in creating realistic and coherent videos. Unlike traditional methods that generate keyframes and then fill in details (which can lead to inconsistencies), Lumiere uses a Space-Time U-Net architecture to create the entire video in one go. This approach ensures better consistency over time. The model performs both spatial and temporal down- and up-sampling, integrating techniques from pre-trained text-to-image models. It's capable of generating full-frame-rate, low-resolution videos by processing multiple space-time scales. This technology sets a new standard in text-to-video generation and can be used for various content creation and video editing tasks, such as converting images to videos, video inpainting, and creating stylized videos.

Your info is on the dark web

Every day, data brokers profit from your sensitive info—phone number, DOB, SSN—selling it to the highest bidder. And who’s buying it? Best case: companies target you with ads. Worst case: scammers and identity thieves.

It's time you check out Incogni. It scrubs your personal data from the web, confronting the world’s data brokers on your behalf. And unlike other services, Incogni helps remove your sensitive information from all broker types, including those tricky People Search Sites.

Help protect yourself from identity theft, spam calls, ID theft and health insurers raising your rates. Plus, just for our readers: Get 55% off Incogni using code PRIVACY.

Google Chrome gains AI features, including a writing helper, theme creator, and tab organizer

Google Chrome is introducing new AI-powered features for Mac and Windows users. These include:

1. AI-Enhanced Writing Assistant: This feature helps users draft text for various online contexts, like forum posts, reviews, or RSVPs. It's accessible by right-clicking a text field and choosing "help me write."

2. Tab Organization: Chrome will now automatically suggest and create tab groups based on the user's open tabs, helping to manage multiple tabs more efficiently.

3. Custom AI Themes: Users can generate custom browser themes using a text-to-image diffusion model. This feature allows for personalization based on subject, mood, style, and color.

These features are part of Chrome's M121 release and are currently experimental, and not yet available to enterprise and educational customers. Other AI and ML tools in Chrome include audio/video captioning, Safe Browsing, silencing permission prompts, and summarizing web pages. Google plans to add more AI and ML features to Chrome, including those integrating the new AI model, Gemini.

How to add expressiveness and intention to your generation with Multi-Motion Brush.

Learn to generate expressions using Multi Motion Brush in Gen-2.

• Create a character using Gen-2

• Use Multi Motion Brush to draw various masks on the character’s face

  • eyebrows, eyes, and mouth positions work best

  • experiment with different directions for each brush, taking into account the expression you are going for in the output

Other stuff

• OpenAI’s GPT Store now forbids “romantic companionship” apps following an influx of girlfriend GPTs, but several remain and efforts to ban them seem to have slowed. Hmm! RECOMMENDED

• Google aims to deliver the "world's most advanced AI" in 2024, and it certainly has a long way to go RECOMMENDED

• Learn by Doing: How LLMs Should Reshape Education

• GPT-4 has become so lazy that people are faking disabilities to try to make it perform as it used to.

• Watch the trailer of the new Kanye West song featuring an AI-generated video

• ElevenLabs announced Dubbing Studio. RECOMMENDED

Maximize Efficiency with Custom Prompts in SuperPower ChatGPT: A Comprehensive Guide

Hope you enjoyed today's newsletter