🤖👩🏼🎨 Meta Steps Into Generative Art with Make-A-Scene
Was this email forwarded to you? Sign up here 📝 EditorialCreative expression has been a central aspect of the evolution of humankind and one of the marvels of human cognition. Emulating creativity using artificial intelligence (AI) has been a longtime goal of the industry. Nothing reflects creativity like art which is why, in recent years, we have seen a proliferation of text-to-image, image-to-image generative art methods that have showcased the potential of creative expression in AI models. Methods such as OpenAI’s DALL-E 2 or Google’s Imagen have achieved amazing milestones in generating photorealistic artistic images from natural language inputs. Last week, Meta AI published details around a new technique called Make-A-Scene, which highlighted new dimensions of the potential of generative art models. Most generative art techniques are highly specialized in one domain, such as text-to-image or image-to-image. Make-A-Scene takes a multimodal approach by generating artistic representations from both: natural language and freeform sketches. The multimodality adds a level of specificity that is impossible to achieve with previous models, as sketches can often reflect aspects such as position, size, and relationships between objects which are hard to express in natural language. Meta tested Make-A-Scene with leading digital artists such as Sofia Crespo, Scott Eaton, Alexander Reben, and Refik Anadol. All of them were incredibly impressed with the level of control in the artistic creation process and the quality of the outputs produced by the model. Make-A-Scene pushes the boundaries of generative AI models in the fascinating quest to emulate artistic creativity. 🔺🔻TheSequence Scope – our Sunday edition with the industry’s development overview – is free. To receive high-quality content about the most relevant developments in the ML world every Tuesday and Thursday, please subscribe to TheSequence Edge 🔺🔻 🗓 Next week in TheSequence Edge: Edge#209: we start a new series about ML testing; explore how Uber backtests time-series forecasting models at scale; discuss Deepchecks, an ML testing platform you should know about. Edge#210: we deep dive into Hopsworks 3.0, which bridges the Modern Data Stack with the machine learning stack in Python. Now, let’s review the most important developments in the AI industry this week 🔎 ML ResearchMake-A-Scene Meta AI published a research paper discussing Make-A-Scene, a multimodal generative model that can output artistic representations from text descriptions and image sketches →read more on Meta AI blog Plex Google Research published a paper introducing Plex, a framework to improve the reliability of deep learning systems →read more on Google Research blog Improving Multitask Learning Amazon Research published a paper presenting a knowledge distillation method to improve multitask learning models →read more on Amazon Research blog Visual Question Answering Google Research published a paper proposing a method for generating question-answer pairs for images →read more on Google Research blog ☝️ We RecommendFor Tide, a UK business banking provider, the ability to detect fraudulent transactions and make credit approval decisions in real-time is key to business success. Sign up for this webinar where Hendrik Brackmann, VP Data at Tide, and Mike Del Balso, Co-founder and CEO of Tecton, discuss the key challenges that Tide encountered with their first attempt at building a feature store to support their real-time machine learning use cases—and how they solved them. There will be a live Q&A after the presentation. 🤖 Cool AI Tech ReleasesMLU Explains Amazon Research released MLU Explains, a website containing visual essays about the core machine learning concepts →read more on Amazon Research blog BetterTransformer PyTorch released BetterTransformer, a high-performance API for transformer inference →read more on PyTorch blog Deep Search IBM open-sourced Deep Search, a toolkit for searching and discovery across large volumes of unstructured data →read more on IBM Research blog 🛠 Real World MLImproving YouTube DeepMind published some details about their deep learning work at YouTube in order to improve the experience of the video platform →read more on DeepMind blog 💸 Money in AI
You’re on the free list for TheSequence Scope and TheSequence Chat. For the full experience, become a paying subscriber to TheSequence Edge. Trusted by thousands of subscribers from the leading AI labs and universities. |
Older messages
⚡️ Last day 50% OFF
Saturday, July 16, 2022
Don't miss out
💥 Edge#208: Google’s Minerva Can Solve Mathematical and Scientific Problems Through Step-by-Step Reasoning
Thursday, July 14, 2022
The model is a major breakthrough in quantitative reasoning techniques.
📝 Guest post: 5 Principles You Need To Know About Continuous ML Data Intelligence*
Thursday, July 14, 2022
In this article, founder and CEO of Galileo Vikram Chatterji discusses the problems with ML data blindspots and introduces ML Data Intelligence that helps an ML team holistically understand and improve
🌐 🕸 Graph Neural Networks Recap
Tuesday, July 12, 2022
Last week we finished our mini-series about Graph Neural Networks, an important one. Here is a full recap for you to catch up with the topics we covered. As the proverb (and many ML people) says:
⚡️ Flash 50% OFF
Monday, July 11, 2022
Only 7 days left!
You Might Also Like
Charted | Economic Growth Forecasts for G7 and BRICS Countries in 2024 📊
Thursday, April 25, 2024
The IMF has released its economic growth forecasts for 2024. How do the G7 and BRICS countries compare in expected real GDP growth? View Online | Subscribe Presented by: Access European benchmarks with
Build5Nines Newsletter - April 25, 2024
Thursday, April 25, 2024
View this email in your browser Build5Nines Build5Nines Newsletter Thank you for subscribing! I look forward to sharing with you the latest cloud news, technical help, and other thoughts around DevOps
Discover the World's Easiest Parallel File System
Thursday, April 25, 2024
Join us in exploring the future of data management with Bjorn Kolbeck, a Google engineer turned CEO and Co-founder of Quobyte, the creators of the world's easiest parallel file system. ͏ ͏ ͏ ͏ ͏ ͏
Issue 314 - New Model 3 Performance is here
Thursday, April 25, 2024
View this email in your browser If you are just now finding out about Tesletter, you can subscribe here! If you already know Tesletter and want to support us, check out our Patreon page Issue 314 - New
Programmer Weekly - Issue 202
Thursday, April 25, 2024
View this email in your browser Programmer Weekly Welcome to issue 202 of Programmer Weekly. Let's get straight to the links this week. Quote of the Week "Computer science inverts the normal.
Python Weekly - Issue 647
Thursday, April 25, 2024
View this email in your browser Python Weekly Welcome to issue 647 of Python Weekly. Let's get straight to the links this week. From Our Sponsor Get Your Weekly Dose of Programming A weekly
Web Tools #562 - Voilà Review, CSS Tools, Media, React Native
Thursday, April 25, 2024
WEB VERSION Issue #562 • April 25, 2024 The following is a paid product review for Voilà, an AI assistant for the browser that enables you to improve your writing, coding, brainstorming, and research
Everyone wants to build the AI dev tool of the future
Thursday, April 25, 2024
A new startup called Augment has raised north of $250 million to build AI-powered dev tools. View this email online in your browser By Alex Wilhelm Thursday, April 25, 2024 Welcome to TechCrunch AM!
7 reasons to use Copilot over ChatGPT
Thursday, April 25, 2024
Coros Vertex 2S; Top 5 news apps; New Yeedi M12 Pro+ -- ZDNET ZDNET Tech Today - US April 25, 2024 placeholder 7 reasons I use Copilot instead of ChatGPT I reach for Copilot every day, and here's
Why they signed up for my Private AI Mentorship
Thursday, April 25, 2024
There are 3 reasons: use cases, accountability, and time.