AI/ML

Contribute to CompVis/stable-diffusion development by creating an account on GitHub.

Blog posts with images get 2.3x more engagement. Here’s the problem - we make a query engine for streaming tables. How the heck are you supposed to pick images for technical topics like comparing the similarities between Deephaven and Materalize, viewing pandas DataFrames, gRPC tooling for getting data streams to the browser, using Kafka with Parquet for storage, or using Redpanda for streaming analytics?

Run your own text to image prompts with CUDA, a bunch of disk space, and an insane amount of memory.

Will A.I. take over artists? Explore the INSANE world of AI Art and Midjourney, and learn how you can get started with generating art using Artificial Intelligence. Right from discovering the insanity of AI and the incredible images it can create to learning some of the most advanced codes for getting the best results, we will cover it all. In this guide, we will cover every aspect of this new technology and share all the pros, cons, and warnings you need to know before creating and using these art pieces. We will also learn how you can extract codes for inspiration from other artists' creations, discuss the cost and whether it makes sense, and also learn how you can get more advanced with prompts. I hope you enjoy this video. Thank you so much for watching :) ► TIMESTAMPS: 00:00 Speechless. AI is Unbelievable! 03:03 This Cannot Exist! 05:23 Disclaimer: I'll Come Clean 05:46 What Is It and How Does It Work? 07:09 How to Get Started 12:39 Price with Pros and Cons 14:39 Advanced Prompt Codes 17:17 Code List and Further Reading 17:59 How to Get Better Results & Copy Command 20:46 Use Your Own Images As Reference 21:47 BIG WARNING! DO NOT MISS THIS! 22:21 Will A.I. Take Over? Your Thoughts? ► IMPORTANT LINKS MENTIONED IN THIS VIDEO: 1. Midjourney: https://www.midjourney.com/ 2. Pratik Naik's A.I. Art Page: https://www.instagram.com/futurist.ai/ 3. Midjourney User Manual & Code List: https://github.com/midjourney/docs/blob/main/user-manual.md#parameters-to-imagine ► SUPPORT THE CHANNEL & GAIN PREMIUM ACCESS: https://www.patreon.com/piximperfect ► WATCH FOR FREE - THE FIRST 3 CLASSES OF MY ULTIMATE PHOTOSHOP COURSE: https://pix.live/freelessons ► RECOMMENDED SOFTWARE & CREATIVE RESOURCES: ✅ The Best A.I. Powered High-End Portrait Retouching Plugins: https://pix.live/retouch4me ✅ Try Photoshop for Free: https://pix.live/photoshop ✅ Unlimited Photoshop Actions, Plugins, Brushes, Assets, etc: https://pix.live/envato ✅ Skies for Sky Replacement: https://pix.live/sky (Use code PIXSKY10 & get $10 off) ✅ Best Plugin for Landscape & Astrophotography: https://pix.live/propanel ✅ The App I Use for YouTube Growth: https://pix.live/ytapp ✅ Music Used in PiXimperfect Videos: https://pix.live/music ► THE GEAR I USE: ✅ My Graphic Tablet: https://pix.live/wacom ✅ Recommended Budget Tablet: https://pix.live/wacomlite ✅ Primary Microphone: https://pix.live/mic1 ✅ Secondary Microphone: https://pix.live/mic2 ✅ Audio Interface: https://pix.live/audiointerface ✅ Camera: https://pix.live/camera ✅ Lens: https://pix.live/lens ► PIXIMPERFECT MERCH STORE: https://teespring.com/stores/piximperfect ► PIXIMPERFECT ACTIONS: https://gumroad.com/piximperfect ► SHARE: https://goo.gl/IUhnUl ► LET'S CONNECT: Instagram: https://www.instagram.com/piximperfect Facebook: http://facebook.com/piximperfect Twitter: https://twitter.com/piximperfect

While deep learning has enabled tremendous progress on text and image datasets, its superiority on tabular data is not clear. We contribute extensive benchmarks of standard and novel deep learning...

Cloud computing isn’t going anywhere, but some companies are shifting their machine learning data and models to their own machines they manage in-house. Adopters are spending less money and getting better performance.

Everybody has heard about the latest cool thing™, which is DALL·E 2 (henceforth called Dall-e). A few months ago, when the first previews started, it was basically everywhere. Now, a few weeks ago, the floodgates have been opened and lots of people on the waitlist got access - that group included me. I’ve spent a day playing around with it, learned some basics (like the fact that adding “artstation” to the end of your phrase automatically makes the output much better…), and generated a bunch of (even a few nice-looking) images.

It was difficult for people to guess whether philosophical responses came from the philosopher Daniel Dennett or the language generator GPT-3.

Perhaps AI can provide new and ~unique~ ideas for food content on the internet.

A complete from-scratch rewrite of fast.ai's most popular course, that's been 2 years in the making.

A free course designed for people with some coding experience, who want to learn how to apply deep learning and machine learning to practical problems.

Convert jargon to plain english

🖼 Training StyleGAN2 on TPUs in JAX

OpenAI is expanding access to DALL-E 2, its image-generating AI system, with the goal of onboarding around 1 million people from the waitlist within weeks.

But the company has had to rush out a bunch of fixes to the image-making model’s worst flaws to do so.

One of my favourite uses for the GPT-3 AI language model is generating explanations of how code works. It’s shockingly effective at this: its training set clearly include a vast …

Let’s call it “The Church of Virtual AWakening” I have not edited any of it. You can tell by the punctuation errors. The only input I gave…

An author tries collaborative writing with GPT-3. Here's what happened.

Not DALL·E 2, not PaLM, not AlphaZero, not even GPT-3.

OpenAI’s DALL-E 2 is incredible at turning text into images. It also highlights the problem of AI bias — and the need to change incentives in the industry.

Image prompts that were turned into pictures using OpenAI's DALL-E 2

Experiments I conducted with DALL·E 2 from @OpenAI replicating styles of well known portrait photographers using photo-realistic AI. 🧵1. Dorothea Lange pic.twitter.com/845AzE51xu— Michael Green (@triplux) June 30, 2022

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

WandB is a central dashboard to keep track of your hyperparameters, system metrics, and predictions so you can compare models live, and share your findings.

Optimizing metrics is a central aspect of most current artificial intelligence (AI) approaches, yet overemphasizing metrics leads to manipulation, short-termism, and other negative consequences. This poses a fundamental challenge within AI. We review how metrics can go wrong in practice, and we put forward an evidence-based framework toward mitigating these harms.