dreemAI

[Eckler ✦ @daniel_eckler]

21 Amazing AI.llusions 🌀
and how to make them 🔨

[Linus ✦ Ekenstam @LinusEkenstam]

What did I just watch?

Star Wars x AI

Mind blown, creative humans using AI to dream up a very different Star Wars.

By @douggypledger & @osymyso

[Dreaming Tulpa 🥓👑 @dreamingtulpa]

Tired of watermarks in videos?

ProPainter is a new AI video inpainting method that is able to remove objects, complete masked videos, remove watermarks and even supports video outpainting 🤯

https://t.co/7IFSk5de72

[Stability AI @StabilityAI]

Researchers at Stability AI helped collect and create Pick-a-Pic - an open dataset of user preferences of AI-generated images.

This dataset will enable improvements in future text-to-image models!

Learn more on our new research blog:
https://t.co/TdwtgQPio8

[dreemAI @dreem_AI]

@sanchitgandhi99 @ClementDelangue @LiuHaohe @emreaydin

[dreemAI @dreem_AI]

Google, metinden video üreten NY merkezli Runway'e 1.5 milyar dolar değerleme ile yatırım yapıyor.

[Kate Clark @KateClarkTweets]

Scoop: Google is investing in AI startup Runway at a $1.5 billion valuation. https://t.co/1b4Bb7GDPV

[camenduru @camenduru]

Now we have #segment #anything + #inpainting #colab 🥳 thanks to the Grounded-Segment-Anything team ❤ https://t.co/N1BItVeC1z please try it 🐣 https://t.co/cKuOi8h5pY

[Aharon Rabinowitz @ABAOProductions]

Here's another test of @WonderDynamics, this time with a bunch of post work in @AdobeVideo AE, with @videocopilot Element3D and @MaxonVFX Magic Bullet for color. My wife was kind enough to be my mocap actor here as she is far more graceful.

[Jeremy Howard @jeremyphoward]

Our new course, "From Deep Learning Foundations to Stable Diffusion", is finally done after 8 months of work!!!

With >30 hours of video content (all free, no ads!), you'll learn how to create and train a Stable Diffusion model starting from pure Python 🧵
https://t.co/bK0PSIzFww

[Charly Wargnier ♨️ @DataChaz]

Everyone is talking about #ChatGPT and #GPT3, but did you know there was a free, #opensource version of GPT-3 called OPT-175B?

No login, no credit card needed! ;)

👉 https://t.co/IBrRnSk980

[Mark Tenenholtz @marktenenholtz]

Someone implemented a framework to allow you to train PaLM (Google’s 540B parameter LM) using the same reinforcement learning strategy as ChatGPT!

Open source strikes again.

To start, here’s the part where you initially pre-train the model:

[elvis @omarsar0]

2022: A Year in Review (ML Papers Edition)

In this thread, let's take a look at some of the top trending ML papers of 2022 ↓

[Deedy @deedydas]

Today, https://t.co/4Doyr3IIja, a Search engine, launched a ChatGPT-like experience on the right hand side on Desktop, and it's awesome!

It smartly picks high quality search results and summarizes them with citations.

How did they make this? What can't it do?
Deep dive 🧵

1/6

[Manuel Sainsily @ManuVision]

🤖 Can chatGPT create 3D models from a simple prompt and view them directly in the interface of our conversation?

[🧵Thread]:

#ai #chatgpy #artificialintelligence #openai @OpenAI

[Linus ✦ Ekenstam @LinusEkenstam]

🤖 AI Generate Art
🔮 Midjourney Guide

This is a little step-by-step on how to turn your random famous person into a Teenage Mutant Ninja Turtle using Midjourney.

🧙🏻‍♂�� Requested by @nicoloborghi 🙏🏻

[CoffeeVectors @CoffeeVectors]

Thought this was fascinating. If the grammar of a sentence isn’t correct, #chatGPT can go in-depth explaining why. The ability to summarize and expand is such an amazing ability when it comes to understanding things.

[Aman @_amankishore]

Point-E unlocks almost instant 3D Asset generation from an Image or Text ⚡️

We made a @huggingface and @mirage_ml apps to instantly create 3D assets! 🤗

Try it out!
https://t.co/hBVdHdWsfv
https://t.co/0PxOTWExvr

[CoffeeVectors @CoffeeVectors]

Very interesting developments with 3D rendering here! Meshlets are basically pathtraced nanite with real time speeds, and neural rendering is a new kind of 3D AI object that you train in engine.

[Lucas Crespo @lucas__crespo]

Outpainting in @runwayml is sick! I was able to generate things outside of the picture frame and then edit it seamlessly… ohhh the possibilities!

[camenduru @camenduru]

Good news 🎊🌟 I found a way running #stablediffusion #webui inside #Jupyter inside 🤗 @huggingface hehe, just duplicate the jupyter spaces and add gpu 🎉 I put a little surprise folder 🎁🎀 happy holiday🤗🎄🎅 ❤https://t.co/Kk9Ad7vJaq