ANOTHER AI MEGA THREAD 🧵

Tesla CEO Elon Musk revealed a working prototype of humanoid robot at Tesla AI day 2022https://t.co/bzseqL50Le pic.twitter.com/D6lfwFQrkz

— The Verge (@verge) October 1, 2022

Stable Diffusion VR
Real-time immersive latent space. \U0001f525
Small clips are sent from the engine to be diffused. Once ready, they're queued back into the projection.
Tools used:https://t.co/UrbdGfvdRd https://t.co/DnWVFZdppT#aiart #vr #stablediffusionart #touchdesigner #deforum pic.twitter.com/x3QwQDkapT

— ScottieFox (@ScottieFoxTTV) October 11, 2022

Everything is changing.
Playing with combinations of #AI and #AR again. This time I am using the Target tracker in SparkAR, Stable Diffusion for generating images and Frame Interpolation ML for making animation. pic.twitter.com/XwaMM4V11T

— Sergei Galkin (@sergeyglkn) October 12, 2022

1/6
How I transferred a physical toy to the digital world in one hour with AI

-> LumaAI (3D scan)
-> Cinema4D (editing)
-> Mixamo (rigging and animation)
-> MetaSparkStudio (AR) pic.twitter.com/zChf6FRaqE

— Sergei Galkin (@sergeyglkn) November 1, 2022

Happy to announce DreamFusion, our new method for Text-to-3D!https://t.co/4xI2VHcoQW

We optimize a NeRF from scratch using a pretrained text-to-image diffusion model. No 3D data needed!

Joint work w/ the incredible team of @BenMildenhall @ajayj_ @jon_barron#dreamfusion pic.twitter.com/YeG0zaFxuu

— Ben Poole (@poolio) September 29, 2022

A group of researchers presented Motion Diffusion Model (MDM), a new diffusion-based generative model capable of generating human motions from text prompts.

Details: https://t.co/iyqjh7nIJh#AI #ArtificialIntelligence #research #animation pic.twitter.com/09cz9N8cdu

— 80 LEVEL (@80Level) October 4, 2022

Mubert-Text-to-Music \U0001f3b5\U0001f3b5\U0001f3b5

Colab notebooks demonstrating prompt-based music generation via Mubert API

GitHub: https://t.co/ExdfvXUCrR pic.twitter.com/2Ycwl7RUvX

— AK (@_akhaliq) October 19, 2022

text \u2192 app \U0001f4ab

Write plain English and it gets turned into an app, that sends inputs to OpenAI API.

an app, built by AI, that uses AI to power the app\U0001f92f pic.twitter.com/2ugZmtgDMa

— Ben Tossell (@bentossell) October 5, 2022

\u2728 You can now create your own AI avatars like these with my new AI mini project:https://t.co/3lLowfJe66

\U0001f4f8 Upload some photos of yourself
\U0001f9e0 Train a model on it and then
\U0001f5a8 Generate 30 AI avatars of your own face in different styles

Still very very basic MVP but it works https://t.co/fwrteJ7dh4 pic.twitter.com/OOGKP11dzP

— @levelsio (@levelsio) October 28, 2022

This is pretty mind-blowing: a podcast that is entirely generated by artificial intelligence where Joe Rogan interviews Steve Jobs. https://t.co/JPeKZ8ylxk

— Alex MacCaw (@maccaw) October 11, 2022

\U0001f389 #StableDiffusion can be fine-tuned to generate medical images, and the outputs can be controlled using natural language text prompts!

In our latest work, we use SD to create synthetic chest xrays and insert pathologies like pleural effusions.

\U0001f9f5 #Radiology #AI #StanfordAIMI pic.twitter.com/FxQLIPmwdZ

— Christian Bluethgen (@cxbln) October 11, 2022

Announcing https://t.co/C7rp4Vj9RS - a better way to read academic papers.

Want to know the science behind GPT-3? We built a tool that explains Attention Is All You Need - the paper that started it all.

Try it at https://t.co/C7rp4Vj9RS! pic.twitter.com/OwHsiYCPbD

— Aman Jha (@amanjha__) October 12, 2022

GPT-3 versus Google Search: pic.twitter.com/oCxIIDV7O4

— David E. Weekly @[email protected] (@dweekly) October 13, 2022

New AI algorithms predict sports teams\u2019 moves with 80% accuracy. Move over Brad Pitt, you're old news, there's a new Moneyball in town.https://t.co/YA6jyvCjAq

— Ben Tossell (@bentossell) October 13, 2022

AI unlocks unlimited product photography. \U0001f92f

Recent advances have made it possible for merchants to turn mobile photos into high quality product images + ad creative.

AI can now learn and reproduce a product on demand. More\u2026\U0001f447[1/10]#ai #aiart #stablediffusion #dreambooth pic.twitter.com/sNrRLtIIa1

— Russ Maschmeyer (@StrangeNative) October 11, 2022

~ Presenting: DiffusionCraft AI ~
Stable Diffusion running live with Minecraft.
Here is my latest experiment with the little help of some python scripts.#diffusioncraft #minecraft #stablediffusion #python #img2img #aigaming pic.twitter.com/XXBFzeeCFL

— Sean (@ThoseSixFaces) October 23, 2022

Testing out Stable Diffusion inpainting on a video
- by @justLV
See below for his process#inpainting #stablediffusion #artificialintelligence pic.twitter.com/XyFk4c1aUg

— Karen X. Cheng (@karenxcheng) November 1, 2022

Introducing AI Magic Tools

Dozens of creative tools to edit and generate content like never before. New tools added every week.

Available now: https://t.co/ekldoIsP34 pic.twitter.com/ejcSnEiCEi

— Runway (@runwayml) October 12, 2022

Introducing Frame Interpolation

Generate seamless video from still images with just one click.

Available now: https://t.co/rpNciHjZRH pic.twitter.com/HOtAo16f0Y

— Runway (@runwayml) November 2, 2022

Excited to announce Imagen Video, our new text-conditioned video diffusion model that generates 1280x768 24fps HD videos! #ImagenVideohttps://t.co/JWj3L7MpBU
Work w/ @wchan212 @Chitwan_Saharia @jaywhang_ @RuiqiGao @agritsenko @dpkingma @poolio @mo_norouzi @fleet_dj @TimSalimans pic.twitter.com/eN81LqZW7I

— Jonathan Ho (@hojonathanho) October 5, 2022

We\u2019re pleased to introduce Make-A-Video, our latest in #GenerativeAI research! With just a few words, this state-of-the-art AI system generates high-quality videos from text prompts.

Have an idea you want to see? Reply w/ your prompt using #MetaAI and we\u2019ll share more results. pic.twitter.com/q8zjiwLBjb

— Meta AI (@MetaAI) September 29, 2022

~ Presenting: Sketch Diffusion ~
Stable Diffusion running live with the Meta Quest Pro in Gravity Sketch. I created this in collaboration with T&DA.#metaquestpro #wearables #ar #stablediffusion #ai #artificialintelligence #img2img #generativeart #python #gravitysketch pic.twitter.com/dJP1Kct25X

— Sean (@ThoseSixFaces) October 28, 2022

More testing of the SD addon for Blender. \U0001f601#b3d #stablediffusion pic.twitter.com/1vJ22sIGgS

— \U0001f463K\u15ea\u15e9\u15efG\U0001f463 (@Kdawg5000) September 27, 2022

1/ Now you can create "drone" shots from your phone footage, thanks to NeRF
Collab with @justlv / software @nerfstudioteam / see below for our process
#NeRF #neuralrendering #artificialintelligence #instantNeRF pic.twitter.com/3FOqGK403N

— Karen X. Cheng (@karenxcheng) October 25, 2022

AI powered app helps you count things pic.twitter.com/cxOEI3BAyz

— Vala Afshar (@ValaAfshar) October 31, 2022

Just wanted to share something small I built the other night --

I grew up listening to Will Durant's history books, and now I can watch them! Videobook lets you "watch" audiobooks (sound on): pic.twitter.com/JcBBQJNPT2

— Daniel Gross (@danielgross) October 27, 2022

The "lyrics" of "Killer Queen" are used to create the images by Artificial Intelligence and it is just beautiful\U0001f970 pic.twitter.com/FZknOB4kqA

— Tansu YE\u011eEN (@TansuYegen) October 7, 2022

"A Year"

AI animation artwork made in colab using my custom stable 3D animation algorithm on top of #stablediffusion model. In the thread I share some details about the algo and when i plan to release it, and talk about the joy and future of AI filmmaking

\U0001f3b6 DakhaBrakha - Vesna pic.twitter.com/OexCG5DCl3

— Dmitrii Tochilkin (@cut_pow) October 3, 2022

The best photoscanning app by far is the @LumaLabsAI beta. It uses self-learning AI to guess parts of the missing scan, and does an amazing job at it. Currently no mesh export, but that's coming soon. pic.twitter.com/vb6bJqmWZ8

— Andrew Price (@andrewpprice) October 12, 2022

Stable Diffusion inpainting in the real world \U0001f929. First experiment with Stable Diffusion and WebAR. #threejs #8thwall #stablediffusion #augmentedreality pic.twitter.com/dFq1sRoh43

— Stijn Spanhove (@stspanho) October 16, 2022

something I've been playing around with: live drag-and-drop AI writing augmentation in @Fermat_ws. it's infinitely easy to prompt engineer different tools, and ones like live counter-argument generation seem to be super powerful. pic.twitter.com/t4hG2IEoJw

— max drake (\u2a0d) (@max__drake) October 14, 2022

This tool for artists, storytellers, and researchers is built for rapid prompt development: generate hundreds of images, manage prompt dependencies, try variations, find nearby concepts, and fine-tune params in real-time.
Start with any prompt. Those from #lexica usually... pic.twitter.com/bgAk0x86Fq

— Noah Mac (@noahamac) October 11, 2022

Introducing the Dreambooth Ion Cannon:

A Stable Diffusion repository and guide designed to allow even the most non-technical of users to generate images according to pre-selected prompts with nothing more than eight photographs of a subjecthttps://t.co/JZTMJqYfqk

— laurence (gpt-3 bot overlord arc) (@functi0nZer0) October 5, 2022

DreamBooth is becoming popular for creating custom Stable Diffusion models using your images.

Here is a beginner friendly thread on how it works: \U0001f9f5 pic.twitter.com/jlLdOqbWBf

— Divam Gupta (@divamgupta) November 1, 2022

Imagic: Text-Based Real Image Editing with Diffusion Models
abs: https://t.co/xRW6F6w2ZG pic.twitter.com/wGifY74i4w

— AK (@_akhaliq) October 18, 2022

I turned stablediffusion-infinity (#outpainting with #stablediffusion on an infinite canvas) into a web app using @pyscript_dev and @Gradio: PyScript for the frontend and Gradio for the backend.

Source code: https://t.co/BpUWQZctcx
Also available on Colab pic.twitter.com/QkpGdTemUl

— Lnyan (@lkwq007) October 1, 2022

Expert level prompt engineering going on here: pic.twitter.com/ZnKgLUN8NZ

— Suhail (@Suhail) October 13, 2022

How do people use #stablediffusion ?
Explore 6.4 million AI generated images from @krea_ai in Atlas.https://t.co/nrbG8PuwFp pic.twitter.com/B8MOJDDDRl

— Nomic AI (@nomic_ai) November 1, 2022

(1/3) Until now, AI translation has focused mainly on written languages. Universal Speech Translator (UST) is the 1st AI-powered speech-to-speech translation system for a primarily oral language, translating Hokkien, one of many primarily spoken languages. https://t.co/onYKQ8uoKN pic.twitter.com/Iy8MRMOypQ

— Meta AI (@MetaAI) October 19, 2022

We've trained a neural net called Whisper that approaches human-level robustness and accuracy on English speech recognition. It performs well even on diverse accents and technical language. Whisper is open source for all to use. https://t.co/ueVywYPEkK

— OpenAI (@OpenAI) September 21, 2022

\u2728 I made a YouTube transcription tool using @OpenAI's #Whisper model to transcribe any YouTube video to a PDF.

Just paste any YouTube link and get the PDF.

It has hyperlink timestamps that go to any specific video section.

It's on @ProductHunt today!https://t.co/PeRbUy6YZn pic.twitter.com/I9Odx3aAJV

— Marco Mascorro (@Mascobot) October 11, 2022

\U0001f941 Introducing @vidtranslator \U0001f30e

Hacked together a twitter bot that uses @OpenAI #whisper to translate any videos in any tweets, in... any language.

Making @Twitter a truly global water cooler.

It's mind-blowing how good it is! Examples \U0001f9f5

— Altryne - targum.video (@altryne) October 3, 2022

we've seen lots of generative AI market maps making the rounds on Twitter. a huge gap: none of them cover music with the same amount of breadth as visual art and text.

so, we made our own \U0001f916 here's a market map of 60+ AI tools for musicians, across the entire creative process: pic.twitter.com/FTvobG3xiN

— Water & Music (@water_and_music) November 1, 2022

big AI art news from Shutterstock. the company is:

- integrating OpenAI's DALL-E to their site to generate stock images
- launching a fund to reimburse Shutterstock creators whose images are sold to train AI art modelshttps://t.co/7OlhYYyPlB

— James Vincent (@jjvincent) October 25, 2022

dying at these AI images of \u201csalmon in a river\u201d pic.twitter.com/mVXP1QSmhE

— thankfulBad (@SortaBad) October 28, 2022

How dead celebrities would look today with artificial intelligence

I can't stop staring at these...

Don't tell me AI isn't going to change the world:

— GREG ISENBERG (@gregisenberg) September 27, 2022

The simplest video inputs can turn out so wild \U0001f47d #aivideo #stablediffusion #stablewarpfusion #ai pic.twitter.com/FgrGLMYXix

— Colton Onushko (@Coltography) October 28, 2022

I decided to turn my error into an image with stable diffusion. That seems about right. pic.twitter.com/NmryXgWkfX

— Cody Blakeney (@code_star) October 7, 2022

This sweater developed by the University of Maryland is an invisibility cloak against AI.

It uses "adversarial patterns" to stop AI from recognizing the person wearing it. pic.twitter.com/aJ8LlHixvX

— Morning Brew \u2615\ufe0f (@MorningBrew) October 25, 2022

OpenAI launches their first accelerator.

$1M to 10 companies + early access to models.https://t.co/l0nTtLomlo

— Lenny Bogdonoff (@rememberlenny) November 2, 2022

Press release: Stability AI Announces $101 Million in Funding for Open-Source Artificial Intelligence @EMostaque https://t.co/VgVDeag8tJ

— Stability AI (@StabilityAI) October 17, 2022

I think most people who are not playing with these technologies are way underestimating the speed of advancement in "creative" AIs & how much of an impact that is going to have on many jobs, soon.

AI language & art models are growing at 10x a year. Beyond Moore's Law pacing. 1/ pic.twitter.com/r0YnROh58z

— Ethan Mollick (@emollick) October 25, 2022

This is not a drill. I was able to run #stablediffusion locally on an iPhone XS. Not via server. On. My. Phone. The prompt: \u201cpineapple on a white table.\u201dWatch it transform. (I broke the model into about 20 CoreML models to avoid running out of memory pic.twitter.com/FJcUNv7elO

— Matt Waller (@wattmaller1) September 24, 2022

The field of AI is moving incredibly fast.

Here\u2019s a curated list of 15 AI newsletters to stay ahead of the field.\U0001f9f5

— AssemblyAI (@AssemblyAI) October 28, 2022

Awesome Diffusion Models

A fantastic and well-organized collection of learning resources on diffusion models such as introductory papers, survey papers, intro videos, long lectures, and blog posts. Papers in vision, natural language, tabular, graph, etc.https://t.co/Dfmkv9mmKD pic.twitter.com/fcqw8LgtM4

— Jean de Nyandwi (@Jeande_d) October 7, 2022

Over the 7 weeks since Stable Diffusion's release, we've seen many amazing open-source contributions from the community. A lot of them have come in the form of awesome Google Colab notebooks! \U0001f525

Here is a thread of 14 awesome notebooks we've seen from the community \u2193

— Stable Diffusion (@StableDiffusion) October 14, 2022

\U0001f6a8 NEW: Our episode with @EMostaque of @stabilityai / StableDiffusion is out!

We discussed
- All things StableDiffusion
- Why gatekeepers are bad for AI
- Prompt eng.
- India's role in AI
- Dishoom in London (!)
- Religion/theology
- And much more!@aarthir and I had a blast pic.twitter.com/pgISO6PkYz

— Sriram Krishnan - sriramk.eth (@sriramk) September 30, 2022

The Illustrated Stable Diffusionhttps://t.co/sbjKHP4Pol

New post!

Over 30 visuals explaining how Stable Diffusion works (diffusion, latent diffusion, CLIP, and a lot more). pic.twitter.com/qkK1f7W1zh

— Jay Alammar (@JayAlammar) October 4, 2022

I got a special surprise for you all...

We just released the first 5.5 hours of our new course "From Deep Learning Foundations to Stable Diffusion", for free!https://t.co/LiUu9HSflG

— @[email protected] (Mastodon) (@jeremyphoward) October 20, 2022

Stable Diffusion is only 30 days old\u2026
a MEGA THREAD \U0001f9f5\xa0on its rapid rise.

— Daniel Eckler \u2726 (@daniel_eckler) September 20, 2022

AI is coming for creativity \U0001f480
Learn these tools or get left behind \U0001f447 pic.twitter.com/XVksvkSdya

— Daniel Eckler \u2726 (@daniel_eckler) October 6, 2022

101 AI Artists you NEED TO SEE to Believe \U0001f447 pic.twitter.com/4xQNyNOry8

— Daniel Eckler \u2726 (@daniel_eckler) September 29, 2022

AI Art 101 \U0001f9f5

27 tweets that will \U0001f92f your brain.

— Daniel Eckler \u2726 (@daniel_eckler) August 30, 2022

AI Art 101.B \U0001f9f5

24 MORE mind melting videos\u2026

— Daniel Eckler \u2726 (@daniel_eckler) September 9, 2022

AI Film Festival tmw!

AI movies from @GlennIsZen @ScottieFoxTTV @LighthiserScott @TomLikesRobots @_hackmans_ @hollyherndon @AceKittyArtist

Panels with @a16z @alonsorobots (Phenaki) @buckhouse at @sequoia @SPolcz + more!

AI games+AI movies+holodeck!!!https://t.co/id0kvdrvww

— The Culture DAO (@theculturedao) November 6, 2022