Thread by @dreamingtulpa

Dear #aiartcommunity 🧡 Issue º35 of #aiartweekly is live! Another packed week! Cover by @unsafe_dB_level 🐍 Adobe released Generative Fill ✍️ Mind-Video reconstructs videos from brainwaves 🤯 Interview with AI artist @ahmadova_marina 🥰 And a new "minimalism" challenge 👀

🧵🔗

All links in this thread and the entire interview with @ahmadova_marina can be found on aiartweekly.com/issues/35 👈

Let's jump in 👇

@ahmadova_marina This week we’ll be exploring the theme of minimalism. I’m looking for simplicity, incorporating basic shapes, colors, and lines to convey an idea or feeling.

https://twitter.com/1546508709513265153/status/1662101364271460354

Big news first! Generative AI art just got a lot more accessible this week. Adobe released a new feature called “Generative Fill” which enables text-to-image, inpainting and outpainting directly within Photoshop. @CoffeeVectors made a test-run 👇

This week we got Mind-Video which is able to reproduce videos from fMRI. I hope someone will invest a lot of money and trains a large enough model so I can visualize my dreams. Imagine a platform where people could share their dreams 🤯 @elonmusk 👀

mind-video.com/?ref=aiartweek…

Meta AI revealed their MMS project this week which is able to transcribe AND generate speech for a 1000+ languages. Compared to OpenAI’s Whisper, models trained on their dataset cover 11x more languages and achieve half the word error rate. Impressive.

ai.facebook.com/blog/multiling…

What comes after Text-to-Image, Text-to-Video, Text-to-3D? Apparently Text2Nerf 🤷‍♂️

eckertzhang.github.io/Text2NeRF.gith…

Okay, now that we got Text-to-NeRF, what about we if we could combine it with other modalities? CoDi is a framework for any-to-any generation via composable diffusion. It can generate language, images, videos, and audio from any combination of the former.

codi-gen.github.io/?ref=aiartweek…

Control-A-Video aka Video-ControlNet comes pretty close to Gen-1 and introduces the ability to guide video generation using depth maps, canny and HED edge detection as well as text descriptions.

controlavideo.github.io/?ref=aiartweek…

Imagine you’ve a 3D asset you want to reuse but in a slightly different way? Sin3DM makes it possible to generate an infinite number of variations with different sizes and boundaries from a single input object.

sin3dm.github.io/?ref=aiartweek…

Last but not least, Minecraft! Looking at Voyager, I think we aren’t that far away from being able to build worlds filled with NPCs that can learn by themselves and react to a player’s input organically.

voyager.minedojo.org/?ref=aiartweek…

Then there was blotterstream this week. An endless audio-reactive music video that is generated in real-time at 24 fps. Chris is working on a Spotify integration so you can run this at home during your own home parties.

twitch.tv/blotterstream?…

@frantzfries shared an interesting video this week in which Carvana created a 1.3 million hyper-personalized videos. Is this the future of marketing?

@joinrealmai is hosting an exclusive exhibit taking place during the 2023 Central Pennsylvania Festival of the Arts! They’re looking for AI-art submissions, so show them what you got!

joinrealm.ai/art-and-algori…

In this weeks interview I had the honour to interview Belgium based artist @ahmadova_marina. Marina catched my eye back in January when she released her now sold out drop “Alius Orbis”. Happy to have had the chance to pick her beautiful brain! 🧠

👉 aiartweekly.com/issues/35

@ahmadova_marina After exploring this weeks lovecraftian theme myself, I found a style I’m extremely in love, so I thought I would start producing weekly style prompts again. This weeks prompt is: "in the style of john bauer, alessandro gottardo, wäinö aaltonen, dark black and light beige"

https://twitter.com/1546508709513265153/status/1661341619969306624

One week after the announcement of DragGAN, developer Zeqiang-Lai put together an unofficial implementation of the paper. Code can be found here.

colab.research.google.com/github/Zeqiang…

Open-source voice training is still a bit of a pain. Luckily there is a new WebUI that you can run on your own hardware. Unfortunately the docs are in Chinese 😅 Luckily again, @NerdyRodent put together a YouTube tutorial.

github.com/RVC-Project/Re…

In case you’ve missed the signup link last week, Google’s MusicLM is in closed beta and you can sign up for access. I did so last week and haven’t heard back yet, but according to @infiniteyay it shouldn’t take longer than a few days 🤞

aitestkitchen.withgoogle.com/experiments/mu…

Part 1 of a three parts series about Generative A.I. by The Economist. Interesting read.

economist.com/interactive/sc…

And that's another week wrapped up. Enjoy your weekend friends ✌️😎

If you haven't already, signup on aiartweekly.com to receive the latest #aiart news directly into your inbox. If you enjoyed this thread, a like, RT and comment go a long way 🧡

https://twitter.com/dreamingtulpa/status/1662134319174008840

@unsafe_dB_level @ahmadova_marina If you like Tweets like this, you might enjoy my weekly newsletter, #aiartweekly.

A free, once–weekly e-mail round-up of the latest AI art news, interviews with artists and useful tools & resources.

Join 1700+ subscribers here:
aiartweekly.com