AIxDESIGN Bookmark Library

Artificial intelligence is changing our creative process by enabling us to generate hyper-real images. Focusing on VQGAN+CLIP, we explore how it works, why it is connected to semiotics and what are artists currently doing with this algorithm. Check out my website for a deeper look at my collaborations with AI : https://www.fabianmosele.com/generating-images-from-text-vqgan-clip 0:00 Intro 1:24 What’s a GAN? 4:23 How does VQGAN CLIP work? 5:37 Semiotics and VQGAN CLIP 9:28 Limits on its dataset 14:13 Limits on its style 16:15 Hyperreality in its essence 19:25 Our AI companion 20:50 Case studies on how artists use it 25:19 Exploitation of image generation 27:49 Ending LINKS in order of appearance: OpenAI’s CLIP https://openai.com/blog/clip/ VQGAN CLIP colab notebook https://colab.research.google.com/drive/1_4Jl0a7WIJeqy5LTjPJfZOwMZopG5C-W?usp=sharing&pli=1#scrollTo=g7EDme5RYCrt RuDALLE’s website https://rudalle.ru/en RuDALLE Telegram bot https://t.me/sber_rudalle_xl_bot Lily Alexandre’s video about AI art https://www.youtube.com/watch?v=Bi4sJEE8wCs Zybrid studio https://www.instagram.com/zybrid.studio Colekush3d https://ckush.com/ Lambert Duchesne https://www.instagram.com/lambertduchesne Monolama https://monolama.com/en/neuro Nightcafe https://creator.nightcafe.studio/ Neural Blender https://neuralblender.com/ Wombo dream https://www.wombo.art/ Hypnogram https://hypnogram.xyz/ MUSIC in order of appearance: RoccoW - Accidental Skwugg Strobotone - Cute Winter Game Theme 01 RoccoW - Nontinde Vendor Theme Soft and Furious - Mermaid Butterfly Jake Allison - Chizzle Dizzle (bollocks office Remix) SKGB - My Girlfriend Left Me For a Tentacle Monster #VQGAN #VideoEssay

Curated list of awesome GAN applications and demo. Contribute to nashory/gans-awesome-applications development by creating an account on GitHub.

You’ll find a number of datasets to train your models

Demos and explanations to make art using machine learning.

by Nono Martínez Alonso

In 2019 The Photographers' Gallery digital programme launched 'Data / Set / Match', a year-long programme that explores new ways to present, visualise and interrogate contemporary image datasets. This introductory essay presents some key concepts and questions that make the computer vision dataset an object of concern for artists, photographers, thinkers and photographic institutions.

Since 2009, coders have created thousands of amazing experiments using Chrome, Android, AI, WebVR, AR and more. We're showcasing projects here, along with helpful tools and resources, to inspire others to create new experiments.

How I created an entire short movie using ML models only (and you can do it as well).

I created a film that was made up entirely of machine learned elements: machine learned sets, characters and textures.

Contribute to google/deepdream development by creating an account on GitHub.

Can you spot the DeepFake? Detect Fakes challenges you to discern AI-manipulated videos from real videos. Can you do better than an algorithm?

Artificial intelligence turning your photos into art

ml5.js aims to make machine learning approachable for a broad audience of artists, creative coders, and students. The library provides access to machine learning algorithms and models in the browser, building on top of TensorFlow.js with no other external dependencies.