Art-A-Hack™ 2023 Special Edition — Warsaw — AI Art in a Time of War

Projects -https://artahack.io/projects/

Alumni

Blog

June 21- Bye Bye At Least Now

When You’re a Jet

Bye Bye For Now Jets

You’re a Jet all the way

Group 1

Code

https://huggingface.co/TheBloke/koala-7B-GGML/tree/main

https://huggingface.co/CRD716/ggml-vicuna-1.1-quantized/blob/main/ggml-vicuna-13B-1.1-q4_0.bin

https://github.com/matib99/YourPersonalGod

Group 2

At the Gallery in Krakow

Group 3

Computing Power and AI Report

https://ainowinstitute.org/publication/policy/compute-and-ai

AI Reading Brainwaves

https://www.euronews.com/next/2023/08/21/this-mind-reading-ai-system-can-recreate-what-your-brain-is-seeing

Create Smooth Videos With Frame Interpolation

https://blog.programster.org/ffmpeg-create-smooth-videos-with-frame-interpolation

How to make frame blending effect

https://www.youtube.com/watch?v=N-HlldkE1Is

Frame Average Node

https://jayaretv.com/fusion/frame-average-node/

Github

https://github.com/vykhovanets/ai_video_pipe

From Lev Manovich:

(AI theory note 28)"AI and the history of digital culture."Generative AI media (2022–) is the fourth major effect of the gradual emergence of a giant digital universe of cultural content (the web). It was born in 1993, when the first graphic browser started popularizing the web. During the 30 years that passed, we see many effects, including these 4:1. The first effect is the switch from categorical, hierarchical and structured organization of information (exemplified by library catalogs and early web directories) to search engines in the late 1990s. There is so much content that organizing it in conventional ways is no longer practical, and search becomes the new default. (Note that search is based on a prediction of what will be most relevant to the user as opposed to giving you a precise answer. AI today is also predictive...)2. The second major effect that interests me is the development of data visualization in first part of the 2000s - another attempt to deal with new data scale. It emerged as a new hip cultural field in 2005-2006. If search attempts to find the most relevant items in the giant data universe, visualization tries to show it as a whole.3. The third effect is the emergence of "data science" as the master discipline of the new era at the end of the 2000s. (While most methods data science uses have already been available for decades, the rapid increase in unstructured data in the 2000s motivated the development of data science as the key new profession of the data society.) My own version of this stage - "cultural analytics" research, 2005-2020. And of course my main method for this research is data visualization but applied to media (images, film, etc.)4. The next, and certainly not the last, major effect of the growth of “digital content society is generative media (GenAI) in the early 2020s. If data science focuses on finding patterns, relations, groupings, and outliers in big data, and if data visualization tries to summarize it visually, generative AI (i.e. particular  machine learning pipelines) approaches “big content” in a different way. It allows the generation of new content with statistical properties related to existing content. Moreover, this new content (texts, images, animation, 3D models, etc.) can interpolate between existing data points, thus creating new content that goes beyond a summary of what already exists. Thus, we move from probabalistic search to probabalistic media generation, 1999 - 2022. 

Here is the link to our repository (group 1)

Week 15 - June 16 - 21 - Race To The Finish

Tony and Sasha our Ukrainian colab members visit from temporary residence in Estonia- Hooray!

Group 3

Media Lab at U of Warsaw

https://www.lbm.uw.edu.pl/lbm.uw.edu.pl

https://www.youtube.com/watch?v=iHx7HjioZH0&t=34s

Killer Robot Dogs Set For War

https://www.dailymail.co.uk/sciencetech/article-11896135/Killer-robot-dogs-controlled-soldiers-MINDS-trialed-Australian-army.html

Eight Reasons To Prioritize BCI Cybersecurity

https://cacm.acm.org/magazines/2023/4/271242-eight-reasons-to-prioritize-brain-computer-interface-cybersecurity/fulltext

Neuralink, OpenWater, DARPA N3, Our Future Matrix-Style Immersive VR

https://hackernoon.com/neuralink-openwater-darpa-n3-and-our-future-matrix-style-immersive-vr

DARPA-funded efforts in the development of novel brain–computer interface technologies

https://www.sciencedirect.com/science/article/pii/S0165027014002702

BCI Experiment Elektryczny Ślad Myśli i Interfejsy Mózg-Komputer 

https://www.youtube.com/watch?v=IldyXnyxtVw

Class Readings

EU Lawmakers Lay Groundwork For Historic AI Regulation

https://www.dw.com/en/eu-lawmakers-lay-groundwork-for-historic-ai-regulation/a-65909881

Autism As A Disorder of Dimensionality

https://opentheory.net/2023/05/autism-as-a-disorder-of-dimensionality/

Edwin Starr - War What Is It Good For - Absolutely Nothing

https://www.youtube.com/watch?v=ztZI2aLQ9Sw

Jackie Chan Sings War

https://www.youtube.com/watch?v=r-bA9FYB8HY

Nature Magazine Bans AI Art

https://news.artnet.com/art-world/nature-magazine-bans-ai-art-2321296?utm_content=from_artnetnews&utm_source=Sailthru&utm_medium=email&utm_campaign=6/18%20Sunday%20AM&utm_term=Daily%20Newsletter%20%5BALL%5D%20%5BMORNING%5D

Grammy Award Issues Statement on AI Content

"Artificial Intelligence (AI) Protocols The GRAMMY Award recognizes creative excellence. Only human creators are eligible to be submitted for consideration for, nominated for, or win a GRAMMY Award. A work that contains no human authorship is not eligible in any Categories. A work that features elements of A.I. material (i.e., material generated by the use of artificial intelligence technology) is eligible in applicable Categories; however: (1) the human authorship component of the work submitted must be meaningful and more than de minimis; (2) such human authorship component must be relevant to the Category in which such work is entered (e.g., if the work is submitted in a songwriting Category, there must be meaningful and more than de minimis human authorship in respect of the music and/or lyrics; if the work is submitted in a performance Category, there must be meaningful and more than de minimis human authorship in respect of the performance); and (3) the author(s) of any A.I. material incorporated into the work are not eligible to be nominees or GRAMMY recipients insofar as their contribution to the portion of the work that consists of such A.I material is concerned. De minimis is defined as lacking significance or importance; so minor as to merit disregard."

How Advertisers Label You

https://themarkup.org/privacy/2023/06/08/from-heavy-purchasers-of-pregnancy-tests-to-the-depression-prone-we-found-650000-ways-advertisers-label-you

Inside The AI Factory

https://nymag.com/intelligencer/article/ai-artificial-intelligence-humans-technology-business-factory.html

Sarah Silverman Sues Open AI

https://www.theverge.com/2023/7/9/23788741/sarah-silverman-openai-meta-chatgpt-llama-copyright-infringement-chatbots-artificial-intelligence-ai?utm_source=Iterable&utm_medium=email&utm_campaign=newsletter-20231207

Week 14 - June 7 to June 13

Group 1

Group 2

GitHub - NVlabs/instant-ngp: Instant neural graphics primitives: lightning fast NeRF and more

https://github.com/NVlabs/instant-ngp GitHub - tetragonites/wolf3d: code four AI Alg Art project number 2code four AI Alg Art project number 2. Contribute to tetragonites/wolf3d development

https://github.com/tetragonites/wolf3d

https://github.com/users/tetragonites/projects/1

Group 3

Class Notes

How Sam Altman Stormed Washington to Set the A.I. Agenda.The chief executive of OpenAI, which makes ChatGPT, has met with at least 100 U.S. lawmakers in recent months. He has also taken his show abroad.

https://www.nytimes.com/2023/06/07/technology/sam-altman-ai-regulations.html

A Week With the Wild Children of the A.I. Boom

https://www.nytimes.com/2023/05/31/magazine/ai-start-up-accelerator-san-francisco.html

Google has created a Generative AI learning path with 9 FREE courses! Topics cover: - Intro to LLMs - Attention Mechanism - Image Generation/Captioning - Intro to Responsible AI From the fundamentals of LLMs to creating & deploying generative AI solutions! Read more Introduction to Generative AI: An introductory level micro-learning course aimed at explaining: - What Generative AI is - How it is used - How it differs from traditional ML Check this out https://lnkd.in/duKJ3sm6 Introduction to Large Language Models: The course explores: - Fundamentals LLMs - Their use cases - Prompt engineering on LLMs Check this out https://lnkd.in/dm_yS4MQ Introduction to Responsible AI: The course explains what responsible AI is, why it's important, and how Google implements responsible AI in their products. Check this out https://lnkd.in/dV8zNvwm Introduction to Image Generation: This course introduces diffusion models, a family of ML models that recently showed promise in the image generation space. Check this out https://lnkd.in/dqcZBZqd Encoder-Decoder Architecture: This course gives you a synopsis of the encoder-decoder architecture. It's a powerful and prevalent machine learning architecture for sequence-to-sequence tasks. Check this out https://lnkd.in/dhDhUgwJ Attention Mechanism: The course teaches you how attention works & how it revolutionised: - machine translation - text summarisation - question answering Check this out https://lnkd.in/dwsZZw6j Transformer Models and BERT Model: This course introduces you to some of the most famous and effective transformer architectures! Check this out https://lnkd.in/dK4p3n2s Create Image Captioning Models: This course teaches you how to create an image captioning model by using deep learning. Check this out https://lnkd.in/d8w32x5Y Introduction to Generative AI Studio: This course introduces Generative AI Studio, a product on Vertex AI. It teaches you to prototype and customize generative AI models so you can use their capabilities in your applications. Check this out https://lnkd.in/dAXdSrEXQwiklabsIntroduction to Generative AI | Google Cloud Skills BoostThis is an introductory level microlearning course aimed at explaining what Generative AI is, how it is used, and how it differs from traditional machine learning methods. It also covers Google Tools to help you develop your own Gen AI apps.This course is estimated to take approximately 45 minutes to complete.lnkd.inLinkedInThis link will take you to a page that’s not on LinkedInQwiklabsIntroduction to Responsible AI | Google Cloud Skills BoostThis is an introductory-level microlearning course aimed at explaining what responsible AI is, why it's important, and how Google implements responsible AI in their products. It also introduces Google's 7 AI principles.QwiklabsIntroduction to Image Generation | Google Cloud Skills BoostThis course introduces diffusion models, a family of machine learning models that recently showed promise in the image generation space. Diffusion models draw inspiration from physics, specifically thermodynamics. Within the last few years, diffusion models became popular in both research and industry. Diffusion models underpin many state-of-the-art image generation models and tools on Google Cloud. This course introduces you to the theory behind diffusion models and how to train and deploy them on Vertex AI.QwiklabsEncoder-Decoder Architecture | Google Cloud Skills BoostThis course gives you a synopsis of the encoder-decoder architecture, which is a powerful and prevalent machine learning architecture for sequence-to-sequence tasks such as machine translation, text summarization, and question answering. You learn about the main components of the encoder-decoder architecture and how to train and serve these models. In the corresponding lab walkthrough, you’ll code in TensorFlow a simple implementation of the encoder-decoder architecture for poetry generation from the beginning.

Audiocraft / MusicGen - AMAZING Text-To-Music AI Model By Facebook | Tutorial | Better Than MusicLM  https://www.youtube.com/watch?v=v-YpvPkhdO4

AlphaDev, an AI system using reinforcement learning to discover enhanced computer science algorithms.

https://twitter.com/DeepMind/status/1666462540367372291

What Happens When AI Enters the Concert Hall?

https://www.nytimes.com/2023/06/10/arts/music/ai-classical-music.html

From Thought to Text: AI Converts Silent Speech into Written Words - Neuroscience News

https://neurosciencenews.com/thoight-text-ai-decoder-23437/

Week 13 - Class Notes May 31- June 6 - To Fly

TO FLY - GET READY FOR IT! - Waiting on Copernicus

https://www.youtube.com/watch?v=3n71KUiWn1I

Group 2

Woof Woof

A Comparison of PPO, TD3 and SAC Reinforcement Algorithms for Quadruped Walking Gait Generation

https://www.scirp.org/journal/paperinformation.aspx?paperid=123401

Group 3

Wonk Proof of Concept

https://www.youtube.com/watch?v=koz6cJuZOAc

Brainwave Control Device by Edmond Dewan

https://www.youtube.com/watch?v=nCGcY6sQjcM

Wiktor’s Shenzhen board arrives in the mail - Hooray!

Class Readings

Artists and Illustrators Are Suing Three A.I. Art Generators for Scraping and 'Collaging' Their Work Without Consent | Artnet News

https://news.artnet.com/art-world/class-action-lawsuit-ai-generators-deviantart-midjourney-stable-diffusion-2246770

Opinion | The Alt-Right Manipulated My Comic. Then A.I. Claimed It.

https://www.nytimes.com/2022/12/31/opinion/sarah-andersen-how-algorithim-took-my-work.html

Stable Diffusion Frivolous · Because frivolous lawsuits based on ignorance deserve a response.

http://www.stablediffusionfrivolous.com

Getty Images is suing the creators of AI art tool Stable Diffusion for scraping its content

https://www.theverge.com/2023/1/17/23558516/ai-art-copyright-stable-diffusion-getty-images-lawsuit

ChatGPT boss wants HQ in Europe (Charm Offensive)

https://www.politico.eu/article/open-ai-chatgpt-sam-altman-kicks-off-eu-charm-offensive-artifical-intelligence/

ChatGPT took their jobs. Now they walk dogs and fix air conditioners.

https://www.washingtonpost.com/technology/2023/06/02/ai-taking-jobs/

Expressions Camera

https://xpressioncamera.com

The world’s first AI ballet has arrived, and it's setting the bar high

https://www.wallpaper.com/art/fusion-ai-ballet-leipzig-opera-house

Andy Warhol paints Debbie Harry on an Amiga - 1985

https://www.youtube.com/watch?v=wLvTG5hwa1A&t=101s

Is A.I. Coming for the Drag Queens Next? A Deep Fake Cabaret at the V&A Exposes the Tech's Limitations | Artnet News

https://news.artnet.com/art-world/is-a-i-coming-for-the-drag-queens-next-a-deep-fake-cabaret-at-the-va-exposes-the-techs-limitations-2308709?utm_content=from_artnetnews&utm_source=Sailthru&utm_medium=email&utm_campaign=6/5%20US%20AM&utm_term=US%20Daily%20Newsletter%20%5BMORNING%5D

AI Now Institute - 2023 Landscape

https://ainowinstitute.org/2023-landscape

Week 12 - Class Notes May 24-30

Group 3

Design of EMG board 1 by Wiktor

https://www.youtube.com/shorts/_wLxJQ7aBgE

Mentalista

https://mentalista.com

Class Readings

Open AI Photoshopping About To Get Too Easy https://www.nytimes.com/2023/05/23/opinion/photoshop-ai-images.html

Man With Paralysis Walks Naturally After Brain Spine Inplants

https://edition.cnn.com/2023/05/24/health/walk-after-paralysis-with-implant-scn/index.html

US Judge Side With Yuga Labs In Bored Ape NFT Trademark Lawsuit

https://www.reuters.com/legal/litigation/us-judge-sides-with-yuga-labs-bored-ape-nft-trademark-lawsuit-2023-04-24/

Bored Ape Creators Score Legal Victory In Lawsuit Against Artists Who Made Copycat NFT Collection

https://www.theartnewspaper.com/2023/04/26/bored-ape-yacht-club-nfts-lawsuit-ryder-ripps-partial-victory

Celebrities that promote Bored Ape NFTs are now facing a class action lawsuit - The list of defendants might as well be a Coachella lineup with names like Diplo, Snoop Dogg, Post Malone, and The Weeknd cited alongside Yuga Labs Inc as well as Justin Bieber, Paris Hilton, Madonna, Jimmy Fallon, and Kevin Hart

https://www.theverge.com/2022/12/13/23507575/bored-ape-yacht-club-yuga-labs-nft-cryptocurrency-lawsuit

Microsoft Calls For AI Rules To Minimize the Technology’s Risks

https://www.nytimes.com/2023/05/25/technology/microsoft-ai-rules-regulation.html

Grimes clones her voice - anyone can make a song with it - https://elf.tech/connect

Martian Love - Where You Want - AI Movie

https://www.youtube.com/watch?v=hQG9ZAdjsPI

Lorn Music Video

https://www.youtube.com/watch?v=3ApMSKql23I

AI Based Copycats

https://www.youtube.com/watch?v=McM3CfDjGs0

System Aesthetics - We are now in transition from an object-oriented to a systems-oriented culture. Here change emanates, not from things, but from the way things are done.

https://www.artforum.com/print/196807/systems-esthetics-32466artforum.com

What happens when your lawyer uses Chat GPT-3 - It did not go well https://www.nytimes.com/2023/05/27/nyregion/avianca-airline-lawsuit-chatgpt.html

YouTube Science Scam

https://www.youtube.com/watch?v=McM3CfDjGs0

Statement On AI Risk

https://www.safe.ai/statement-on-ai-risk#open-letter

"AIBO—An Emotionally Intelligent Artificial Intelligence Brainwave Opera—Or I Built A "Sicko" AI, and So Can You" in Information Disorder - Algorithms and Society published by Routledge Books - https://www.routledge.com/Information-Disorder-Algorithms-and-Society/Filimowicz/p/book/9781032290775

World’s First AI Generated Statue

https://news.artnet.com/art-world/impossible-statue-ai-generated-stockholm-museum-23[…]ay%20AM%20US&utm_term=US%20Daily%20Newsletter%20%5BMORNING%5D

Week 11 - ISEA Paris Week May 17-23

Photo by Alain Thibault

Group 1

MMS: Massively Multilingual Speech. - Can do speech2text and text speech in 1100 languages. - Can recognize 4000 spoken languages. - Code and models available under the CC-BY-NC 4.0 license. - half the word error rate of Whisper.

Github

https://github.com/facebookresearch/fairseq/tree/main/examples/mms

Paper

https://scontent-lga3-2.xx.fbcdn.net/v/t39.8562-6/348836647_265923086001014_687800580827579[…]GkLV3haLgAXkFFhYmxMG8D9J2WV1hKDqYAQNPW4-4g&oe=6471ACCF

Blog

https://ai.facebook.com/blog/multilingual-model-speech-recognition/?utm_source=twitter&utm_medium=organic_social&utm_campaign=blog&utm_content=cardMeta AI

Group 2

Using .skn skin file as model texture  · Issue #128 · deepmind/mujoco

https://github.com/deepmind/mujoco/issues/128

Infusion Systems

https://infusionsystems.com/catalog/product_info.php/products_id/693

SAC Algorithm

https://github.com/rail-berkeley/rlkit/blob/master/examples/sac.py

TDMPC

https://github.com/nicklashansen/tdmpc

Temporal Differences

https://www.youtube.com/watch?v=s-y_110sTTA

Group 3

Facial EMG and Reactions

https://onlinelibrary.wiley.com/doi/epdf/10.1111/j.1469-8986.1990.tb01962.x

Wiki

https://en.wikipedia.org/wiki/Facial_electromyography

VR Touch and Emotions

(PDF) Touching Virtual Humans: Haptic Responses Reveal the Emotional Impact of Affective Agents PDF | Interpersonal touch is critical for social-emotional development and presents a powerful modality for communicating emotions. 

Stability AI Released Stability Studio

https://stability.ai/blog/stablestudio-open-source-community-driven-future-dreamstudio-release

OSC Into Touch Designer

https://infusionsystems.com/catalog/info_pages.php?pages_id=181

Synaptogenesis

https://www.youtube.com/watch?v=1fnm1vGGRYI&t=12s

Class Notes

Open AI’s Sam Altman urges AI Regulation

https://www.nytimes.com/2023/05/16/technology/openai-altman-artificial-intelligence-regulation.html

Supreme Court Rules Against Andy Warhol in Prince Case

https://www.nytimes.com/2023/05/18/us/supreme-court-warhol-copyright.html

https://hyperallergic.com/822888/supreme-court-rules-against-andy-warhol-foundation-in-lynn-goldsmith-copyright-case/

German Artist Michael Moebius Wins $120 Million in a 'Monumental' Lawsuit Against Hundreds of Foreign Counterfeiters | Artnet News

https://news.artnet.com/art-world/artist-michael-moebius-wins-monumental-copyright-l[…]0PM&utm_term=Daily%20Newsletter%20%5BALL%5D%20%5BAFTERNOON%5D

Inferno

https://www.youtube.com/watch?v=sGIbZ5DD4fY

Meta slapped with record $1.3 billion EU fine over data privacy

https://edition.cnn.com/2023/05/22/tech/meta-facebook-data-privacy-eu-fine/index.html

Ellen Waving From ISEA 2023 Paris

https://www.youtube.com/shorts/S9nxI7XTHhI

Week 10 -Class Notes May 10-May 15

Exhibition Proposal Draft

Week 9 MidTerm Break - Moving Forward April 27 - May 9

Class Readings

Humane AI Wearable Camera

https://www.inverse.com/tech/humane-ai-wearable-camera-sensor-projector-video-demo

Ashton Kutcher’s AI Investment Firm

https://variety.com/2023/digital/news/ashton-kutcher-guy-oseary-sound-ventures-ai-investment-fund-1235599939/

Anthropic - An AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.

https://www.anthropic.com/

How Do We Ensure AI Is For Humans?

https://www.nytimes.com/interactive/2023/05/02/magazine/ai-gary-marcus.html

There Is No AI - Jaron Lanier

https://www.newyorker.com/science/annals-of-artificial-intelligence/there-is-no-ai

Geoff Hinton on AI

https://www.youtube.com/watch?v=N0ER1MC9cqM

My Weekend With An Emotional Support AI

https://www.nytimes.com/2023/05/03/technology/personaltech/ai-chatbot-pi-emotional-support.html

Stability AI Releases Deep Floyd Text To Image Model

https://stability.ai/blog/deepfloyd-if-text-to-image-model

Is Crafting ‘Super Prompts’ for A.I. Generators the Art of the Future? Probably Not

https://news.artnet.com/opinion/ai-prompt-engineer-2288620?utm_content=from_artnetne[…]28%20US%20AM&utm_term=US%20Daily%20Newsletter%20%5BMORNING%5D

Free GPT-4 Chatbot - Ora - Create your own chatbot with just a description and a click

ora.ai

Janusz Janowski nowym dyrektorem Zachęty. Historia tej nominacji pokazuje zasadniczy błąd konserwatystów wobec sztuki współczesnej

https://klubjagiellonski.pl/2022/01/22/janusz-janowski-nowym-dyrektorem-zachety-histor[…]e-zasadniczy-blad-konserwatystow-wobec-sztuki-wspolczesnej/

Chinese police detain man for allegedly using ChatGPT to spread rumors online | CNN Business

RIP Metaverse, we hardly knew ye

https://edition.cnn.com/2023/05/09/tech/china-arrest-chatgpt-hnk-intl/index.html

Art-A-Hack Metaverse project in 2016  (way before Meta) https://artahack.io/projects/metaverse-art-gallery/

Art-A-Hack 2016 - Metaverse Art Gallery 

https://www.youtube.com/watch?v=KyNQ89wivbc

HOW I FAKED MY LIFE USING AI: or (THE LIFE AND DEATH OF RYAN GOSLING PERSON) 

https://www.youtube.com/watch?v=FRClNMC_z-s

https://www.businessinsider.com/metaverse-dead-obituary-facebook-mark-zuckerberg-tech-fad-ai-chatgpt-2023-5?IR=T

Group 2

MuJoCo stands for Multi-Joint dynamics with Contact.

https://mujoco.org/

Multi-Joint dynamics with Contact. A general purpose physics simulator. - mujoco/LICENSE at main · 

deepmind/mujoco

GitHub - deepmind/mujoco: Multi-Joint dynamics with Contact. A general purpose physics simulator.

GitHub

https://github.com/deepmind/dm_control

Shap-E - A conditional generative model for 3D assets

https://github.com/openai/shap-e

https://arxiv.org/abs/2305.02463

Group 3

Richard Teitlebaum biometrics 1968

Nina Sobell interviewed by Renata Janiszewska 

https://techspressionism.com/video/interview/sobell/

World’s largest grammar database reveals accelerating loss of language diversity

https://www.colorado.edu/today/2023/04/19/worlds-largest-grammar-database-reveals-accelerating-loss-language-diversity

New open-source hardware thrusts brain-signal processing into a maker’s world

https://spectrum.ieee.org/neurotechnology-diy

Emotibit News

https://mailchi.mp/fb992b5417d5/emotibit-update-get-beta-access-5396656?e=2df651d2da

DeFlickering

https://chenyanglei.github.io/deflicker/

Cemetery Project

https://radom.wyborcza.pl/radom/7,48201,29725481,miedzynarodowy-projekt-badawczy-na-cmentarzu-zydowskim-w-przysusze.html

How To Install Automatic 111 On A Mac

https://www.youtube.com/watch?v=DUqsYm_rYcA

Group 2 Weeks 5 - 8

Progress with implementing learning with the 3D model in a physical environment has been slow, but steady. Initilly we were experiencing issues with the 3D model imported from Maya into Unity, but were able to get it working with Unity's physics engine as you can see here:

With this 3D model we were able to get the character moving from place to place using manually assigned ranges of motion for each joint:

But were having some issues with the 3D model not holding it's form together in the way we hoped it would. In order to remedy these issues of the 3D model not working expected, we have opted to rebuild it in Unity, where it should work in a more predictable way:

On the visualization side, we are developing hand-drawn animations that we hope will play over the surface of the character model, stills of which you can find here:

This approach my need to change now that the model is built within Unity and may be harder to extract back out of it for the purposes of rendering.

We are also beginning to consider the environment that the wolf will have to traverse. We have acquired the heightmap of a 1 km square around Węgrów, which we have converted into geometry which can act as the base surface for the wolf to walk on:

In the physical world, the wolf's rig has become a part of the bell that will be in the installation and later public monument in Węgrów, as a sort of zoetrope going along the top of a bell made by the Kruszewscy Bell Company in Węgrów, the same company that has mae and maintains all of the church bells in Węgrów. Here is an image of the bell after just coming out of casting in brass, before polishing and weatherproofing:

Week 8 - You So Done

You So Done - Noga Erez

https://www.youtube.com/watch?v=Xn813NKlhzI

Readings April 19 - April 25

Group 3

3D Brainwave Sculptures

https://artahack.io/projects/deep-thought/

Measuring The Magic of the Mutual Gaze

https://www.youtube.com/watch?v=Ut9oPo8sLJw

Ultra Sharp Upscale

https://www.youtube.com/watch?v=A6dQPMy_tHY

Flicker Free Animations

https://www.youtube.com/watch?v=Qph7A3UaVds

Kandinsky 2.1 open source image generator 

 https://www.youtube.com/watch?v=dYt9xJ7dnpU

https://github.com/ai-forever/Kandinsky-2

Kandinsky 2.1 inherits best practicies from Dall-E 2 and Latent diffusion, while introducing some new ideas.

As text and image encoder it uses CLIP model and diffusion image prior (mapping) between latent spaces of CLIP modalities. This approach increases the visual performance of the model and unveils new horizons in blending images and text-guided image manipulation.

For diffusion mapping of latent spaces we use transformer with num_layers=20, num_heads=32 and hidden_size=2048.

Other architecture parts:

Text encoder (XLM-Roberta-Large-Vit-L-14) - 560M

Diffusion Image Prior — 1B

CLIP image encoder (ViT-L/14) - 427M

Latent Diffusion U-Net - 1.22B

MoVQ encoder/decoder - 67M

Kandinsky 2.1 was trained on a large-scale image-text dataset LAION HighRes and fine-tuned on our internal datasets.

Deforum Art Text 2 Video

https://github.com/deforum-art/sd-webui-text2video

Deforum Art For Automatic 1111 Web UI

https://github.com/deforum-art/deforum-for-automatic1111-webui

Trailer - All This Can Happen

https://www.youtube.com/watch?v=KMOPMRJiNSQ

General Links

AI, Drake, The Weeknd Fake

https://www.nytimes.com/2023/04/19/arts/music/ai-drake-the-weeknd-fake.html

Sarcastic Robot Powered By GPT-4

https://www.youtube.com/watch?v=PgT8tPChbqc

Group 3, Week 8 - EMG Sound

No sound in the video but instead an illustration of how muscle motion would become sound through captured data.

Group 1 - video sample 2

We lose colour, we are voiceless, and AI speaks for us

Group 1 Week 8 - morphing projection

The voice generated by the AI can be heard: "The risk of losing our culture ... " 

Group 1 Week 8 - Video sample

Group 3 Week 8 - Test framing

Need to work out language subtitles, frame rate, flickering, timing, layout. Rendered in H624.