Link to this page location: #top
Link to this page location: #top

ai/ml in visuals

UNDER THE HOOD

Link to this page location: #about

about the course

Within 7 weeks you will get core theory of Visual AI/ML and handy instruments - both installed on your local machine and available in the cloud - including GANs, Stable Diffusion and other practical tools for image processing.

Academic approach without academic complexity

The course may be treated as a comprehensive guided tour, aimed to establish solid ground for the further AI/ML experiments.

It delivers principles and details of the Neural Networks operations without sinking in the complex math formula and/or professional programming. The architectures and their specifics are also covered up and down - from an entire picture to the low-level experiments.

Creative origin

Author of the course is a recognized practicing artist, thus the program is built upon the artistic point of view, exploring aesthetic (and/or even semantic) side of the technology on par with its functional features. The course also goes beyond popular toolkits and includes few less known tricks and techniques, introduced by the author. In short - it’s by an artist and for the artists.

Clear perspective

One of the most important aspects of the course - the holistic Creative Coding approach, connecting "classic" generative practices like TouchDesigner to the modern AI/ML applications. While it may lack some hot niche topics like prompt engineering, it gives a uniform understanding of the area and its place in the modern hi tech artistry.

Various practical outcomes

Course material represents a balanced combination of theory and custom opensource instruments. Alongside general concepts development, students will master specific tools - from DeepDream to GANs to Stable Diffusion - having it set up at their disposal. This won’t compete with the army of Youtube tutorials tweaking UIs; instead, it completes them with a view from the inside.

Start

June 2024

Duration

7 weeks

Your skill level

Beginner, Intermediate

Software

PyTorch/TouchDesigner

Commitment

2 lessons per week

End date

Soon

Format

Online, Curated

Who needs this

Motion Designers Media Artists 3D Artists VR / XR Producers NFT Artists Interactive Developers Musicians VJs AI/ML Enthusiasts Designers

course format & materials

Online video lectures twice a week [Monday /Thursday]

Lecture notes with reference links. Exercises in Colab and with locally installed software

[During the course] Chat with the tutor, course curators, and other participants

Collection of Github repositories and private code with full installation support

Link to this page location: #galery
name
name

syllabus

Detailed course program

1.1. Intro to the course
Python, Colab vs local, libraries and modules. Framework setup.
1.2. Introduction to the neural networks
Neuron, graph, loss function. Training as an optimization process. CPPN (image reproduction)

2.1. CNN: concept, features
Convolutions as graphics filters, how they process & store data.
2.2. Architectures & building principles
Style transfer, autoencoders, GAN. Features, iterative pipeline, network extensions.

3.1. Modern GANs
ProGAN, StyleGANs. Latent space - animation, blending, projection, special tricks.
3.2. StyleGAN2 training
Data preparation, training process. Augmentation.

4.1. Image transformations (image-to-image)
From pix2pix to StarGAN2. Applied methods overview.
4.2. Integration with TouchDesigner
OSC, NDI, built-in Python with TouchEngine

5.1. Multimodal synthesis with foundation models
CLIP, early iterative methods. CPPNs, Aphantasia, VQGAN.
5.2. Transformers & Diffusion models
Principles & specifics. Denoised & latent diffusion.

6.1. Stable Diffusion as the current generative tool #1
Architecture, use cases: txt2img, img2img, interpolations
6.2. SD control & finetuning
Controlnet. Textual inversion, custom diffusion, LoRA, ..

Development of the own project with visual AI/ML methods

outcomes from the course

Comprehension of the Neural Networks principles. Low-level experiments with visual ML

Comprehension of the modern NN architectures (convolutional, transformers, diffusion).

Applied skills to train & use modern GAN models.

Practical comprehension of the modern generative paradigm with multimodal models.

Skills to use and customize Diffusion methods.

Use of generative AI/ML in the integrated projects.

Team

We are are a team of professionals ready to help you throughout the journey. Besides an ample technical expertise, each of us has an individual style and a unique vision to share with you.

Vadim Epstein

Course Author

Stanislav Glazov

Instructor for TouchDesigner integration

Vadim Epstein

MEDIA ARTIST, DIRECTOR, EDUCATOR, CODER, VJ

Former IT consultant and casual theoretical physicist, combining serious technical background, strong corporate experience and vivid creative mind. Has worked in various fields such as net.art and science art since 1996, eventually focused on visual media with stochastic algo narratives.

As an artist and curator, had made visuals for hundreds of concerts, festivals, parties, and commercial events. The artworks have been exhibited worldwide in Montreal, Vancouver, Stuttgart, Paris, London, Moscow, Lille; highlighted on the conferences NeurIPS 2020 / 2021 / 2022, CVPR 2021; sold as NFT collections, etc.

Besides commercial and personal projects, has delivered numerous talks, workshops and training courses.

More info

Why people choose AI/ML in Visuals course The course is not a bunch of Youtube tutorials, rather it’s a holistic ground for your growth in the AI/ML area  It teaches the fundamentals of neural networks  The course is well balanced over the core theory and handy practical tools  The AI/ML in Visuals course has been evolving since 2019  taught to more than 200 artists and designers The course will teach you how not to fear AI taking your job, Instead, you will learn how to manage them and use them to your advantage Prerequisites are flexible: the more you know, the more you get. No hardcore math ahead, yet Python literacy is advised  The course follows Creative Coding ideas, exploring custom ways rather than using ready-made tools  The AI/ML in Visuals course expands "old-school" generative practice onto modern AI-driven realms The course teaches both renowned concepts and bespoke author tricks 

Link to this page location: #book

777€ 555€

online course starts in june

We will announce the exact start date in May

*you can pay 99€ now to fix early bird discount

  • Access to the course sessions
  • Access to lecture notes with references
  • Access to private code & models
  • Access to the shared chat for homeworks & topics discussions
  • Assistance with your final project

Incl. VAT: 88,61 €
If you have EU VAT ID,
please, contact us to avoid double tax

FAQ FAQ FAQ FAQ

Minimum skills (not strongly required, but get ready to learn): familiarity with command line (shell) operations.
Programming skills will greatly help with exploring specific details of the used instruments.
Prerequisites are flexible: the more you know, the more you get.

Complete course program would require Windows computer with a decent Nvidia GPU with at least 6Gb VRAM (hard minimum is 1060, reasonable level 2070+).
Users with Macs would be able to use Collab versions (no integration with TD in this case).

Partial payment option available: 50% before the start of the course and 50% 1 month after the start

All practical topics have corresponding tasks to complete as homeworks. Most of them require to repeat the actions from the lectures on your own supply.We recommend to execute them even if everything is clear in theory - to ensure that you won’t face unexpected issues in your future work.
During final week you will have to develop and complete your own project (with our assistance) as a kind of exam of the obtained knowledge.

10-12 hours per week should be sufficient to master necessary concepts and skills. You may want to invest more time for more exhaustve explorations though. Remember, the course program is somewhat open-ended: nearly all topics are not limited in scope, and have lots of options for extra developments.

Link to this page location: #contacts