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

ai/ml in visuals


Link to this page location: #about

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.


More information will be provided later


7 weeks

Your skill level

Beginner, Intermediate




2 lessons per week

End date



Online, Curated

Who needs this

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

Link to this page location: #galery

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

Vadim Epstein

Course Author

Stanislav Glazov

Instructor for TouchDesigner integration

Vadim Epstein


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 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

Link to this page location: #book

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