https://github.com/johnowhitaker/aiaiart

Course content and resources for the AIAIART course.
https://github.com/johnowhitaker/aiaiart

Last synced: 3 months ago
JSON representation

Course content and resources for the AIAIART course.

• Host: GitHub
• URL: https://github.com/johnowhitaker/aiaiart
• Owner: johnowhitaker
• License: mit
• Created: 2021-09-11T09:50:05.000Z (about 3 years ago)
• Default Branch: master
• Last Pushed: 2022-11-03T13:05:46.000Z (about 2 years ago)
• Last Synced: 2024-05-15T12:30:07.755Z (6 months ago)
• Language: Jupyter Notebook
• Size: 37.6 MB
• Stars: 563
• Watchers: 21
• Forks: 46
• Open Issues: 0
• Metadata Files:
  • Readme: readme.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-generative-ai - GitHub - johnowhitaker/aiaiart

README

        
# AIAIART course

NEWS: I'm working on a successor to this course called 'The Generative Landscape' which will be out mid-November. Development for that will be happening in [this repository](https://github.com/johnowhitaker/tglcourse).

This repo contains the notebooks used for the AIAIART course. Part 1 (first four lessons) ran via Discord in September/October 2021. Part 2 started in April 2022 and wrapped up with Lesson 9. Join the Discord linked below for course-related chat and reminders of any upcoming additions.

The videos for each lesson are linked within the notebooks, but can also be viewed in this YouTube playlist: https://www.youtube.com/playlist?list=PL23FjyM69j910zCdDFVWcjSIKHbSB7NE8

Notebooks:

- Lesson 1 - PyTorch, Tensors, Gradient Descent (colab): https://colab.research.google.com/drive/1pp8hS5C6RTMpOLBJMwnx3d7JjicqgJKx?usp=sharing

- Lesson 2 - Learning Representations, Style Transfer (colab): https://colab.research.google.com/drive/1Rk8cXMdad9ASIVI6avPyp5bl0qmeOu6S?usp=sharing

- Lesson 3 - GANS+CLIP (colab): https://colab.research.google.com/drive/1qnV7PT1aSwomXvRmdoY_pgcR2ruvm6Of?usp=sharing

- Lesson 4 - Going Further (colab): https://colab.research.google.com/drive/1ipnriyQ-S5PD97sqZo4aieQOefMlkPwJ?usp=sharing

- Lesson 5 - Recap of key ideas and start of part 2: https://colab.research.google.com/drive/1cFqAHB_EQqDh0OHCIpikpQ04yzsjITXt?usp=sharing

- Lesson 6 - Transformers for image synthesis and VQ-GAN revisited: https://colab.research.google.com/drive/1VhiIxMw9YClzmwamu9oiBewhZPnhmSV-?usp=sharing

- Lesson 7 - Diffusion Models: https://colab.research.google.com/drive/1NFxjNI-UIR7Ku0KERmv7Yb_586vHQW43?usp=sharing

- Lesson 7.5 - We had a less formal stream chatting about a few new papers and looking at an experiment with CLOOB Conditioned Latent Denoising Diffusion GANs. Stream recording: https://youtu.be/OBrlYBP4GZA

- Lesson 8 - Neural Cellular Automata: https://colab.research.google.com/drive/1Qpx_4wWXoiwTRTCAP1ohpoPGwDIrp9z-?usp=sharing

- Lesson 9 - Evolutionary Algorithms and CPPNs: https://colab.research.google.com/drive/1Od3xufd6SUe0-6SgGUJ8sIP8AYI8oEgD?usp=sharing

More recently, I've also shared a few bonus notebooks while working on the new course:

- Grokking Stable Diffusion: https://colab.research.google.com/drive/1dlgggNa5Mz8sEAGU0wFCHhGLFooW_pf1?usp=sharing (Breaking down the different components and showing how you can hack them to achieve different effects)

- Grokking SD Part 2: Textual Inversion: https://colab.research.google.com/drive/1RTHDzE-otzmZOuy8w1WEOxmn9pNcEz3u?usp=sharing (Exploring how textual inversion adds new 'concepts' to the vocabulary.

Feel free to reach out to me @johnowhitaker on Twitter with feedback, questions or requests. And come join our discord to share your work and chat with others doing similar projects: https://discord.gg/vSjhr8xb4g. The Discord is the best way to hear about upcoming lessons and livestreams.

All code and content in this repo is released under the [MIT licence](https://opensource.org/licenses/MIT).