The use of AI in the arts is all anyone can seem to talk about today, but what’s the story behind all of this new tech? While many creatives and their teams are fearful of the implications of all this rapid innovation, we’re finding ever more success stories of creatives who have managed to harness the power of AI to enhance their creative journeys. But don’t just take our word for it.
In this episode of the Mix, we sat down with interdisciplinary artist, designer, educator, and AI video designer Ben Gillin, and he shared his process on video design using AI softwares such as mid journey, a few anecdotes from his recent successes, and his thoughts about the taboo behind AI in the arts.
Open Source: refers to a software or project that is developed and made available to the public with its source code accessible, allowing anyone to view, modify, and distribute the code according to the terms of its associated license.
Algorithm: A set of instructions or rules followed by a computer program to perform a specific task or solve a problem. Algorithms can be used to analyze data, make predictions, or automate processes.
Python: A widely used programming language known for its simplicity and readability. It is often used for web development, data analysis, artificial intelligence, and various other applications.
HTML, CSS, JavaScript: These are core technologies for building and designing websites. HTML (Hypertext Markup Language) is used for structuring content, CSS (Cascading Style Sheets) is used for styling and layout, and JavaScript is used for adding interactivity to web pages.
Text-to-Text Algorithm: An algorithm that takes input in the form of text and produces output in the form of text. It can be used for various natural language processing tasks such as language translation, summarization, and more.
Artificial Intelligence (AI): The simulation of human intelligence processes by machines, especially computer systems. AI technologies can include machine learning, natural language processing, computer vision, and more.
Lyrics Generation: The process of creating song lyrics using computational methods. AI algorithms can be trained to generate lyrics that mimic the style of different artists or genres.
Machine Learning: A subset of AI that involves training algorithms to learn patterns from data and make predictions.
Chatbot: A computer program designed to simulate conversation with human users, often used for customer support or information retrieval.
Natural Language Processing (NLP): A branch of AI that focuses on the interaction between computers and human language. NLP enables computers to understand, interpret, and generate human language.
Web Design: The process of creating the visual and interactive aspects of websites. It involves layout design, color schemes, typography, and user experience considerations.
Artificial Neural Networks: A computational model inspired by the structure and function of the human brain, often used in machine learning to process complex patterns and relationships in data.
Upscale: The process of increasing the resolution or quality of an image using various algorithms or techniques. AI can be used to enhance the details of images.
Photo Realistic: A quality of graphics or images that closely resemble real-life objects or scenes. AI can generate images that mimic reality with high fidelity.
Discord: A communication platform often used for text, voice, and video chatting, commonly used by gamers and communities. In this context, it's used to interact with AI models.
Model Training: The process of teaching an AI algorithm by exposing it to large amounts of data. The algorithm learns patterns from the data to make predictions or generate outputs.
Painterly Aesthetic: A visual style in which images resemble paintings, often characterized by brushstroke-like textures and artistic qualities.
Image Upscaling: Using algorithms to increase the size or resolution of images, enhancing their clarity and details.
Quality Enhancement: Improving the quality of an image, video, or other media using various techniques, which can include reducing noise, enhancing colors, and increasing sharpness.
Chat Service: A platform or application that enables users to communicate through text, voice, or video. In this context, referring to the platform where the interaction with the AI model occurs.
Prompt: A prompt is a piece of text used to instruct or guide an AI model in generating content. It provides the initial input for the AI's creative process.
Copyright: Legal protection granted to original works of authorship, giving the creator exclusive rights to use, distribute, and reproduce their work.
License Holders: Individuals or entities that hold the rights to specific content, allowing them to grant or deny permissions for its use by others.
Content Identification: The process by which platforms like YouTube automatically detect copyrighted material within uploaded videos, both in terms of audio and images.
Generative AI
Is a type of Artificial Intelligence that is capable of generating images, texts, or other media using learned behavior from a variety of inputs.
MidJourney
MidJourney is an image generator that operates through Discord. They are building a web application but it’s in alpha at the moment. MidJourney lets you generate 1 image at a time and doesn’t do video by default.
Website | Docs
Stable Diffusion
Stable Diffusion can generate images and videos. Stable Diffusion is open source and can be downloaded to use anyway you’d like. There are plenty of generative stable diffusion models to choose from and you can even train your own with your own artwork.
There is a bit more of a learning curve when using Stable Diffusion as there are many ways to use it. The most common is through Google Colab notebooks.
Google Colab Notebooks
Ben uses Colab solely for Stable Diffusion projects. In general, Colab is a free Jupyter Notebook service with built-in GPUs and TPUs, ideal for machine learning, data science, and education.
Deforum - What most people cut their teeth with when it comes to Ai animation.
Video Killed the Radio Star - Open Source project to generate music videos using Ai. This was originally created by David Marx based on my videos. It’s evolved over time to be a robust set of features tailored for music video generation based on music files.
Fast Stable Diffusion aka Automatic1111 - Multi-tool for stable diffusion that has extensions for anything and everything.
KLMC2 - Creates short or long form ambient slow moving animations that are almost dreamlike.
WarpFusion - An advanced notebook you can support and gain access to on their Patreon.
Featuring: Ben Gillin (interdisciplinary artist, designer, educator, and AI video designer)
Thanks for tuning into the Mix! The Mix is a Musixmatch Pro podcast aimed at further education for Creators, Mangers, Reps, Artists, Singer Songwriters & everyone on the topics of today!
.png)
