What’s your background and how did you get into AI art?
I hold a degree in commercial art and have been passionately pursuing a career as an artist for over two decades. My journey has been multifaceted, encompassing roles as a traditional painter, gallery curator, and digital artist—a title I proudly retain to this day.
My first foray into the world of AI art was through PIFUHD, an innovative tool that may be unfamiliar to some. PIFUHD was, and continues to be, an early version of technology that transforms images into 3D models. This tool has been instrumental in my work, particularly in projects that incorporate figurative 3D models. It allowed me to effortlessly create 3D models, and I was driven to explore its full potential. By experimenting with unconventional human collages, I was able to observe the unique models that emerged. These models became a defining feature in some of my early digital collectibles, dating back to 2021.
The integration of AI into my artistic process has not only expanded my creative horizons but also symbolizes the exciting intersection of technology and art. It’s a testament to how innovation can breathe new life into traditional mediums, opening doors to uncharted territories of expression and design.
Do you have a specific project you’re currently working on? What is it?
Currently, I’m in the midst of finalizing a project for SuperRare, a platform renowned for its digital art. This particular endeavor involves the transformation of images into 3D models, the integration of Midjourney textures, and I’m still contemplating whether to incorporate sound and/or voice. It’s a multifaceted project that reflects my commitment to pushing the boundaries of digital artistry.
In addition to the SuperRare project, I’m also working on a submission for Fubar, an annual glitch art festival that celebrates the unconventional and avant-garde.
Beyond these specific projects, I make it a point to create and share experimental pieces on Social Media every day. This daily practice is more than a routine; it’s a creative exploration that allows me to test new ideas, experiment with emerging technologies, and gauge my enjoyment of different artistic processes. It’s a continual journey of discovery that helps me identify potential avenues for expansion and innovation. By sharing these experiments with the public, I not only engage with a broader audience but also foster a sense of openness and collaboration in the ever-evolving world of digital art.
What drives you to create?
I’ve maintained a daily art practice since my high school days, so it might sound cliché, but creating has become more than a passion — it’s a habit. The world is brimming with inspiration, offering endless material for visual commentary. Whether it’s the natural beauty of our surroundings or the ever-changing landscape of news and current events, every day presents a multitude of new ideas and visual stimuli.
With the advent of digital technology, the possibilities for artistic expression have expanded exponentially. The tools at our disposal allow us to capture, manipulate, and convey complex ideas in ways that were previously unimaginable. This constant evolution fuels my creativity and drives me to explore new horizons.
What does your workflow look like?
Workflow and process are integral to my artistic practice, and I’m continually experimenting with various pipelines and systems to achieve the desired results. My approach is dynamic, embracing both traditional tools and cutting-edge technologies.
Here’s an illustrative example of my workflow:
- Prompt Creation: I might start with a simple prompt in Stable Diffusion, such as
70s fashion model, disco club, New York City.
- Midjourney Image: I use the same prompt to create an image for the Mid Journey phase.
- Image Editing: I crop the head in Photoshop and upscale it using AI technology like Topaz.
- Script Generation: I generate a script using ChapGPT.
- Voice Creation: I create a voice using Eleven Labs.
- Avatar Creation: I use the head image to create a talking avatar in D-ID Studio.
- Texture Development: I use the video as a texture in Blender.
- Background Creation: I create background textures in MidJourney.
- Final Composition: I composite everything in After Effects.
I’ll iterate through this workflow, adding or subtracting elements to see what works best over time. It’s a process of continuous refinement and exploration.
Lately, I’ve been experimenting with a diverse array of tools, including:
- Blender (with dream texture)
- Stable Diffusion
- AnimeDiff (for looping Stable Diffusion)
- CSM (for image to 3D conversion)
- ECON (for image to 3D conversion)
- Photoshop (using generative fill)
This blend of tools allows me to create works that I feel have a strong visual element but also deeply resonant with the themes and concepts I wish to explore. It’s a workflow that’s as dynamic and multifaceted and is constantly evolving.
What is your favourite prompt when creating art?
My favorite prompts for creating art are often simple yet intriguing, allowing for a wide range of interpretations and creative explorations. A prompt that I frequently return to is:
An ultra-realistic, colorful, [non-human] in [t-pose], wearing an [oversize pixelated glitch costume] in a [photo studio], full body, [shoes].
I typically begin with an initial image, adjusting its weight depending on the results I’m aiming for. This prompt serves as a versatile foundation, and I’ll use it across various generators, taking the results and either feeding them back into themselves or cross-breeding them with other elements.
My primary goal in utilizing AI imagery is to create textures for 3D models. The fusion of AI-generated visuals with 3D modeling opens up exciting possibilities, allowing me to craft unique and captivating pieces.
Here are some examples of my work that include this prompt:
How do you imagine AI (art) will be impacting society in the near future?
AI’s impact on art and society is already profound, and I believe its influence will only continue to grow in the near future. Many of us have been utilizing AI technologies for years without even realizing it, whether through tools like Photoshop’s content-aware feature or voice assistants like Alexa and Siri.
The past six months have been particularly transformative in the realms of image, voice, text, and video generation. The pace of innovation has been astonishing, and it’s become increasingly challenging to keep up with the rapid advancements. As someone deeply engaged with technology, I find this era incredibly exciting. The opportunity to experiment with new tools and techniques is thrilling, and the creative possibilities seem virtually limitless.
However, this excitement is tempered by unresolved issues related to copyright and ownership of artwork. The integration of AI into the artistic process raises complex questions about authorship, intellectual property rights, and ethical considerations. These are challenges that the art community and society at large must grapple with as we move forward.
I envision a future where artists are empowered to create their own models for generating art, and where the tools to do so become more accessible to non-technical individuals and those with limited resources. The democratization of AI art tools has the potential to foster a more inclusive and diverse creative landscape, allowing more voices to be heard and more visions to be realized.
Who is your favourite artist?
- AI: Roope Rainisto, Claire Silver, @Ganbrood
- Glitch Alpha Force: Sky Goodman, @Sabato, Dawnia
- Tezos / ETH: @Xer0x_NFT, @0x3y3, @spogelsemaskine
- Generative: @simondemai, @annaluciacodes, @kimasendorf
- Trad Art: @chrisduncanartandsounds, @tau_au, @juliemehretu
- Artist / Curators: @thedinachang, @RefractionDAO, @cabline1
Anything else you would like to share?
Shoutouts to all the collectors and curators and supporters, love you all