Mums Against Donk 4
Machine learning and real-time generative visuals for London's leading donk and happy hardcore club night.
Building on my existing work with the collective, I created a visual set that pays homage to their event's reputation as being camp and silly. With TouchDesigner, I designed a set of generative components that respond in real-time to the incoming audio from the decks. These components are inspired by liquid light shows, and make use of generative growth systems, noise displacements and video distortion.
To complement Alterum's DJ set, I used transfer learning to manipulate a GAN model to create abstracted, morphing looping visuals that were displayed behind her throughout. Alterum always wears distinctive makeup during each of her sets, and this has become synonymous with Mums Against Donk's visual identity.
![](https://iilcaa.design/wp-content/uploads/2023/12/TDMovieOut.17-2048x1152.jpg)
![](https://iilcaa.design/wp-content/uploads/2023/12/TDMovieOut.7-1-2048x1152.jpg)
![](https://iilcaa.design/wp-content/uploads/2023/12/TDMovieOut.19.jpg)
![](https://iilcaa.design/wp-content/uploads/2023/12/TDMovieOut.6-1.jpg)
![](https://iilcaa.design/wp-content/uploads/2023/12/TDMovieOut.0-1.jpg)
![](https://iilcaa.design/wp-content/uploads/2023/12/TDMovieOut.18-2048x1152.jpg)
Credits
Visual & Machine Learning Programming
Alicia Wright
Transfer Learning Dataset Content
Alterum @_alterum
INFERNO Visuals Dec 2023
Audio-reactive generative visual set controlled, rendered and delivered in real time using TouchDesigner.
For INFERNO's final event of 2023, I applied creative machine learning, GLSL, 2D textures, deformed 3D meshes and manipulated found footage to create a visual environment that is an abstracted representation of INFERNO's history and community.
The visual set consisted of generative components that respond in real time to a live audio feed from the decks, via the venue's main sound desk. The components were programmed to respond to low frequencies, moving in time to kick drums and heavy bass as a result, with additional custom parameters controlled on the fly using MIDI.
I trained a GAN using over 2,300 images pulled from the INFERNO photo archive's almost 9-year history. The model was trained under StyleGAN 2 ADA at 512px for 550kimg. Latent vector interpolation loops from randomly selected seeds featured heavily throughout the set, and incoming low audio frequencies were used to control their playback.
Also included in the visual set were found video clips of lava flows and volcanic eruptions, digitally manipulated to move in time with the live music, and creatively recoloured.
![](https://iilcaa.design/wp-content/uploads/2023/12/TDMovieOut.2-2048x1152.jpg)
![](https://iilcaa.design/wp-content/uploads/2023/12/TDMovieOut.9-2048x1152.jpg)
![](https://iilcaa.design/wp-content/uploads/2023/12/TDMovieOut.3-2048x1152.jpg)
![](https://iilcaa.design/wp-content/uploads/2023/12/TDMovieOut.5-2048x1152.jpg)
![](https://iilcaa.design/wp-content/uploads/2023/12/TDMovieOut.13.jpg)
![](https://iilcaa.design/wp-content/uploads/2023/12/TDMovieOut.0-2048x1152.jpg)
![](https://iilcaa.design/wp-content/uploads/2023/12/TDMovieOut.4-2048x1152.jpg)
![](https://iilcaa.design/wp-content/uploads/2023/12/TDMovieOut.8-2048x1152.jpg)
Credits
Visual & Machine Learning Programming
Alicia Wright
Dataset Content
INFERNO photo archive courtesy of Lewis G. Burton @lewisgburton
Mums Against Goffs Machine Learning Visuals
Generative live visuals for London's leading donk and happy hardcore club night's crossover event with r u a goff?
In collaboration with photographers El Hogg @999999999boyscrysendpics & Mia Evans @ahgeewiz, I produced a collection of generative live visuals as part of a larger visual set shown in the event's main room.
Using Nvidia StyleGAN2 ADA PyTorch, I trained machine learning models from scratch using datasets of images taken at previous Mums Against Donk events. The variety within the datasets, and the reduced training time allowed me to create highly abstracted motion graphics which interpolate between different latent vectors.
The final datasets consisted of ~280 images each at 256px. El's model was trained for 550kimg and Mia's for 750kimg.
The resulting works are a unique representation of the community cultured by Mums Against Donk’s parties, paying homage to the ever morphing identity of London's queer nightlife.
Credits
Machine Learning Programming
Alicia Wright
Dataset Content
El Hogg @999999999boyscrysendpics
Mia Evans @ahgeewiz
Mums Against Donk 3
Live performance system and real-time generative visuals for the third installment of London's leading donk club night.
Taking influence from scratch video, early VJing and the event's community, I created a live performance system for Mums Against Donk's third event at Corsica Studios.
The system is built using TouchDesigner, utilising additional Python scripting to provide a user interface for control and feedback, alongside external MIDI input and audio-reactive manipulation of the visuals.
![](https://iilcaa.design/wp-content/uploads/2023/08/smiley-1024x1024.png)
![](https://iilcaa.design/wp-content/uploads/2023/08/ket-1024x1024.png)
![](https://iilcaa.design/wp-content/uploads/2023/08/poppers-1024x1024.png)
Mums Against Donk position themselves as a silly, satirical protest against donk music. To allow the visuals to better integrate with the event and their image, I took archival news footage that was critical of 90s warehouse parties and manipulated it to fit a new context, turning it on it's head. This, combined with memes and stock video clips reminiscent of 2000s VJ compilation DVDs helped create a visual experience of Mums Against Donk's spirit and music.
Looping 3D animations of acid smileys, ketamine and poppers are calls to donk and UK rave culture's roots in acid house, and play on the event's social reputation.
The TouchDesigner system takes an audio signal from the club's front of house mixer and analyses it for frequency, allowing different elements of the visuals to react to different frequencies. The threshold and gain of each frequency band can be controlled using physical input from the MIDI controller.
Generative, stock footage, memes and overlay clips are assigned to buttons on the MIDI controller and correspond to the UI displayed on the laptop screen. Each column of clips has controls for playback speed, opacity and post-FX that allow complete control of the visuals throughout the internal processing chain.
![](https://iilcaa.design/wp-content/uploads/2023/08/TDMovieOut.1.jpg)
![](https://iilcaa.design/wp-content/uploads/2023/08/TDMovieOut.5.jpg)
![](https://iilcaa.design/wp-content/uploads/2023/08/TDMovieOut.0.jpg)
![](https://iilcaa.design/wp-content/uploads/2023/08/TDMovieOut.3.jpg)
![](https://iilcaa.design/wp-content/uploads/2023/08/TDMovieOut.2.jpg)
![](https://iilcaa.design/wp-content/uploads/2023/08/TDMovieOut.4.jpg)
Credits
System Programming & Content
Alicia Wright
Event Organiser
Alterum @_alterum
Future Flashback
Generative live visuals and 3D renders for a club night inspired by 2000s nostalgia.
Drawing on my early music experiences, I created a set of generative visuals and 3D renders to channel 2000s pop nostalgia .
I created a setup for performance linking TouchDesigner and Resolume via Syphon, with external MIDI control and external audio input, BPM clock or Ableton Link connection manipulating visuals in real-time.
I took visual cues from 2000s pop music videos I remember from my childhood and responded by creating 3D motion graphics in Blender and audio-reactive generative visuals in TouchDesigner.
I looked at Umbrella by Rihanna’s use of distortion and rippling, Bulletproof by La Roux’s 3D and fractal effect, Can’t Get You Out Of My Head by Kylie Minogue’s computer-generated buildings and Poker Face by Lady Gaga’s tech product placements.
Credits
Visual Programming & 3D
Alicia Wright
Raw Youth Collage Album (Concept)
Album artwork and live visuals sampler for Mura Masa’s second album and tour.
![](https://iilcaa.design/wp-content/uploads/2023/04/lp-front.jpg)
![](https://iilcaa.design/wp-content/uploads/2023/04/cd-album-disc.jpg)
![](https://iilcaa.design/wp-content/uploads/2023/04/cd-singles-disc.jpg)
![](https://iilcaa.design/wp-content/uploads/2023/04/cd-singles-front.jpg)
This conceptual redesign of Mura Masa's second studio album aims to channel the release's title into visual means.
Through generative processes, each track on the album was analysed to generate a unique seed, with which a pattern was created. The LP disc labels are a visual representation of the album's title track, whilst the rest of the album's tracks are part of the inside of the gatefold cover, and feature on the 9-panel folding lyric sheet poster.
![](https://iilcaa.design/wp-content/uploads/2023/04/LP-gatefold2.jpg)
![](https://iilcaa.design/wp-content/uploads/2023/04/LP-gatefold3.jpg)
![](https://iilcaa.design/wp-content/uploads/2023/04/LP-gatefold4.jpg)
![](https://iilcaa.design/wp-content/uploads/2023/04/cd-album-insert.jpg)
![](https://iilcaa.design/wp-content/uploads/2023/04/cd-album-insert2.jpg)
In addition to the artwork, I also produced a sampler of concept live visuals. Key tracks from the RYC tour's setlist were used to produce audio-reactive generative visuals using TouchDesigner. The visuals mainly react to bass and sub frequencies. Alongside the generative content is live-action footage, both manipulated and raw.
Credits
Design & Visual Programming
Alicia Wright
Live-Action Footage Support
Ben Harbour
Emilia Trim
Gustė Novikaite
Isabel Phillips
Maria Peliugaeva
London Design Festival 2022 (Concept)
Generative posters to represent the Kings Cross District of the 2022 London Design Festival.
![](https://iilcaa.design/wp-content/uploads/2022/03/ldf_poster-01.jpg)
![](https://iilcaa.design/wp-content/uploads/2022/03/ldf_poster-02-724x1024.jpg)
Made using Processing, the designs feature archways from King’s Cross Station and Coal Drops Yard and Lewis Cubitt’s structural rivet. The svg output from Processing is further deconstructed using Illustrator, where it is combined with text and further graphic elements.
Credits
Design & Programming
Alicia Wright