AV-Labor

Diesmal: AI Model Building with LoRAs & Local LLMs mit Portrait XO

*WORKSHOP in ENGLISH!*
In this hands-on workshop, participants will learn how to run AI models using local large language models (LLMs) and Low-Rank Adaptation (LoRAs: a lightweight, accessible method for customizing AI behavior without the massive computational costs of training from scratch). Participants will begin by setting up a local LLM — a fully functional AI model running directly on their own machine — giving agency and privacy of local data usage. From there, participants will learn how to fine-tune that model using LoRAs: a lightweight, accessible method for customizing AI behavior without massive computational costs. We’ll walk through the full pipeline — curating ethically sourced training data with clear provenance and consent, preparing datasets, configuring LoRA parameters, running a fine-tune, and evaluating the results.
The workshop will engage with deeper questions this work demands: What does it mean to own your AI infrastructure? How can small-scale model building become an act of creative sovereignty? How does running locally shift the power dynamics of who gets to shape AI — and who gets shaped by it? We’ll approach model training as a practice rooted in consent, data provenance, and intentionality — asking not just how to train a model, but what we feed it and why.
No prior machine learning experience is required. Bring a laptop and a willingness to get into critical engagement with generative AI.

Alle Infos zum AV-LABOR: zimmt.net/av-labor-2026

AV-Labor

Diesmal: Sounddesign in 3D mit Max/MSP mit Martin Recker

Max/MSP ist eine visuelle Programmiersprache, mit der sich alle Grenzen sprengen lassen, die ihr vielleicht aus anderen Audioprogrammen kennt. Eure Klangutopien und musikalischen Experimente können hier Wirklichkeit werden. Durch den modularen und intuitiven Aufbau ermöglicht Max/MSP euch, selbst zu Programmierer*innen eurer Ideen zu werden und in kürzester Zeit funktionierende Prototypen zu erstellen.
In diesem Labor bekommt ihr – auch ohne Vorkenntnisse – einen schnellen Einstieg in die Arbeit mit Max/MSP. Gemeinsam entwickeln und experimentieren wir mit kreativen und klanglichen Möglichkeiten, die das 32-Kanal-Lautsprechersystem des ZiMMT bietet. Der Schwerpunkt liegt auf experimentellem Sounddesign im Raum.
Keine Vorkenntnisse nötig.
Bitte bringt – falls vorhanden – einen Laptop mit installierter Max/MSP-Demoversion sowie Kopfhörer mit

Alle Infos zum AV-LABOR: zimmt.net/av-labor-2026

AV-Labor

Diesmal: 2D Digital Animation mit Paula Ábalos (Workshop in english)

This workshop offers a first introduction to animation principles. Exploring the basics of digital 2D animation using drawing tools on a computer. It introduces core animation principles through a digital workflow.

Paula Ábalos is a visual artist based in Leipzig, Germany. After completing her studies in Visual Arts (major in painting) at Universidad Finis Terrae in Santiago, she pursued the Meisterschüler program in Media Arts at the Academy of Visual Arts Leipzig (HGB), under the supervision of Clemens von Wedemeyer.

Her practice unfolds primarily in the field of experimental video, in dialogue with other media such as animation, sound, photography, performance, drawing, and artist books. Through these forms, she merges documentary, fictional, and poetic elements to construct immersive narratives. Ábalos’ research explores the impact of labor on individuals, as well as liminal states between wakefulness and sleep. She is particularly interested in the relationship between work and sleep, and in the ways these concepts intersect and resonate today.

Alle Infos zum AV-LABOR: zimmt.net/av-labor-2026