Creative work with generative image models is typically mediated through prompts, often requiring designers to translate visual and material intentions into words. Such translation can have a constraining effect on creative tasks in visual domains such as fashion and textile design. To understand how designers make sense of the material of AI based on its interpretable properties, we let users interact with the technology by manipulating the neurons that lie in its hidden layers. In two material-driven design workshops, we introduced fashion and textile practitioners to the technical material properties of a model trained to generate fashion imagery. We found that the interaction leads to new forms of material experiences by offering a gateway into AI’s otherwise implicit functioning and discuss the how thinking hidden layers might support intuitive rather than interpretative control when designing with AI, leading to more active material experiences.

As AI and data systems often falter when encountering queer identities and knowledge, reinforcing existing oppressions, queer people have resisted such systems and their normalizing tendencies. This pictorial explores tactics of queering AI through a collaborative zine-making project (i.e. zineography) that challenges generative AI and data systems. We share how we workshopped and materialized queering tactics in zine spreads; analyzed these spreads according to materials, content, and tone; and visualized our analysis as thematic collages. We contribute: (1) tangible characteristics of queering AI and data systems (i.e. materials, tones, and aesthetics); and (2) design opportunities for using zineographies as a radical method for building and collectively sharing knowledge about a marginalized community, including recommendations for enacting queer zineographies. By materializing queering tactics through zine-making, we invite embodied, action-oriented critiques that question dominant techno-solutionist movements and trace queer possibilities outside of their normalizing narratives.

Today's AI models learn rich internal representations, such as the visual features inside diffusion models that produce generated images, and offer a new kind of material for co-creation. However, interfaces for creating with generative AI typically operate on the level of inputs and outputs, obscuring the material formation that unfolds in between. To address this gap, this pictorial documents a material-driven journey of designing an interface for interacting with the hidden layers of diffusion models.

This pictorial describes the process of developing an interaction technique for directly engaging with the hidden layers of a generative AI model for image synthesis. First, we give some background to generative AI in HCI, arguing that current interaction techniques prevent us from directly interacting with the material of AI, foreclosing its use in design. Drawing on inspiration from the Computer Science field of feature visualization, we investigate the materiality of our prototype, a GAN model trained to generate fashion imagery, and show how Hidden Layer Interaction offers an alternative to standard prompting. In doing so, we illustrate how this change in approach leads to new forms of interaction with the internal semantics of generative AI, and demonstrate how one might use Hidden Layer Interaction to engage with AI as a material in design.