Real-time Manipulation Tool for Stable Diffusion

Developed An Expressive Tool for Real-Time Manipulation of Diffusion Models through Network Bending.

This tool introduces a novel approach to real-time manipulation of diffusion models by inte gratng network bending techniques into the 2D Conditional U-Net model within the StreamDiffusion pipeline. Leveraging the flexibility of TouchDesigner, I developed an interactive tool designed for seamless integration into artistic workflows, enabling users to manipulate generative outputs dynamically and expressively.

Unlike traditional text-to-image models, my tool facilitates open ended exploration of the latent space, producing a diverse range of outputs that actively diverge from the training data. Through artistic experimentation, I demonstrate the tool’s ability to generate outputs ranging from subtle enhancements to abstract transformations, unlocking new creative possibilities.

This research provides a foundation for advancing real-time, artist-driven interaction with generative AI models, bridging the gap between technical innovation and creative expression.