Nick Stacke

I'm a PhD student in the CompVis group advised by Björn Ommer (LMU). My research focuses on efficient methods to control and alter diffusion T2I models. This includes extending them to perform efficient video generation as well finding disentangled representations for more fine-grained control.

News 🔥

Research

CTRLorALTer: Conditional LoRAdapter for Efficient 0-Shot Control & Altering of T2I Models

Nick Stracke, Stefan A Baumann, Joshua M Susskind, Miguel A Bautista, Björn Ommer

ECCV 2024

Project Page / arXiv / Code

LoRAs don't have to be static! They can also introduce new conditioning into foundation models more efficiently and effectively than previous methods.

Continuous, Subject-Specific Attribute Control in T2I Models by Identifying Semantic Directions

Stefan Andreas Baumann, Felix Krause, Michael Neumayr, Nick Stracke, Vincent Tao Hu, Björn Ommer

Preprint 2024

Project Page / arXiv / Code / Colab / Twitter

T2I diffusion models alredy knew how to do fine-grained control, we just had to learn out how to leverage this capability.

Boosting Latent Diffusion with Flow Matching

Johannes Fischer*, Ming Gui*, Pingchuan Ma*, Nick Stracke, Stefan Andreas Baumann, Björn Ommer

ECCV 2024

Project Page / arXiv / Code

Making high-resolution T2I diffusion fast and increasing resolutions to multiple megapixels by adding flow matching-based superresolution stages in latent space.