9 papers
Improved Distributional Diffusion Models
Tommaso Martorella, Alexandre Galashov, Felix Krause +4
Distributional Diffusion Models (DDMs) replace the standard mean-prediction denoiser with a \emph{distributional} denoiser trained via a scoring rule objective, learning a stochast…
Logit Refiner: Improving Visual Autoregressive Models via Intra-Scale Dependency Modeling
Meimingwei Li, Stefan Andreas Baumann, Felix Krause +1
Visual Autoregressive Models (VAR) generate images through next-scale prediction, producing all tokens within each scale in parallel. We show that this parallel decoding constitute…
Concept Guidance: Precise, Training-Free Latent Control for Text-to-Image Generation
Nikolai Röhrich, Isabell Hans, Felix Krause +1
Text-to-image diffusion models have two major drawbacks that severely limit their practical utility: (1) standard models lack an intrinsic mechanism for continuous, concept-specifi…
Denoising, Fast and Slow: Difficulty-Aware Adaptive Sampling for Image Generation
Johannes Schusterbauer, Ming Gui, Yusong Li +3
Diffusion- and flow-based models usually allocate compute uniformly across space, updating all patches with the same timestep and number of function evaluations. While convenient,…
DisMo: Disentangled Motion Representations for Open-World Motion Transfer
Thomas Ressler-Antal, Frank Fundel, Malek Ben Alaya +4
Recent advances in text-to-video (T2V) and image-to-video (I2V) models, have enabled the creation of visually compelling and dynamic videos from simple textual descriptions or init…
Adapting Self-Supervised Representations as a Latent Space for Efficient Generation
Ming Gui, Johannes Schusterbauer, Timy Phan +4
We introduce Representation Tokenizer (RepTok), a generative modeling framework that represents an image using a single continuous latent token obtained from self-supervised vision…
SCFlow: Implicitly Learning Style and Content Disentanglement with Flow Models
Pingchuan Ma, Xiaopei Yang, Yusong Li +4
Explicitly disentangling style and content in vision models remains challenging due to their semantic overlap and the subjectivity of human perception. Existing methods propose sep…
TREAD: Token Routing for Efficient Architecture-agnostic Diffusion Training
Felix Krause, Timy Phan, Ming Gui +3
Diffusion models have emerged as the mainstream approach for visual generation. However, these models typically suffer from sample inefficiency and high training costs. Consequentl…
Continuous, Subject-Specific Attribute Control in T2I Models by Identifying Semantic Directions
Stefan Andreas Baumann, Felix Krause, Michael Neumayr +4
Recent advances in text-to-image (T2I) diffusion models have significantly improved the quality of generated images. However, providing efficient control over individual subjects,…