Exploring Diffusion Transformer Designs via Grafting
image-generation self-attention convolutions diffusion-models grafting linear-attention text-to-image-generation architecture-research diffusion-transformer sub-quadratic-attention model-grafting hyena-operator model-architecture-editing diffusion-transformers architecture-editing hyena-x hyena-y mamba-2
-
Updated
Jun 18, 2025 - Jupyter Notebook