AI RESEARCH

Exploring Low-Dimensional Subspaces in Diffusion Models for Controllable Image Editing

arXiv CS.LG

ArXi:2409.02374v3 Announce Type: replace-cross Recently, diffusion models have emerged as a powerful class of generative models. Despite their success, there is still limited understanding of their semantic spaces. This makes it challenging to achieve precise and disentangled image generation without additional