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