Diffusion Models already have a Semantic Latent Space

Understand

Diffusion models achieve outstanding generative performance in various domains.

• Despite their great success, they lack semantic latent space which is essential for controlling the generative process.
• To address the problem, we propose asymmetric reverse process (Asyrp) which discovers the semantic latent space in frozen pretrained diffusion models.
• Our semantic latent space, named h-space, has nice properties for accommodating semantic image manipulation: homogeneity, linearity, robustness, and consistency across timesteps.