Exact Diffusion Inversion via Bi-directional Integration Approximation. (arXiv:2307.10829v5 [cs.CV] UPDATED)

Recently, various methods have been proposed to address the inconsistency
issue of DDIM inversion to enable image editing, such as EDICT [36] and
Null-text inversion [22]. However, the above methods introduce considerable
computational overhead. In this paper, we propose a new technique, named
\emph{bi-directional integration approximation} (BDIA), to perform exact
diffusion inversion with neglible computational overhead. Suppose we would like
to estimate the next diffusion state $\boldsymbol{z}_{i-1}$ at timestep $t_i$
with the historical information $(i,\boldsymbol{z}_i)$ and
$(i+1,\boldsymbol{z}_{i+1})$. We first obtain …

approximation arxiv computational diffusion editing image integration issue null paper text