Our project page is at: https://yulu.net.cn/freelong .

We address these challenges by investigating the primary contributors to error accumulation in DDIM inversion and identify the singularity problem in traditional noise schedules as a key issue.

In this work, we present MuDI, a novel framework that enables multi-subject personalization by effectively decoupling identities from multiple subjects.

For example, to study the causal relations between the drugs and diseases, one can conduct clinical tests via selectively administering the medicines to the patients.

However, current methods for evaluating such models remain incomplete: standard likelihood-based metrics do not always apply and rarely correlate with perceptual fidelity, while sample-based metrics, such as FID, are insensitive to overfitting, i.e., inability to generalize beyond the training set.