Diffuse-XL

<!-- SC_OFF --><div class="md"><p>I'm proposing a way to handle massive context longer than a model's context window by

Limited-angle digital breast tomosynthesis (DBT) reconstructs a volume from a few low-dose projections over a narrow arc

We study why diffusion autoencoders can achieve similar image quality while learning substantially different latent stru

Video face restoration (VFR) aims to recover high-quality and temporally consistent facial details from severely degrade

Conditional diffusion models can generate anatomically plausible medical ultrasound (US) images, but anatomical plausibi

Text-to-image (T2I) diffusion models often fail to faithfully render explicit textual descriptions, instead defaulting t

Training-free concept erasure is an attractive mechanism for controlling text-to-image diffusion models, but precise era

Reconstructing high-fidelity, relightable 3D avatars from a single in-the-wild image is a challenging ill-posed problem,

State-of-the-art single-image 3D reconstruction methods often rely on complex hybrid architectures and loss functions, o

A tiny, readable diffusion language model.

A general fine-tuning kit geared toward image/video/audio diffusion models.

The forward and reverse process, with runnable code.