Image inpainting, the process of restoring corrupted images, has seen significant
advancements with the advent of diffusion models (DMs). Despite these advancements …

Recent studies have demonstrated that diffusion models can generate high-quality samples,
but their quality heavily depends on sampling guidance techniques, such as classifier …

One of the key shortcomings in current text-to-image (T2I) models is their inability to
consistently generate images which faithfully follow the spatial relationships specified in the …

Text-to-image generation (TTI) refers to the usage of models that could process text input
and generate high fidelity images based on text descriptions. Text-to-image generation …

We present Deep Compression Autoencoder (DC-AE), a new family of autoencoder models
for accelerating high-resolution diffusion models. Existing autoencoder models have …

We introduce DiffH2O, a new diffusion-based framework for synthesizing realistic, dexterous
hand-object interactions from natural language. Our model employs a temporal two-stage …

Is the Text to Motion model robust? Recent advancements in Text to Motion models primarily
stem from more accurate predictions of specific actions. However, the text modality typically …

Generating images from text has become easier because of the scaling of diffusion models
and advancements in the field of vision and language. These models are trained using vast …

Recent advancements in multimodal models highlight the value of rewritten captions for
improving performance, yet key challenges remain. For example, while synthetic captions …

We study the scaling properties of latent diffusion models (LDMs) with an emphasis on their
sampling efficiency. While improved network architecture and inference algorithms have …