We present a method to create interpretable concept sliders that enable precise control over
attributes in image generations from diffusion models. Our approach identifies a low-rank …

Diffusion-based models have gained significant popularity for text-to-image generation due
to their exceptional image-generation capabilities. A risk with these models is the potential …

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

Diffusion models represent a new paradigm in text-to-image generation. Beyond generating
high-quality images from text prompts models such as Stable Diffusion have been …

Generative models have been very popular in the recent years for their image generation
capabilities. GAN-based models are highly regarded for their disentangled latent space …

Recently, diffusion models have emerged as a powerful class of generative models. Despite
their success, there is still limited understanding of their semantic spaces. This makes it …

Sparse autoencoders (SAEs) have become a core ingredient in the reverse engineering of
large-language models (LLMs). For LLMs, they have been shown to decompose …

Text-to-image diffusion models have made significant progress in generating naturalistic
images from textual inputs, and demonstrate the capacity to learn and represent complex …

Despite increasing progress in development of methods for generating visual counterfactual
explanations, previous works consider them as an entirely local technique. In this work, we …

We present a method to create diffusion-based video models from pretrained Text-to-Image
(T2I) models. Recently, AnimateDiff proposed freezing the T2I model while only training …