The rapid advancement of visual generative models necessitates efficient and reliable
evaluation methods. Arena platform, which gathers user votes on model comparisons, can …

By increasing model parameters but activating them sparsely when performing a task, the
use of Mixture-of-Experts (MoE) architecture significantly improves the performance of Large …

The increased model capacity of Diffusion Transformers (DiTs) and the demand for
generating higher resolutions of images and videos have led to a significant rise in inference …

Diffusion Transformers have emerged as the preeminent models for a wide array of
generative tasks, demonstrating superior performance and efficacy across various …

Diffusion Transformers have demonstrated remarkable capabilities in image generation but
often come with excessive parameterization, resulting in considerable inference overhead in …

Diffusion Transformers have recently demonstrated unprecedented generative capabilities
for various tasks. The encouraging results, however, come with the cost of slow inference …

Diffusion models have achieved impressive advancements in various vision tasks. However,
these gains often rely on increasing model size, which escalates computational complexity …

Existing text-to-image (T2I) diffusion models face several limitations, including large model
sizes, slow runtime, and low-quality generation on mobile devices. This paper aims to …

We introduce DiffusionTrend for virtual fashion try-on, which forgoes the need for retraining
diffusion models. Using advanced diffusion models, DiffusionTrend harnesses latent …

As text-to-image models grow increasingly powerful and complex, their burgeoning size
presents a significant obstacle to widespread adoption, especially on resource-constrained …