Filtered to diffusion transformers · clear filter
This paper helps us understand how text-to-image diffusion transformers work by analyzing the role of "template tokens" in generating images from text prompts. Practitioners might care because it shows how to improve the efficiency of these models without sacrificing their performance.
This paper develops a system called AlayaWorld that can generate interactive virtual worlds from text, images, or videos, allowing for customizable and evolving environments. Practitioners in areas like game development, virtual reality, or interactive storytelling might care about this research for its potential to streamline the creation of immersive experiences.
This paper improves the efficiency of video generation by reducing the computational load of attention, a key bottleneck in diffusion transformers. Practitioners can benefit from the speedup achieved by Sol-Attn, which enables faster video generation and editing without compromising visual quality.
This paper develops a method to transform video foundation models' representations into compact, reconstruction-capable, and generation-friendly video latents, which can be used in various generative modeling tasks. Practitioners can use VideoRAE to improve the performance of their models by leveraging the semantic and spatio-temporal structure captured by the frozen video foundation encoder.