Diffusion Transformers (DiTs) dominate video generation but their high computational cost
severely limits real-world applicability, usually requiring tens of minutes to generate a few …

Latent diffusion models with Transformer architectures excel at generating high-fidelity
images. However, recent studies reveal an optimization dilemma in this two-stage design …

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 …

This paper presents SANA-1.5, a linear Diffusion Transformer for efficient scaling in text-to-
image generation. Building upon SANA-1.0, we introduce three key innovations:(1) Efficient …

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

In commonly used sub-quadratic complexity modules, linear attention benefits from
simplicity and high parallelism, making it promising for image synthesis tasks. However, the …

Latent diffusion models have emerged as the leading approach for generating high-quality
images and videos, utilizing compressed latent representations to reduce the computational …

We have witnessed the unprecedented success of diffusion-based video generation over
the past year. Recently proposed models from the community have wielded the power to …

Text serves as the key control signal in video generation due to its narrative nature. To
render text descriptions into video clips, current video diffusion models borrow features from …

In this technical report, we present Magic 1-For-1 (Magic141), an efficient video generation
model with optimized memory consumption and inference latency. The key idea is simple …