Diffusion-based generative models struggle to maintain high style consistency across generated images via text description. Although several style-aligned image generation methods have been proposed to address this issue, they exhibit suboptimal performance and are primarily built upon the U-Net architecture, limiting their compatibility with DiT diffusion models like Flux that has emerged as a predominant model in the field of image generation. To address these limitations, we propose AlignedGen, a novel training-free style-aligned image generation method for DiT models to significantly enhance style consistency across generated images. Specifically, AlignedGen incorporates two key components to achieve this: Shifted Position Embedding (ShiftPE) and Advanced Attention Sharing (AAS). ShiftPE alleviates the text controllability degradation observed in prior methods when applied to DiT models through its non-overlapping position indices design, while AAS comprises three specialized techniques to unleash the full potential of DiT for style-aligned generation. Furthermore, to broaden the applicability of our method, we present an efficient query, key, and value feature extraction algorithm, enabling our method to seamlessly incorporate external images as style references. Extensive experimental results validate that our method effectively enhances style consistency across generated images while maintaining favorable text controllability.

We present The Matrix, the first foundational realistic world simulator capable of generating continuous 720p high-fidelity real-scene video streams with real-time, responsive control in both first- and third-person perspectives, enabling immersive exploration of richly dynamic environments. Trained on limited supervised data from AAA games like Forza Horizon 5 and Cyberpunk 2077, complemented by large-scale unsupervised footage from real-world settings like Tokyo streets, The Matrix allows users to traverse diverse terrains -- deserts, grasslands, water bodies, and urban landscapes -- in continuous, uncut hour-long sequences. Operating at 16 FPS, the system supports real-time interactivity and demonstrates zero-shot generalization, translating virtual game environments to real-world contexts where collecting continuous movement data is often infeasible. For example, The Matrix can simulate a BMW X3 driving through an office setting--an environment present in neither gaming data nor real-world sources. This approach showcases the potential of AAA game data to advance robust world models, bridging the gap between simulations and real-world applications in scenarios with limited data.

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 latency, impacting real-time performance adversely. While prior research has highlighted the presence of high similarity in activation values between adjacent diffusion steps (referred to as redundancy) and proposed various caching mechanisms to mitigate computational overhead, the exploration of redundancy in existing literature remains limited, with findings often not generalizable across different DiT models. This study aims to address this gap by conducting a comprehensive investigation into redundancy across a broad spectrum of mainstream DiT models. Our experimental analysis reveals substantial variations in the distribution of redundancy across diffusion steps among different DiT models. Interestingly, within a single model, the redundancy distribution remains stable regardless of variations in input prompts, step counts, or scheduling strategies. Given the lack of a consistent pattern across diverse models, caching strategies designed for a specific group of models may not easily transfer to others. To overcome this challenge, we introduce a tool for analyzing the redundancy of individual models, enabling subsequent research to develop tailored caching strategies for specific model architectures. The project is publicly available at https://github.com/xdit-project/DiTCacheAnalysis.

In this paper, we argue that iterative computation with diffusion models offers a powerful paradigm for not only generation but also visual perception tasks. We unify tasks such as depth estimation, optical flow, and amodal segmentation under the framework of image-to-image translation, and show how diffusion models benefit from scaling training and test-time compute for these perceptual tasks. Through a careful analysis of these scaling properties, we formulate computeoptimal training and inference recipes to scale diffusion models for visual perception tasks. Our models achieve competitive performance to state-of-the-art methods using significantly less data and compute. Diffusion models have emerged as powerful techniques for generating images and videos, while showing excellent scaling behaviors. In this paper, we present a unified framework to perform a variety of perceptual tasks -- depth estimation, optical flow estimation, and amodal segmentation -- with a single diffusion model, as illustrated in Figure 1. Previous works such as Marigold (Ke et al., 2024), FlowDiffuser (Luo et al., 2024), and pix2gestalt (Ozguroglu et al., 2024) demonstrate the potential of repurposing image diffusion models for various inverse vision tasks individually.

The discovery of new materials is very important to the field of materials science. When researchers explore new materials, they often have expected performance requirements for their crystal structure. In recent years, data-driven methods have made great progress in the direction plane of crystal structure generation, but there is still a lack of methods that can effectively map material properties to crystal structure. In this paper, we propose a Crystal DiT model to generate the crystal structure from the expected material properties by embedding the material properties and combining the symmetry information predicted by the large language model. Experimental verification shows that our proposed method has good performance.

This paper presents EasyAnimate, an advanced method for video generation that leverages the power of transformer architecture for high-performance outcomes. We have expanded the DiT framework originally designed for 2D image synthesis to accommodate the complexities of 3D video generation by incorporating a motion module block. It is used to capture temporal dynamics, thereby ensuring the production of consistent frames and seamless motion transitions. The motion module can be adapted to various DiT baseline methods to generate video with different styles. It can also generate videos with different frame rates and resolutions during both training and inference phases, suitable for both images and videos. Moreover, we introduce slice VAE, a novel approach to condense the temporal axis, facilitating the generation of long duration videos. Currently, EasyAnimate exhibits the proficiency to generate videos with 144 frames. We provide a holistic ecosystem for video production based on DiT, encompassing aspects such as data pre-processing, VAE training, DiT models training (both the baseline model and LoRA model), and end-to-end video inference. Code is available at: https://github.com/aigc-apps/EasyAnimate. We are continuously working to enhance the performance of our method.

Recent developments in large-scale pre-trained text-to-image diffusion models have significantly improved the generation of high-fidelity images, particularly with the emergence of diffusion models based on transformer architecture (DiTs). Among these diffusion models, diffusion transformers have demonstrated superior image generation capabilities, boosting lower FID scores and higher scalability. However, deploying large-scale DiT models can be expensive due to their extensive parameter numbers. Although existing research has explored efficient deployment techniques for diffusion models such as model quantization, there is still little work concerning DiT-based models. To tackle this research gap, in this paper, we propose TerDiT, a quantization-aware training (QAT) and efficient deployment scheme for ternary diffusion models with transformers. We focus on the ternarization of DiT networks and scale model sizes from 600M to 4.2B. Our work contributes to the exploration of efficient deployment strategies for large-scale DiT models, demonstrating the feasibility of training extremely low-bit diffusion transformer models from scratch while maintaining competitive image generation capacities compared to full-precision models. Code will be available at https://github.

We explore a new class of diffusion models based on the Machine learning is experiencing a renaissance powered transformer architecture. We train latent diffusion models by transformers. Over the past five years, neural architectures of images, replacing the commonly-used U-Net backbone for natural language processing [8, 42], vision [10] with a transformer that operates on latent patches. We analyze and several other domains have largely been subsumed by the scalability of our Diffusion Transformers (DiTs) transformers [60]. Many classes of image-level generative through the lens of forward pass complexity as measured by models remain holdouts to the trend, though--while Gflops. We find that DiTs with higher Gflops--through increased transformers see widespread use in autoregressive models transformer depth/width or increased number of input [3,6,43,47], they have seen less adoption in other generative tokens--consistently have lower FID.