Related papers: LightCache: Memory-Efficient, Training-Free Accele…

Text-to-video diffusion models deliver impressive results but remain slow because of the sequential denoising of 3D latents. Existing approaches to speed up inference either require expensive model retraining or use heuristic-based step…

Generative models, particularly diffusion models, have made significant success in data synthesis across various modalities, including images, videos, and 3D assets. However, current diffusion models are computationally intensive, often…

Diffusion transformer-based video generation models (DiTs) have recently attracted widespread attention for their excellent generation quality. However, their computational cost remains a major bottleneck-attention alone accounts for over…

We introduce TurboDiffusion, a video generation acceleration framework that can speed up end-to-end diffusion generation by 100-200x while maintaining video quality. TurboDiffusion mainly relies on several components for acceleration: (1)…

Diffusion models deliver high-fidelity synthesis but remain slow due to iterative sampling. We empirically observe there exists feature invariance in deterministic sampling, and present InvarDiff, a training-free acceleration method that…

Diffusion models have emerged as state-of-the-art in image generation, but their practical deployment is hindered by the significant computational cost of their iterative denoising process. While existing caching techniques can accelerate…

Based on recent advanced diffusion models, Text-to-image (T2I) generation models have demonstrated their capabilities to generate diverse and high-quality images. However, leveraging their potential for real-world content creation,…

We propose Latte, a novel Latent Diffusion Transformer for video generation. Latte first extracts spatio-temporal tokens from input videos and then adopts a series of Transformer blocks to model video distribution in the latent space. In…

Diffusion-based image generation models excel at producing high-quality synthetic content, but suffer from slow and computationally expensive inference. Prior work has attempted to mitigate this by caching and reusing features within…

Diffusion models are a powerful generative framework, but come with expensive inference. Existing acceleration methods often compromise image quality or fail under complex conditioning when operating in an extremely low-step regime. In this…

Diffusion models are emerging expressive generative models, in which a large number of time steps (inference steps) are required for a single image generation. To accelerate such tedious process, reducing steps uniformly is considered as an…

Diffusion Transformers (DiTs) excel at visual generation yet remain hampered by slow sampling. Existing training-free accelerators - step reduction, feature caching, and sparse attention - enhance inference speed but typically rely on a…

Autoregressive video diffusion models support real-time synthesis but suffer from error accumulation and context loss over long horizons. We discover that attention heads in AR video diffusion transformers serve functionally distinct roles…

Flow Matching models achieve state-of-the-art image generation quality but incur substantial inference cost due to iterative denoising through large Transformer networks. We observe that different layer groups within a Transformer exhibit…

Diffusion models achieve remarkable generative quality, but computational overhead scales with step count, model depth, and sequence length. Feature caching is effective since adjacent timesteps yield highly similar features. However, an…

Diffusion models have revolutionized high-fidelity image and video synthesis, yet their computational demands remain prohibitive for real-time applications. These models face two fundamental challenges: strict temporal dependencies…

Recent diffusion models enable high-quality video generation, but suffer from slow runtimes. The large transformer-based backbones used in these models are bottlenecked by spatiotemporal attention. In this paper, we identify that a…

Latent diffusion models have enabled high-quality video synthesis, yet their inference remains costly and time-consuming. As diffusion transformers become increasingly efficient, the latency bottleneck inevitably shifts to VAE decoders. To…

Though diffusion-based video generation has witnessed rapid progress, the inference results of existing models still exhibit unsatisfactory temporal consistency and unnatural dynamics. In this paper, we delve deep into the noise…

Long video generation remains a challenging and compelling topic in computer vision. Diffusion based models, among the various approaches to video generation, have achieved state of the art quality with their iterative denoising procedures.…