Related papers: Foresight: Adaptive Layer Reuse for Accelerated an…
Contemporary diffusion models built upon U-Net or Diffusion Transformer (DiT) architectures have revolutionized image generation through transformer-based attention mechanisms. The prevailing paradigm has commonly employed self-attention…
Diffusion Models have become a cornerstone of modern generative AI for their exceptional generation quality and controllability. However, their inherent \textit{multi-step iterations} and \textit{complex backbone networks} lead to…
Diffusion models have emerged as a powerful class of generative models across various modalities, including image, video, and audio synthesis. However, their deployment is often limited by significant inference latency, primarily due to the…
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 models are widely recognized for generating high-quality and diverse images, but their poor real-time performance has led to numerous acceleration works, primarily focusing on UNet-based structures. With the more successful…
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)…
Video generation has drawn significant interest recently, pushing the development of large-scale models capable of producing realistic videos with coherent motion. Due to memory constraints, these models typically generate short video…
Diffusion Transformers (DiTs) deliver state-of-the-art generative performance but their quadratic training cost with sequence length makes large-scale pretraining prohibitively expensive. Token dropping can reduce training cost, yet na\"ive…
Auto-regressive Large Language Models (LLMs) demonstrate remarkable performance across different domains such as vision and language processing. However, due to sequential processing through a stack of transformer layers, autoregressive…
Diffusion models achieve state-of-the-art video generation quality, but their inference remains expensive due to the large number of sequential denoising steps. This has motivated a growing line of research on accelerating diffusion…
Diffusion Transformers (DiTs) are a dominant backbone for high-fidelity text-to-image generation due to strong scalability and alignment at high resolutions. However, quadratic self-attention over dense spatial tokens leads to high…
While diffusion models have achieved great success in the field of video generation, this progress is accompanied by a rapidly escalating computational burden. Among the existing acceleration methods, Feature Caching is popular due to its…
In this paper, we propose an efficient, fast, and versatile distillation method to accelerate the generation of pre-trained diffusion models: Flash Diffusion. The method reaches state-of-the-art performances in terms of FID and CLIP-Score…
While generative modeling on time series facilitates more capable and flexible probabilistic forecasting, existing generative time series models do not address the multi-dimensional properties of time series data well. The prevalent…
The generative priors of pre-trained latent diffusion models (DMs) have demonstrated great potential to enhance the visual quality of image super-resolution (SR) results. However, the noise sampling process in DMs introduces randomness in…
Diffusion Transformers (DiT) have emerged as powerful generative models for various tasks, including image, video, and speech synthesis. However, their inference process remains computationally expensive due to the repeated evaluation of…
Diffusion models have recently revolutionized the field of image synthesis due to their ability to generate photorealistic images. However, one of the major drawbacks of diffusion models is that the image generation process is costly. A…
Video object removal and inpainting are critical tasks in the fields of computer vision and multimedia processing, aimed at restoring missing or corrupted regions in video sequences. Traditional methods predominantly rely on flow-based…
We present Dual3D, a novel text-to-3D generation framework that generates high-quality 3D assets from texts in only $1$ minute.The key component is a dual-mode multi-view latent diffusion model. Given the noisy multi-view latents, the 2D…
Video generation models have demonstrated remarkable performance, yet their broader adoption remains constrained by slow inference speeds and substantial computational costs, primarily due to the iterative nature of the denoising process.…