相关论文: Tuning-Free Long Video Generation via Global-Local…

Diffusion models have made significant advances in generating high-quality images, but their application to video generation has remained challenging due to the complexity of temporal motion. Zero-shot video editing offers a solution by…

Recent large-scale pre-trained diffusion models have demonstrated a powerful generative ability to produce high-quality videos from detailed text descriptions. However, exerting control over the motion of objects in videos generated by any…

Leveraging pre-trained conditional diffusion models for video editing without further tuning has gained increasing attention due to its promise in film production, advertising, etc. Yet, seminal works in this line fall short in generation…

Latent diffusion models (LDMs) dominate high-quality image generation, yet integrating representation learning with generative modeling remains a challenge. We introduce a novel generative image modeling framework that seamlessly bridges…

We present an efficient text-to-video generation framework based on latent diffusion models, termed MagicVideo. MagicVideo can generate smooth video clips that are concordant with the given text descriptions. Due to a novel and efficient 3D…

Temporally consistent video-to-video generation is critical for applications such as style transfer and upsampling. In this paper, we provide a theoretical analysis of warped noise - a recently proposed technique for training video…

Text-driven diffusion models have unlocked unprecedented abilities in image generation, whereas their video counterpart still lags behind due to the excessive training cost of temporal modeling. Besides the training burden, the generated…

Diffusion-based video editing has emerged as an important paradigm for high-quality and flexible content generation. However, despite their generality and strong modeling capacity, Diffusion Transformers (DiT) remain computationally…

In recent years, data-driven techniques have greatly advanced autonomous driving systems, but the need for rare and diverse training data remains a challenge, requiring significant investment in equipment and labor. World models, which…

Diffusion-based generative models have exhibited powerful generative performance in recent years. However, as many attributes exist in the data distribution and owing to several limitations of sharing the model parameters across all levels…

Flow matching and diffusion models have shown impressive results in text-to-image generation, producing photorealistic images through an iterative denoising process. A common strategy to speed up synthesis is to perform early denoising at…

We propose Latent-Shift -- an efficient text-to-video generation method based on a pretrained text-to-image generation model that consists of an autoencoder and a U-Net diffusion model. Learning a video diffusion model in the latent space…

Latent Consistency Models (LCMs) have achieved impressive performance in accelerating text-to-image generative tasks, producing high-quality images with minimal inference steps. LCMs are distilled from pre-trained latent diffusion models…

Deep denoising models require extensive real-world training data, which is challenging to acquire. Current noise synthesis techniques struggle to accurately model complex noise distributions. We propose a novel Realistic Noise Synthesis…

This work addresses the challenge of streamed video depth estimation, which expects not only per-frame accuracy but, more importantly, cross-frame consistency. We argue that sharing contextual information between frames or clips is pivotal…

We introduce Lumiere -- a text-to-video diffusion model designed for synthesizing videos that portray realistic, diverse and coherent motion -- a pivotal challenge in video synthesis. To this end, we introduce a Space-Time U-Net…

Sounding Video Generation (SVG) is an audio-video joint generation task challenged by high-dimensional signal spaces, distinct data formats, and different patterns of content information. To address these issues, we introduce a novel…

Recent video generative models have demonstrated impressive visual fidelity, yet they often struggle with semantic, geometric, and identity consistency. In this paper, we propose a system-level framework, termed the Divide-and-Conquer…

High-resolution video generation, while crucial for digital media and film, is computationally bottlenecked by the quadratic complexity of diffusion models, making practical inference infeasible. To address this, we introduce HiStream, an…

Although diffusion-based models can generate high-quality and high-resolution video sequences from textual or image inputs, they lack explicit integration of geometric cues when controlling scene lighting and visual appearance across…