Related papers: Taming Consistency Distillation for Accelerated Hu…
Sound content creation, essential for multimedia works such as video games and films, often involves extensive trial-and-error, enabling creators to semantically reflect their artistic ideas and inspirations, which evolve throughout the…
Diffusion models have been verified to be effective in generating complex distributions from natural images to motion trajectories. Recent diffusion-based methods show impressive performance in 3D robotic manipulation tasks, whereas they…
Recent advancements in diffusion models (DMs) have greatly advanced remote sensing image super-resolution (RSISR). However, their iterative sampling processes often result in slow inference speeds, limiting their application in real-time…
Subject-driven image generation aims to synthesize novel depictions of a specific subject across diverse contexts while preserving its core identity features. Achieving both strong identity consistency and high prompt diversity presents a…
Text-to-video diffusion models have advanced video generation significantly. However, customizing these models to generate videos with tailored motions presents a substantial challenge. In specific, they encounter hurdles in (a) accurately…
Modern neural networks are powerful predictive models. However, when it comes to recognizing that they may be wrong about their predictions, they perform poorly. For example, for one of the most common activation functions, the ReLU and its…
The high computational cost and slow inference time are major obstacles to deploying Video Diffusion Models (VDMs). To overcome this, we introduce a new Video Diffusion Model Compression approach using individual content and motion dynamics…
Reasoning segmentation enables open-set object segmentation via implicit text queries, therefore serving as a foundation for embodied agents that should operate autonomously in real-world environments. However, existing methods for…
Recent hybrid video generation models combine autoregressive temporal dynamics with diffusion-based spatial denoising, but their sequential, iterative nature leads to error accumulation and long inference times. In this work, we propose a…
Recent diffusion-based human image animation techniques have demonstrated impressive success in synthesizing videos that faithfully follow a given reference identity and a sequence of desired movement poses. Despite this, there are still…
Current diffusion models for human image animation struggle to ensure identity (ID) consistency. This paper presents StableAnimator, the first end-to-end ID-preserving video diffusion framework, which synthesizes high-quality videos without…
In this paper, we propose the first diffusion-based all-in-one video restoration method that utilizes the power of a pre-trained Stable Diffusion and a fine-tuned ControlNet. Our method can restore various types of video degradation with a…
Recent advancements in human video synthesis have enabled the generation of high-quality videos through the application of stable diffusion models. However, existing methods predominantly concentrate on animating solely the human element…
The iterative sampling procedure employed by diffusion models (DMs) often leads to significant inference latency. To address this, we propose Stochastic Consistency Distillation (SCott) to enable accelerated text-to-image generation, where…
Adapter-based methods are commonly used to enhance model performance with minimal additional complexity, especially in video editing tasks that require frame-to-frame consistency. By inserting small, learnable modules into pretrained…
Diffusion models are proficient at generating high-quality images. They are however effective only when operating at the resolution used during training. Inference at a scaled resolution leads to repetitive patterns and structural…
Diffusion distillation is central to accelerating image and video generation, yet existing methods are fundamentally limited by the denoising process, where step reduction has largely saturated. Partial timestep low-resolution generation…
Diffusion-based Video Super-Resolution (VSR) is renowned for generating perceptually realistic videos, yet it grapples with maintaining detail consistency across frames due to stochastic fluctuations. The traditional approach of pixel-level…
Character Animation aims to generating character videos from still images through driving signals. Currently, diffusion models have become the mainstream in visual generation research, owing to their robust generative capabilities. However,…
Computational imaging methods increasingly rely on powerful generative diffusion models to tackle challenging image restoration tasks. In particular, state-of-the-art zero-shot image inverse solvers leverage distilled text-to-image latent…