Related papers: Adaptive Video Distillation: Mitigating Oversatura…
The inference latency of diffusion models remains a critical barrier to their real-time application. While trajectory-based and distribution-based step distillation methods offer solutions, they present a fundamental trade-off.…
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…
Text-to-3D generation has shown rapid progress in recent days with the advent of score distillation, a methodology of using pretrained text-to-2D diffusion models to optimize neural radiance field (NeRF) in the zero-shot setting. However,…
Modern video generative models based on diffusion models can produce very realistic clips, but they are computationally inefficient, often requiring minutes of GPU time for just a few seconds of video. This inefficiency poses a critical…
Distribution matching distillation (DMD) facilitates few-step image generation by aligning a distilled student with a reference multi-step teacher. In practice, however, optimizing DMD can reduce sample diversity in few-step synthesis, and…
Diffusion models (DMs) produce high-quality images, yet their sampling remains costly when adapted to new domains. Distilled DMs are faster but typically remain confined within their teacher's domain. Thus, fast and high-quality generation…
Distribution Matching Distillation (DMD) is a powerful acceleration paradigm, yet its stability is often compromised in Forbidden Zone, regions where the real teacher provides unreliable guidance while the fake teacher exerts insufficient…
We present an ultra-efficient post-training method for shortcutting large-scale pre-trained flow matching diffusion models into efficient few-step samplers, enabled by novel velocity field self-distillation. While shortcutting in flow…
Diffusion models showcase strong capabilities in image synthesis, being used in many computer vision tasks with great success. To this end, we propose to explore a new use case, namely to copy black-box classification models without having…
Perceptual studies demonstrate that conditional diffusion models excel at reconstructing video content aligned with human visual perception. Building on this insight, we propose a video compression framework that leverages conditional…
Diffusion Transformers (DiT) have become the de-facto model for generating high-quality visual content like videos and images. A huge bottleneck is the attention mechanism where complexity scales quadratically with resolution and video…
Diffusion models have made significant strides in image generation, mastering tasks such as unconditional image synthesis, text-image translation, and image-to-image conversions. However, their capability falls short in the realm of video…
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…
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…
Class-incremental learning aims to learn new classes in an incremental fashion without forgetting the previously learned ones. Several research works have shown how additional data can be used by incremental models to help mitigate…
Dataset distillation is an effective technique for reducing the cost and complexity of model training while maintaining performance by compressing large datasets into smaller, more efficient versions. In this paper, we present a novel…
Efficient streaming video generation is critical for simulating interactive and dynamic worlds. Existing methods distill few-step video diffusion models with sliding window attention, using initial frames as sink tokens to maintain…
With growing interest in deploying text-to-video (T2V) models in resource-constrained environments, reducing their high computational cost has become crucial, leading to extensive research on pruning and knowledge distillation methods while…
Recent years have witnessed the remarkable success of deep learning in remote sensing image interpretation, driven by the availability of large-scale benchmark datasets. However, this reliance on massive training data also brings two major…
Video editing and generation methods often rely on pre-trained image-based diffusion models. During the diffusion process, however, the reliance on rudimentary noise sampling techniques that do not preserve correlations present in…