Related papers: Few-Step Diffusion via Score identity Distillation

Recent advancements in text-to-3D generation improve the visual quality of Score Distillation Sampling (SDS) and its variants by directly connecting Consistency Distillation (CD) to score distillation. However, due to the imbalance between…

Text-to-Image (T2I) generation methods based on diffusion model have garnered significant attention in the last few years. Although these image synthesis methods produce visually appealing results, they frequently exhibit spelling errors…

Although recent advancements in text-to-3D generation have significantly improved generation quality, issues like limited level of detail and low fidelity still persist, which requires further improvement. To understand the essence of those…

Training machine learning models on massive datasets is expensive and time-consuming. Dataset distillation addresses this by creating a small synthetic dataset that achieves the same performance as the full dataset. Recent methods use…

Score distillation sampling (SDS) demonstrates a powerful capability for text-conditioned 2D image and 3D object generation by distilling the knowledge from learned score functions. However, SDS often suffers from blurriness caused by noisy…

Distilled one-step (T=1) or few-step (T$\leq$4) diffusion models enable real-time image generation but often exhibit reduced sample diversity compared to their multi-step counterparts. In multi-step diffusion, diversity can be introduced…

Dataset distillation enables efficient training by distilling the information of large-scale datasets into significantly smaller synthetic datasets. Diffusion based paradigms have emerged in recent years, offering novel perspectives for…

Recent score-based diffusion models (SBDMs) show promising results in unpaired image-to-image translation (I2I). However, existing methods, either energy-based or statistically-based, provide no explicit form of the interfered intermediate…

Large pretrained diffusion models have significantly enhanced the quality of generated videos, and yet their use in real-time streaming remains limited. Autoregressive models offer a natural framework for sequential frame synthesis but…

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…

Idempotent generative networks (IGNs) are a new line of generative models based on idempotent mapping to a target manifold. IGNs support both single-and multi-step generation, allowing for a flexible trade-off between computational cost and…

With the success of flow matching in visual generation, sampling efficiency remains a critical bottleneck for its practical application. Among flow models' accelerating methods, ReFlow has been somehow overlooked although it has theoretical…

Currently, Flow matching methods aim to compress the iterative generation process of diffusion models into a few or even a single step, with MeanFlow and FreeFlow being representative achievements of one-step generation based on Ordinary…

Score distillation sampling is an effective technique to generate 3D models from text prompts, utilizing pre-trained large-scale text-to-image diffusion models as guidance. However, the produced 3D assets tend to be over-saturating,…

Dataset distillation seeks to synthesize a highly compact dataset that achieves performance comparable to the original dataset on downstream tasks. For the classification task that use pre-trained self-supervised models as backbones,…

The extensive amounts of data required for training deep neural networks pose significant challenges on storage and transmission fronts. Dataset distillation has emerged as a promising technique to condense the information of massive…

Data Fairness is a crucial topic due to the recent wide usage of AI powered applications. Most of the real-world data is filled with human or machine biases and when those data are being used to train AI models, there is a chance that the…

Dataset distillation aims to encapsulate the rich information contained in dataset into a compact distilled dataset but it faces performance degradation as the image-per-class (IPC) setting or image resolution grows larger. Recent…

Data-free knowledge distillation aims to learn a compact student network from a pre-trained large teacher network without using the original training data of the teacher network. Existing collection-based and generation-based methods train…

The slow inference process of image diffusion models significantly degrades interactive user experiences. To address this, we introduce Diffusion Preview, a novel paradigm employing rapid, low-step sampling to generate preliminary outputs…