16 papers
RefAlign: Representation Alignment for Reference-to-Video Generation
Lei Wang, YuXin Song, Ge Wu +5
Reference-to-video (R2V) generation is a controllable video synthesis paradigm that constrains the generation process using both text prompts and reference images, enabling applica…
Training-free image inversion for one-step diffusion models
Tao Wu, Senmao Li, Yaxing Wang +3
In this work, we introduce a novel training-free inversion (TFinv) framework for one-step diffusion models,addressing key challenges in real image inversion and editing. We first i…
FasterVAR: Plug-and-Play Acceleration for Visual Autoregressive Models
Senmao Li, Kai Wang, Salman Khan +3
Visual Autoregressive (VAR) modeling departs from the next-token prediction paradigm of traditional Autoregressive (AR) models through next-scale prediction, enabling high-quality…
Continuous-Time Distribution Matching for Few-Step Diffusion Distillation
Tao Liu, Hao Yan, Mengting Chen +8
Step distillation has become a leading technique for accelerating diffusion models, among which Distribution Matching Distillation (DMD) and Consistency Distillation are two repres…
Adversarial Concept Distillation for One-Step Diffusion Personalization
Yixiong Yang, Tao Wu, Senmao Li +4
Recent progress in accelerating text-to-image diffusion models enables high-fidelity synthesis within a single denoising step. However, customizing the fast one-step models remains…
WaDi: Weight Direction-aware Distillation for One-step Image Synthesis
Lei Wang, Yang Cheng, Senmao Li +3
Despite the impressive performance of diffusion models such as Stable Diffusion (SD) in image generation, their slow inference limits practical deployment. Recent works accelerate…