42 citations · 65 across the 11 of their papers we have counts for
14 papers
A Better Critic Matters for Distribution Matching Distillation
Zongze Wu, Xianbang Wang, Zhengyang Geng +5
Distribution Matching Distillation (DMD) trains a few-step student using the difference between a teacher's score and an online critic's estimate of the student distribution's scor…
EditStream: A Unified Autoregressive Framework for Interactive Video Generation and Editing
Yuqian Zhou, Zhenghong Zhou, Zongze Wu +5
Interactive video generation and editing are becoming increasingly important for creative design. In this report, we introduce EditStream: a unified framework for interactive video…
Improved Baselines with Representation Autoencoders
Jaskirat Singh, Boyang Zheng, Zongze Wu +3
Representation Autoencoders (RAE) replace traditional VAE with pretrained vision encoders. In this paper, we systematically investigate several design choices and find three insigh…
End-to-End Training for Unified Tokenization and Latent Denoising
Shivam Duggal, Xingjian Bai, Zongze Wu +5
Latent diffusion models (LDMs) enable high-fidelity synthesis by operating in learned latent spaces. However, training state-of-the-art LDMs requires complex staging: a tokenizer m…
Causality in Video Diffusers is Separable from Denoising
Xingjian Bai, Guande He, Zhengqi Li +3
Causality -- referring to temporal, uni-directional cause-effect relationships between components -- underlies many complex generative processes, including videos, language, and ro…
What matters for Representation Alignment: Global Information or Spatial Structure?
Jaskirat Singh, Xingjian Leng, Zongze Wu +4
Representation alignment (REPA) guides generative training by distilling representations from a strong, pretrained vision encoder to intermediate diffusion features. We investigate…
Improved Mean Flows: On the Challenges of Fastforward Generative Models
Zhengyang Geng, Yiyang Lu, Zongze Wu +3
MeanFlow (MF) has recently been established as a framework for one-step generative modeling. However, its ``fastforward'' nature introduces key challenges in both the training obje…
SliderSpace: Decomposing the Visual Capabilities of Diffusion Models
Rohit Gandikota, Zongze Wu, Richard Zhang +3
We present SliderSpace, a framework for automatically decomposing the visual capabilities of diffusion models into controllable and human-understandable directions. Unlike existing…
TurboEdit: Instant text-based image editing
Zongze Wu, Nicholas Kolkin, Jonathan Brandt +2
We address the challenges of precise image inversion and disentangled image editing in the context of few-step diffusion models. We introduce an encoder based iterative inversion t…
Lazy Diffusion Transformer for Interactive Image Editing
Yotam Nitzan, Zongze Wu, Richard Zhang +4
We introduce a novel diffusion transformer, LazyDiffusion, that generates partial image updates efficiently. Our approach targets interactive image editing applications in which, s…
Third Time's the Charm? Image and Video Editing with StyleGAN3
Yuval Alaluf, Or Patashnik, Zongze Wu +4
StyleGAN is arguably one of the most intriguing and well-studied generative models, demonstrating impressive performance in image generation, inversion, and manipulation. In this w…
StyleAlign: Analysis and Applications of Aligned StyleGAN Models
Zongze Wu, Yotam Nitzan, Eli Shechtman +1
In this paper, we perform an in-depth study of the properties and applications of aligned generative models. We refer to two models as aligned if they share the same architecture,…
StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery
Or Patashnik, Zongze Wu, Eli Shechtman +2
Inspired by the ability of StyleGAN to generate highly realistic images in a variety of domains, much recent work has focused on understanding how to use the latent spaces of Style…
StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation
Zongze Wu, Dani Lischinski, Eli Shechtman
We explore and analyze the latent style space of StyleGAN2, a state-of-the-art architecture for image generation, using models pretrained on several different datasets. We first sh…