119 citations · 166 across the 22 of their papers we have counts for
27 papers
Context Unrolling in Omni Models
Ceyuan Yang, Zhijie Lin, Yang Zhao +16
We present Omni, a unified multimodal model natively trained on diverse modalities, including text, images, videos, 3D geometry, and hidden representations. We find that such train…
Seedance 2.0: Advancing Video Generation for World Complexity
Team Seedance, De Chen, Liyang Chen +168
Seedance 2.0 is a new native multi-modal audio-video generation model, officially released in China in early February 2026. Compared with its predecessors, Seedance 1.0 and 1.5 Pro…
Continuous Adversarial Flow Models
Shanchuan Lin, Ceyuan Yang, Zhijie Lin +2
We propose continuous adversarial flow models, a type of continuous-time flow model trained with an adversarial objective. Unlike flow matching, which uses a fixed mean-squared-err…
UniWeTok: An Unified Binary Tokenizer with Codebook Size for Unified Multimodal Large Language Model
Shaobin Zhuang, Yuang Ai, Jiaming Han +12
Unified Multimodal Large Language Models (MLLMs) require a visual representation that simultaneously supports high-fidelity reconstruction, complex semantic extraction, and generat…
Seedance 1.5 pro: A Native Audio-Visual Joint Generation Foundation Model
Team Seedance, Heyi Chen, Siyan Chen +194
Recent strides in video generation have paved the way for unified audio-visual generation. In this work, we present Seedance 1.5 pro, a foundational model engineered specifically f…
Adversarial Flow Models
Shanchuan Lin, Ceyuan Yang, Zhijie Lin +2
We present adversarial flow models, a class of generative models that belongs to both the adversarial and flow families. Our method supports native one-step and multi-step generati…
SkipSR: Faster Super Resolution with Token Skipping
Rohan Choudhury, Shanchuan Lin, Jianyi Wang +6
Diffusion-based super-resolution (SR) is a key component in video generation and video restoration, but is slow and expensive, limiting scalability to higher resolutions and longer…
Growing Visual Generative Capacity for Pre-Trained MLLMs
Hanyu Wang, Jiaming Han, Ziyan Yang +6
Multimodal large language models (MLLMs) extend the success of language models to visual understanding, and recent efforts have sought to build unified MLLMs that support both unde…
Adversarial Distribution Matching for Diffusion Distillation Towards Efficient Image and Video Synthesis
Yanzuo Lu, Yuxi Ren, Xin Xia +6
Distribution Matching Distillation (DMD) is a promising score distillation technique that compresses pre-trained teacher diffusion models into efficient one-step or multi-step stud…
Seedance 1.0: Exploring the Boundaries of Video Generation Models
Yu Gao, Haoyuan Guo, Tuyen Hoang +41
Notable breakthroughs in diffusion modeling have propelled rapid improvements in video generation, yet current foundational model still face critical challenges in simultaneously b…
VINCIE: Unlocking In-context Image Editing from Video
Leigang Qu, Feng Cheng, Ziyan Yang +7
In-context image editing aims to modify images based on a contextual sequence comprising text and previously generated images. Existing methods typically depend on task-specific pi…
Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation
Shanchuan Lin, Ceyuan Yang, Hao He +6
Existing large-scale video generation models are computationally intensive, preventing adoption in real-time and interactive applications. In this work, we propose autoregressive a…
SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training
Jianyi Wang, Shanchuan Lin, Zhijie Lin +10
Recent advances in diffusion-based video restoration (VR) demonstrate significant improvement in visual quality, yet yield a prohibitive computational cost during inference. While…
Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model
Team Seawead, Ceyuan Yang, Zhijie Lin +52
This technical report presents a cost-efficient strategy for training a video generation foundation model. We present a mid-sized research model with approximately 7 billion parame…
Training-free Diffusion Acceleration with Bottleneck Sampling
Ye Tian, Xin Xia, Yuxi Ren +6
Diffusion models have demonstrated remarkable capabilities in visual content generation but remain challenging to deploy due to their high computational cost during inference. This…
CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Models
Hao He, Ceyuan Yang, Shanchuan Lin +7
This paper introduces CameraCtrl II, a framework that enables large-scale dynamic scene exploration through a camera-controlled video diffusion model. Previous camera-conditioned v…
Diffusion Adversarial Post-Training for One-Step Video Generation
Shanchuan Lin, Xin Xia, Yuxi Ren +3
The diffusion models are widely used for image and video generation, but their iterative generation process is slow and expansive. While existing distillation approaches have demon…
Is Your Text-to-Image Model Robust to Caption Noise?
Weichen Yu, Ziyan Yang, Shanchuan Lin +5
In text-to-image (T2I) generation, a prevalent training technique involves utilizing Vision Language Models (VLMs) for image re-captioning. Even though VLMs are known to exhibit ha…
AnimateDiff-Lightning: Cross-Model Diffusion Distillation
Shanchuan Lin, Xiao Yang
We present AnimateDiff-Lightning for lightning-fast video generation. Our model uses progressive adversarial diffusion distillation to achieve new state-of-the-art in few-step vide…
SDXL-Lightning: Progressive Adversarial Diffusion Distillation
Shanchuan Lin, Anran Wang, Xiao Yang
We propose a diffusion distillation method that achieves new state-of-the-art in one-step/few-step 1024px text-to-image generation based on SDXL. Our method combines progressive an…
Diffusion Model with Perceptual Loss
Shanchuan Lin, Xiao Yang
Diffusion models without guidance generate very unrealistic samples. Guidance is used ubiquitously, and previous research has attributed its effect to low-temperature sampling that…
MagicProp: Diffusion-based Video Editing via Motion-aware Appearance Propagation
Hanshu Yan, Jun Hao Liew, Long Mai +2
This paper addresses the issue of modifying the visual appearance of videos while preserving their motion. A novel framework, named MagicProp, is proposed, which disentangles the v…
Common Diffusion Noise Schedules and Sample Steps are Flawed
Shanchuan Lin, Bingchen Liu, Jiashi Li +1
We discover that common diffusion noise schedules do not enforce the last timestep to have zero signal-to-noise ratio (SNR), and some implementations of diffusion samplers do not s…
Robust High-Resolution Video Matting with Temporal Guidance
Shanchuan Lin, Linjie Yang, Imran Saleemi +1
We introduce a robust, real-time, high-resolution human video matting method that achieves new state-of-the-art performance. Our method is much lighter than previous approaches and…