YSH's picture

YSH

BestWishYsh

·

https://shyuanbest.github.io/

AI & ML interests

None yet

Recent Activity

liked a model about 1 hour ago

Skywork/SkyReels-A2

upvoted a paper about 1 hour ago

SkyReels-A2: Compose Anything in Video Diffusion Transformers

upvoted a paper 1 day ago

Be Yourself: Bounded Attention for Multi-Subject Text-to-Image Generation

View all activity

Organizations

BestWishYsh's activity

upvoted a paper about 1 hour ago

SkyReels-A2: Compose Anything in Video Diffusion Transformers

Paper • 2504.02436 • Published about 17 hours ago • 3

upvoted 2 papers 1 day ago

Be Yourself: Bounded Attention for Multi-Subject Text-to-Image Generation

Paper • 2403.16990 • Published Mar 25, 2024 • 25

FlashFace: Human Image Personalization with High-fidelity Identity Preservation

Paper • 2403.17008 • Published Mar 25, 2024 • 21

upvoted a paper 3 days ago

TextCrafter: Accurately Rendering Multiple Texts in Complex Visual Scenes

Paper • 2503.23461 • Published 5 days ago • 72

upvoted 7 papers 4 days ago

Unified Multimodal Discrete Diffusion

Paper • 2503.20853 • Published 8 days ago • 8

Synthetic Video Enhances Physical Fidelity in Video Synthesis

Paper • 2503.20822 • Published 9 days ago • 15

Lumina-Image 2.0: A Unified and Efficient Image Generative Framework

Paper • 2503.21758 • Published 7 days ago • 18

ChatAnyone: Stylized Real-time Portrait Video Generation with Hierarchical Motion Diffusion Model

Paper • 2503.21144 • Published 8 days ago • 23

Video-R1: Reinforcing Video Reasoning in MLLMs

Paper • 2503.21776 • Published 7 days ago • 74

VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness

Paper • 2503.21755 • Published 7 days ago • 30

Segment Any Motion in Videos

Paper • 2503.22268 • Published 7 days ago • 15

upvoted a paper 6 days ago

ClassDiffusion: More Aligned Personalization Tuning with Explicit Class Guidance

Paper • 2405.17532 • Published May 27, 2024 • 1

upvoted 2 papers 7 days ago

LeX-Art: Rethinking Text Generation via Scalable High-Quality Data Synthesis

Paper • 2503.21749 • Published 7 days ago • 25

Wan: Open and Advanced Large-Scale Video Generative Models

Paper • 2503.20314 • Published 9 days ago • 44

upvoted a paper 8 days ago

FullDiT: Multi-Task Video Generative Foundation Model with Full Attention

Paper • 2503.19907 • Published 9 days ago • 8

upvoted a paper 10 days ago

MagicComp: Training-free Dual-Phase Refinement for Compositional Video Generation

Paper • 2503.14428 • Published 16 days ago • 8

upvoted 3 papers 14 days ago

InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity

Paper • 2503.16418 • Published 14 days ago • 33

MagicMotion: Controllable Video Generation with Dense-to-Sparse Trajectory Guidance

Paper • 2503.16421 • Published 14 days ago • 9

MagicID: Hybrid Preference Optimization for ID-Consistent and Dynamic-Preserved Video Customization

Paper • 2503.12689 • Published 18 days ago • 5

upvoted a paper 16 days ago

Concat-ID: Towards Universal Identity-Preserving Video Synthesis

Paper • 2503.14151 • Published 17 days ago • 10