YSH

BestWishYsh's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a Space 6 days ago

Running

9

OpenS2V Eval

📊

9

A Detailed Benchmark for Subject-to-Video Generation

updated 2 datasets 8 days ago

BestWishYsh/OpenS2V-Eval

Preview • Updated 8 days ago • 1k • 5

BestWishYsh/OpenS2V-5M

Updated 8 days ago • 26.4k • 23

New activity in BestWishYsh/OpenS2V-Eval about 1 month ago

Update app.py

2

#2 opened about 1 month ago by

franciszzj

upvoted a paper about 2 months ago

Plan-X: Instruct Video Generation via Semantic Planning

Paper • 2511.17986 • Published Nov 22, 2025 • 17

New activity in BestWishYsh/OpenS2V-Eval about 2 months ago

runtime error

❤️ 1

1

#1 opened about 2 months ago by

carpedkm

updated a Space 2 months ago

Build error

75

ConsisID-preview

🔥

75

Identity-Preserving Text-to-Video Generation

New activity in BestWishYsh/OpenS2V-Eval 3 months ago

Need support to update the datasets and verify the account

2

#3 opened 3 months ago by

BestWishYsh

upvoted a paper 3 months ago

FlashI2V: Fourier-Guided Latent Shifting Prevents Conditional Image Leakage in Image-to-Video Generation

Paper • 2509.25187 • Published Sep 29, 2025 • 2

authored 2 papers 3 months ago

FlashI2V: Fourier-Guided Latent Shifting Prevents Conditional Image Leakage in Image-to-Video Generation

Paper • 2509.25187 • Published Sep 29, 2025 • 2

Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedback

Paper • 2510.16888 • Published Oct 19, 2025 • 21

upvoted a paper 3 months ago

Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedback

Paper • 2510.16888 • Published Oct 19, 2025 • 21

liked a dataset 3 months ago

ZhuoweiChen/Phantom-data-Koala36M

Preview • Updated Sep 30, 2025 • 73 • 9

upvoted a paper 3 months ago

BindWeave: Subject-Consistent Video Generation via Cross-Modal Integration

Paper • 2510.00438 • Published Oct 1, 2025 • 9

commented a paper 3 months ago

BindWeave: Subject-Consistent Video Generation via Cross-Modal Integration

Paper • 2510.00438 • Published Oct 1, 2025 • 9 •

2

upvoted a paper 4 months ago

OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling

Paper • 2509.12201 • Published Sep 15, 2025 • 106

liked a model 4 months ago

tencent/HunyuanImage-2.1

Text-to-Image • Updated Oct 14, 2025 • 239 • • 475

upvoted 3 papers 5 months ago

Mixture of Contexts for Long Video Generation

Paper • 2508.21058 • Published Aug 28, 2025 • 35

CineScale: Free Lunch in High-Resolution Cinematic Visual Generation

Paper • 2508.15774 • Published Aug 21, 2025 • 20

Wan-S2V: Audio-Driven Cinematic Video Generation

Paper • 2508.18621 • Published Aug 26, 2025 • 20