YSH PRO

BestWishYsh's activity

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

upvoted a collection 6 days ago

2026 March 🍀 - China Open Source Highlights

Collection

13 items • Updated 4 days ago • 3

upvoted an article 9 days ago

view article

Article

Make your ZeroGPU Spaces go brrr with ahead-of-time compilation

• 
• 
• +2

Sep 2, 2025

•

76

upvoted a paper 9 days ago

HiFi-Inpaint: Towards High-Fidelity Reference-Based Inpainting for Generating Detail-Preserving Human-Product Images

Paper • 2603.02210 • Published 12 days ago • 28

upvoted an article 10 days ago

view article

Article

ZeroGPU Spaces 加速实践：PyTorch Ahead-of-Time Compilation 全解析

• 
• 
• +2

Sep 2, 2025

•

8

upvoted a paper 10 days ago

Helios: Real Real-Time Long Video Generation Model

Paper • 2603.04379 • Published 10 days ago • 163

upvoted a collection 20 days ago

Helios

Collection

Helios: 14B Real-Time Long Video Generation Model can be Cheaper, Faster but Keep Stronger than 1.3B ones • 7 items • Updated 5 days ago • 20

upvoted a paper about 1 month ago

FSVideo: Fast Speed Video Diffusion Model in a Highly-Compressed Latent Space

Paper • 2602.02092 • Published Feb 2 • 18

upvoted 2 papers about 2 months ago

iFSQ: Improving FSQ for Image Generation with 1 Line of Code

Paper • 2601.17124 • Published Jan 23 • 33

Focal Guidance: Unlocking Controllability from Semantic-Weak Layers in Video Diffusion Models

Paper • 2601.07287 • Published Jan 12 • 5

upvoted a paper 4 months ago

Plan-X: Instruct Video Generation via Semantic Planning

Paper • 2511.17986 • Published Nov 22, 2025 • 18

upvoted 3 papers 5 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 • 22

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

Paper • 2510.00438 • Published Oct 1, 2025 • 10

upvoted a paper 6 months ago

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

Paper • 2509.12201 • Published Sep 15, 2025 • 107

upvoted 6 papers 7 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

Accelerate High-Quality Diffusion Models with Inner Loop Feedback

Paper • 2501.13107 • Published Jan 22, 2025 • 3

Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity

Paper • 2502.01776 • Published Feb 3, 2025 • 3

SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer

Paper • 2501.18427 • Published Jan 30, 2025 • 24