43 23 17

YSH

BestWishYsh

https://shyuanbest.github.io/

AI & ML interests

None yet

Recent Activity

new activity 9 days ago

Senqiao/LISA_Plus_7b:How to load the model?

upvoted a paper 10 days ago

EchoVideo: Identity-Preserving Human Video Generation by Multimodal Feature Fusion

commented on a paper 10 days ago

EchoVideo: Identity-Preserving Human Video Generation by Multimodal Feature Fusion

View all activity

Organizations

BestWishYsh's activity

New activity in Senqiao/LISA_Plus_7b 9 days ago

How to load the model?

#1 opened 13 days ago by

zinkovich

upvoted a paper 10 days ago

EchoVideo: Identity-Preserving Human Video Generation by Multimodal Feature Fusion

Paper • 2501.13452 • Published 11 days ago • 7

commented a paper 10 days ago

EchoVideo: Identity-Preserving Human Video Generation by Multimodal Feature Fusion

Paper • 2501.13452 • Published 11 days ago • 7 •

upvoted a paper 11 days ago

Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step

Paper • 2501.13926 • Published 11 days ago • 33

commented a paper 11 days ago

Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step

Paper • 2501.13926 • Published 11 days ago • 33 •

updated a dataset 15 days ago

BestWishYsh/ConsisID-preview-Data

Viewer • Updated 15 days ago • 31.9k • 678 • 19

updated a model 15 days ago

BestWishYsh/ConsisID-preview

Image-to-Video • Updated 15 days ago • 687 • 26

updated a Space 15 days ago

Runtime error

🔥

ConsisID-preview

Identity-Preserving Text-to-Video Generation

upvoted a paper 21 days ago

Multi-subject Open-set Personalization in Video Generation

Paper • 2501.06187 • Published 24 days ago • 14

commented 2 papers 21 days ago

ConceptMaster: Multi-Concept Video Customization on Diffusion Transformer Models Without Test-Time Tuning

Paper • 2501.04698 • Published 26 days ago • 15 •

Multi-subject Open-set Personalization in Video Generation

Paper • 2501.06187 • Published 24 days ago • 14 •

upvoted a paper 22 days ago

ConceptMaster: Multi-Concept Video Customization on Diffusion Transformer Models Without Test-Time Tuning

Paper • 2501.04698 • Published 26 days ago • 15

upvoted a paper 28 days ago

Ingredients: Blending Custom Photos with Video Diffusion Transformers

Paper • 2501.01790 • Published Jan 3 • 8

commented a paper 28 days ago

Ingredients: Blending Custom Photos with Video Diffusion Transformers

Paper • 2501.01790 • Published Jan 3 • 8 •

updated a Space about 1 month ago

Running

🥇

ChronoMagic Bench

A Benchmark for Metamorphic Evaluation of T2V Generation

updated a dataset about 1 month ago

BestWishYsh/ChronoMagic-Bench

Viewer • Updated Dec 31, 2024 • 1.8k • 113 • 10

upvoted a paper about 1 month ago

VideoMaker: Zero-shot Customized Video Generation with the Inherent Force of Video Diffusion Models

Paper • 2412.19645 • Published Dec 27, 2024 • 13

commented a paper about 1 month ago

VideoMaker: Zero-shot Customized Video Generation with the Inherent Force of Video Diffusion Models

Paper • 2412.19645 • Published Dec 27, 2024 • 13 •

New activity in Alibaba-NLP/gme-Qwen2-VL-7B-Instruct about 1 month ago

Question about the Figure 5 in ArXiv

#3 opened about 1 month ago by

BestWishYsh

Release the UMRB

#2 opened about 1 month ago by

BestWishYsh