yangpei

yangpei's activity

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

upvoted a paper about 1 hour ago

Making MLLM Latents Matter: Factor-Aware Predictive Learning for Cinematic Video Generation

Paper • 2610.30926 • Published 1 day ago • 161

upvoted 2 papers 3 days ago

Has GPT-6-Astra Achieved Embodied Intelligence?

Paper • 2610.22471 • Published 9 days ago • 469

MT Forcing: Towards Stable and Consistent Multi-Turn Image Editing with Autoregressive Diffusion

Paper • 2610.25404 • Published 6 days ago • 45

upvoted 2 papers about 2 months ago

VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning

Paper • 2608.26105 • Published Aug 26 • 82

EchoWM: Open and Enterable Omnimodal World Models

Paper • 2608.23189 • Published Aug 24 • 83

upvoted a paper 4 months ago

Video-MME-Logical: A Controlled Diagnostic Benchmark for Video Temporal-Logical Reasoning

Paper • 2606.27828 • Published Jun 26 • 26

liked 2 datasets 4 months ago

svjack/3D_Chibi_Images_Captioned

Viewer • Updated May 31, 2025 • 139 • 17 • 1

HH-LG/StyleExpert

Viewer • Updated Mar 6 • 74.1k • 82 • 2

upvoted a paper 4 months ago

Latent Spatial Memory for Video World Models

Paper • 2606.09828 • Published Jun 8 • 71

upvoted a paper 5 months ago

EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation

Paper • 2605.23271 • Published May 22 • 75

liked a Space 10 months ago

Running on Zero

Agents

Featured

2.7k

Qwen Image Multiple Angles 3D Camera

🎥

2.7k

Edit image perspective by adjusting camera angle

updated a model 11 months ago

yangpei/TokenPure

Updated Dec 4, 2025 • 2

published a model 11 months ago

yangpei/TokenPure

Updated Dec 4, 2025 • 2

liked a dataset 12 months ago

Yejy53/Echo-4o-Image

Viewer • Updated Oct 9, 2025 • 5.3k • 600 • 36

liked a dataset about 1 year ago

jackyhate/text-to-image-2M

Updated Jul 28 • 1.69k • 187

New activity in XLabs-AI/flux-ip-adapter-v2 about 1 year ago

Flux’s IPAdapter with a high weight (necessary for the desired aesthetic) ‘breaks’ the consistency of the generated image in relation to the base image when used together with ControlNet.

1

#19 opened over 1 year ago by

xpropcks

New activity in InstantX/FLUX.1-dev-IP-Adapter over 1 year ago

Whether to provide the code to train the adapter

4

#7 opened almost 2 years ago by

liu00

training code for ip-adapter with Flux.1-dev?

1

#13 opened over 1 year ago by

mxymxymxy