Fengyuan Shi

shifengyuan's activity

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

authored 2 papers 4 days ago

BIVDiff: A Training-Free Framework for General-Purpose Video Synthesis via Bridging Image and Video Diffusion Models

Paper • 2312.02813 • Published Dec 5, 2023 • 1

Taming Scalable Visual Tokenizer for Autoregressive Image Generation

Paper • 2412.02692 • Published Dec 3, 2024

updated 5 models 4 days ago

TencentARC/Open-MAGVIT2-AR-XL-256-resolution

Updated 4 days ago • 4 • 1

TencentARC/Open-MAGVIT2-AR-L-256-resolution

Updated 4 days ago • 4

TencentARC/Open-MAGVIT2-AR-B-256-resolution

Updated 4 days ago • 4

TencentARC/Open-MAGVIT2-Tokenizer-256-resolution

Updated 4 days ago • 4

TencentARC/Open-MAGVIT2-Tokenizer-128-resolution

Updated 4 days ago • 6

updated 8 models 7 days ago

TencentARC/IBQ-AR-XXL

Updated 7 days ago • 4 • 1

TencentARC/IBQ-AR-XL

Updated 7 days ago • 4

TencentARC/IBQ-AR-L

Updated 7 days ago • 4

TencentARC/IBQ-AR-B

Updated 7 days ago • 6

TencentARC/IBQ-Tokenizer-262144

Updated 7 days ago • 2

TencentARC/IBQ-Tokenizer-8192

Updated 7 days ago • 2

TencentARC/IBQ-Tokenizer-1024

Updated 7 days ago • 4

TencentARC/IBQ-Tokenizer-16384

Updated 7 days ago • 4

updated a collection about 1 month ago

SEED-Voken

Collection

A Series of Powerful Visual Tokenizers • 14 items • Updated Dec 4, 2024