Yushi Huang's picture

🔄 In a Training Loop

Yushi Huang

Harahan

·

https://harahan.github.io/

Harahan

AI & ML interests

Efficient AIGC, especially for video/image generation and MLLMs

Recent Activity

authored a paper 13 days ago

Flash-VAED: Plug-and-Play VAE Decoders for Efficient Video Generation

authored a paper 13 days ago

Real-Time Human Frontal View Synthesis from a Single Image

authored a paper 13 days ago

Salt: Self-Consistent Distribution Matching with Cache-Aware Training for Fast Video Generation

View all activity

Organizations

None yet

liked 3 models 23 days ago

Harahan/FLUX2-9B-RTDMD

Text-to-Image • Updated 19 days ago • 1

Harahan/SD35M-RTDMD

Text-to-Image • Updated 19 days ago • 1

Harahan/FLUX1-12B-RTDMD

Text-to-Image • Updated 19 days ago • 2

liked 3 models 4 months ago

lightx2v/Wan2.1-T2V-1.3B-longcat-step500

Text-to-Video • Updated Feb 11 • 50 • 4

lightx2v/Wan2.1-T2V-1.3B-longcat-step1000

Text-to-Video • Updated Feb 11 • 49 • 3

lightx2v/Wan2.1-T2V-1.3B-longcat-step1500

Text-to-Video • Updated Feb 11 • 160 • 7

liked 2 models 5 months ago

Harahan/QVGen-CogVideoX-2B-W4A4

Text-to-Video • Updated Feb 2 • 17 • 1

Harahan/QVGen-Wan-1_3B-W4A4

Text-to-Video • Updated Feb 2 • 9 • 2