ILLUME: Illuminating Your LLMs to See, Draw, and Self-Enhance Paper • 2412.06673 • Published 13 days ago • 11
Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling Paper • 2412.05271 • Published 16 days ago • 116
Cycle3D: High-quality and Consistent Image-to-3D Generation via Generation-Reconstruction Cycle Paper • 2407.19548 • Published Jul 28 • 24
OD-VAE: An Omni-dimensional Video Compressor for Improving Latent Video Diffusion Model Paper • 2409.01199 • Published Sep 2 • 12
WF-VAE: Enhancing Video VAE by Wavelet-Driven Energy Flow for Latent Video Diffusion Model Paper • 2411.17459 • Published 26 days ago • 10
Open-Sora Plan: Open-Source Large Video Generation Model Paper • 2412.00131 • Published 25 days ago • 32
WF-VAE: Enhancing Video VAE by Wavelet-Driven Energy Flow for Latent Video Diffusion Model Paper • 2411.17459 • Published 26 days ago • 10
Open-Sora Plan: Open-Source Large Video Generation Model Paper • 2412.00131 • Published 25 days ago • 32
Open-Sora Plan: Open-Source Large Video Generation Model Paper • 2412.00131 • Published 25 days ago • 32 • 2