Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Models Paper • 2410.02416 • Published Oct 3, 2024 • 29
CFG-Zero*: Improved Classifier-Free Guidance for Flow Matching Models Paper • 2503.18886 • Published 10 days ago • 19
Common Diffusion Noise Schedules and Sample Steps are Flawed Paper • 2305.08891 • Published May 15, 2023 • 9
Tuning-Free Multi-Event Long Video Generation via Synchronized Coupled Sampling Paper • 2503.08605 • Published 23 days ago • 26
Cosmos World Foundation Model Platform for Physical AI Paper • 2501.03575 • Published Jan 7 • 76
Skywork-Reward-Data-Collection Collection Open-source preference datasets used to train the Skywork reward model series • 17 items • Updated Oct 12, 2024 • 16
VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models Paper • 2502.02492 • Published Feb 4 • 64
video-effects Collection Fine-tunes of open video generation models like CogVideoX to emulate cool video effects like "squish", "dissolve", "cakeify", etc. Pika inspired. • 8 items • Updated 26 days ago • 6
Towards Precise Scaling Laws for Video Diffusion Transformers Paper • 2411.17470 • Published Nov 25, 2024 • 1