Video Generation with Diffusion Models
24 repos
Deep learning approaches for synthesizing and manipulating video using diffusion models, flow matching, and diffusion transformers. Repositories cover video-to-video composition, motion transfer, frame interpolation, and end-to-end video generation from text or images. The cluster includes both foundational diffusion-based architectures and practical implementations, with most work in Python, centered on models like HunyuanVideo and Open-Sora that represent the state of neural video synthesis.
Python · 20
JavaScript · 1
diffusion-models ·40,665
video-generation ·40,665
diffusion-transformer ·25,126
hunyuan-video ·4,180
flow-matching ·3,902
world-models ·3,215
ltx-video ·2,803
qwen-image ·2,803
dreamzero ·2,803
auto-regressive-diffusion-model ·2,803
