Text-to-Video and Video Generation

4 repos

This cluster focuses on generative models and tools for creating videos from text prompts and other inputs, with a strong emphasis on open-source implementations. The repositories span diffusion-based video synthesis, LoRA fine-tuning frameworks, and practical adaptations of models like Flux and CogVideoX. Most repos are Python-based toolkits and research implementations exploring techniques for controllable video generation, customization, and optimization.

Python · 2
diffusion ·3,192
video-generation ·3,192
musev ·2,845
human-video-generation ·2,845
image2video ·2,845
infinite-length ·2,845
3d-reconstruction ·302
unified-model ·302
multimodal ·28
long-video-generation ·17