Text-to-Video and Image-to-Video Generation
23 repos
Generative AI models and tools for synthesizing videos from text prompts or image inputs, including diffusion-based architectures and LoRA-based control mechanisms. The cluster spans foundational video generation models like Pyramid Flow and Vchitect, alongside specialized LoRA detailers for fine-grained control over video attributes (depth, pose, edge detection). Most repositories are implemented in Python with supporting JavaScript and notebook-based demos, reflecting both research codebases and interactive inference tooling.
Python · 4
JavaScript · 3
Jupyter Notebook · 2
text-to-video ·49,631
image-to-video ·49,631
text-to-image ·29,304
seedance2 ·28,996
generative-ai ·28,703
ai-video-generation ·28,617
kling-ai ·28,617
muapi ·28,424
open-source ·28,424
ai-art-generator ·28,131
