Text-to-Video & Video Generation

143 repos across 7 sub-areas

Open-source models and tools for generating videos from text prompts and images, leveraging diffusion-based and transformer architectures. The cluster centers on practical implementations like CogVideo, HunyuanVideo, and VideoCrafter, alongside supporting libraries for video synthesis, inference optimization, and dataset preparation. Most repos are Python-based research and production code, with a secondary focus on image-to-video conversion and emerging models like Flux-based variants.

AI Video Generation and Animation

32 repos

Tools and models for generating, transforming, and animating video content using deep learning, spanning text-to-video synthesis, image-to-video conversion, and video editing frameworks. The cluster includes both foundational generative models and practical implementation repositories, with a heavy emphasis on Python-based pipelines and AIGC (AI-Generated Content) workflows. Central projects like VideoCrafter and TIP-I2V exemplify the technical depth, though most repos focus on making video generation accessible through various input modalities and customization checkpoints.

Text-to-Video and Image-to-Video Generation

24 repos

Tools and models for generating video content from text prompts and images, with a focus on diffusion-based approaches. The cluster centers on CogVideoX variants and related implementations that enable video synthesis at various resolutions and efficiency levels. Researchers and practitioners exploring this area will find model implementations, inference frameworks, and techniques for scaling video generation across different hardware constraints.

Cluster 634654

23 repos

Cluster 634658

23 repos

Cluster 634659

16 repos

Video Generation & Diffusion Models

14 repos

Text-to-video and image-to-video generation systems built on diffusion model architectures. This cluster centers on generative AI frameworks for converting textual descriptions or static images into video sequences, with significant focus on model variants, fine-tuning approaches (LoRA-based), and control mechanisms (depth, pose, edge detection). Repositories here span model implementations, inference code, and specialized adapter models for different control modalities.

Video Generation and Diffusion Models

11 repos

Libraries and model implementations for generating, processing, and controlling video content using diffusion-based approaches. The cluster centers on video generation frameworks built with popular diffusion libraries like Hugging Face Diffusers, leveraging safe tensor formats for model distribution. Repositories include both general-purpose video generation tools and specialized model variants (such as the Wan2.1-Fun series at different model scales) that enable video synthesis with varying levels of control and computational requirements.