(WIP) A convenient and user-friendly anime-style video data processing library that integrates various advanced anime-style video processing techs and models

Video dataset dedicated to portrait-mode video recognition.

[NeurIPS 2024] Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image

Any-length Video Inpainting and Editing with Plug-and-Play Context Control

Tools for merging pretrained large language models.

🔥 InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity

The official Python SDK for Model Context Protocol servers and clients

SynCity: Training-Free Generation of 3D Worlds

StarVector is a foundation model for SVG generation that transforms vectorization into a code generation task. Using a vision-language modeling architecture, StarVector processes both visual and te…

MagicMotion: Controllable Video Generation with Dense-to-Sparse Trajectory Guidance

[CVPR 2025] StdGEN: Semantic-Decomposed 3D Character Generation from Single Images

Pixeltable — AI Data infrastructure providing a declarative, incremental approach for multimodal workloads.

[CVPR 2025] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

HuBERT content encoders for: A Comparison of Discrete and Soft Speech Units for Improved Voice Conversion

Public repository containing METR's DVC pipeline for eval data analysis

Various AI scripts. Mostly Stable Diffusion stuff.

Code of LHM: Large Animatable Human Reconstruction Model for Single Image to 3D in Seconds

[ECCV2024] VideoMamba: State Space Model for Efficient Video Understanding

Cut video files with minimal recoding

Open-source, accurate and easy-to-use video speech recognition & clipping tool, LLM based AI clipping intergrated.

SkyReels V1: The first and most advanced open-source human-centric video foundation model

SkyReels-A1: Expressive Portrait Animation in Video Diffusion Transformers

利用AI大模型，一键解说并剪辑视频； Using AI models to automatically provide commentary and edit videos with a single click.

Easily create large video dataset from video urls

Win & Liunux Gradio WebUI for CSM-1B model by sesame