Agent skill for narrated cinematic films built entirely from code: one continuous camera over photos, maps and cards, timed to the voice. Claude Code, Codex, Cursor, Gemini CLI.
- agent-skills
- claude-code
- codex
- documentary
132,241 visible repositories in the index
769–792 of 1,095 · Most stars
Agent skill for narrated cinematic films built entirely from code: one continuous camera over photos, maps and cards, timed to the voice. Claude Code, Codex, Cursor, Gemini CLI.
[CVPR 2024 Highlight] GenAD: Generalized Predictive Model for Autonomous Driving
Luminaire is a python package that provides ML driven solutions for monitoring time series data.
[CVPR 2025] VideoWorld is a simple generative model that learns purely from unlabeled videos—much like how babies learn by observing their environment.
将参考声音和中文文案自动生成白板动画视频的本地 AI 工具。
Official Implementation of OmniWeaving: Towards Unified Video Generation with Free-form Composition and Reasoning
Code and models accompanying "Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning"
This project provides a stock market environment using OpenGym with Deep Q-learning and Policy Gradient.
DeepSeek Harness 故事创作插件:集成网文写作、短剧漫剧、小说改游戏与视频解说四个可视化工作台 | DeepSeek Harness plugin for novels, short dramas, games & video recaps
[CVPR2026 🎉] Stand-In is a lightweight, plug-and-play framework for identity-preserving video generation.
OpenCV+YOLO+LLAVA powered video surveillance system
MemoRizz: A Python library serving as a memory layer for AI applications. Leverages popular databases and storage solutions to optimize memory usage. Provides utility classes and methods for efficient data management.
GitHub Copilot support for Sublime Text LSP plugin provided through Copilot.vim.
Implementation of Phenaki Video, which uses Mask GIT to produce text guided videos of up to 2 minutes in length, in Pytorch
Read-only mirror of https://gitlab.gnome.org/World/Constrict
A Munch is a Python dictionary that provides attribute-style access (a la JavaScript objects).
CLIP + FFT/DWT/RGB = text to image/video
Automatically ⬆️ upload TikTok videos
Official code for StoryMem: Multi-shot Long Video Storytelling with Memory
Code Video Model Official Repo
Editable reference-media timeline director for ComfyUI MiniMax H3 Reference to Video
Official implementation of FlowHMR, a generative model for physically plausible motion capture from monocular video.
Fizgig — LoRA & Fine-tune Studio for Klein 9B, Krea 2, MiniMax H3, Qwen Image 2.1, Anima & Z-Image Turbo and Ace-Step XL: train, fine-tune, profile, repair and extract LoRAs & LoKR for Image, Video & Music Models
Django module to easily send templated emails using django templates, or using a transactional mail provider (mailchimp, silverpop, etc.)