Tag
A prompt template you can paste directly into Claude Code to automatically set up a local video workbench based on ffmpeg, Python, and Playwright, designed for macOS/Linux developers.
An open-source Agent Skill called ffmpeg-skill integrates FFmpeg directly into AI coding assistants like Claude Code, Cursor, and Codex, providing 42 tools for video editing with a probe-process-verify workflow that runs entirely locally via a single `npx ffmpeg-skill` install.
The author has open-sourced 'jevclip', a tool based on Jev that processes videos to generate summaries, highlight reels, and trimmed versions by removing unnecessary content, with adjustable parameters and low cost.
Qwen3.8-Omni-Flash is a natively multimodal agentic model designed for real-world productivity, improving multimodal understanding and reasoning with a MoE architecture and extended context window, along with releasing open-source frameworks for multimodal applications.
A tool that allows users to upload videos, explore them in volumetric playback, export 360-degree orbits, and customize the orbit tempo for download.
Video Volume is a web-based tool that enables users to visualize videos in a 3D volume with interactive orbiting and zooming controls, supporting MP4 and MOV formats.
This article points out the pain points in academic toy demos and industrial precision assembly, including view occlusion, high degrees of freedom dynamics nonlinear contact, video acquisition delay, and GPU resource waste caused by cloud training.
Google's agentic video understanding capability is being utilized by three companies to reduce costs and enhance accuracy in video processing tasks using Gemini Flash models.
The author details fixing a green/pink video bug on an NZXT Signal 4K30 capture card caused by an RGB vs. YUV mismatch, with assistance from Claude AI for firmware investigation.
A tweet demonstrating AGI transcription and full harmony analysis capabilities from a video, likely showcasing an AI tool or feature.
This repository provides LoRAs for the MiniMax H3 model, designed to run in ComfyUI for video enhancement, such as sharpening videos while maintaining photorealism.
Agentic Video in the Gemini API is a new feature that reduces token consumption by up to 88% while increasing quality for processing long videos, enabling tools like Thumio to generate YouTube thumbnails from links.
LeVJEPA extends LeJEPA to video for efficient training, using one encoder and projector to process only 5% of video patches, matching or beating V-JEPA 2 with significantly less compute.
Smart Thumbnails in Qencode MCP enables agents to automatically select video thumbnails, streamlining the workflow from upload to publish without manual intervention.
SubSmith is a language-learning platform that converts user videos into study materials by generating accurate subtitles, offering instant word definitions, and integrating with Anki for flashcard export.
A GitHub repository aggregating 979 video scraping APIs for downloading, transcribing, and extracting metadata from multiple video platforms.
ABot-Recon enables real-time 3D reconstruction of large-scale environments from continuous video streams by using a fixed local context, achieving high efficiency and low memory usage.
FFmpeg 9.0 is a major release of the popular open-source multimedia framework, offering libraries and command-line tools for audio, video, subtitle and metadata processing.
This paper addresses the challenge of maintaining boundary faithfulness in backbone models when processing subsequent video frames beyond the first.
China open-sourced a real-time 3D scene reconstruction model that works from a single regular video without LiDAR, achieving 20 FPS on a single GPU and maintaining stability over 10,000+ frames.