Python framework that facilitates the quick development of complex video analysis applications and other series-processing based applications in a multiprocessing environment.

Director Agent + vision critic + image, video, music & voice models - all on a single AMD Instinct MI300X.

A pipeline framework for developing video and image processing application. Supports multiple GPUs and Machine Learning tooklits

Open-source AI video pipeline. Text prompt → scenario → images → video clips → editor → MP4. Self-hosted, multi-provider, MCP-ready.

YOLO/RTSP/RTMP edge camera proof of concept with paid integration review support

Hollywood-grade AI video production system: Multi-Agent orchestration, 25-field cinematic shot language, and automated filmmaking pipeline. Built for AI agents.

AI assisted video editing pipeline | scene analysis, LLM edit planning, ffmpeg rendering, and YouTube publishing.

AI-powered stickman animation video production pipeline - from script to YouTube. Uses Gemini, Imagen, edge-tts, ffmpeg. Slideshow mode costs ~.02/video.

One prompt -> full narrated MP4. Fully local AI video pipeline using ComfyUI (SD 1.5), FFmpeg, and Windows TTS. No SaaS APIs.

CPRE488 MP2 - 1080p HDMI video pipeline for Zynq using Vivado/Vitis—TPG→VDMA with GenLock→VTC→HDMI, plus YUV422 luminance processing and FMC I²C bring-up

AI-powered speculative video content pipeline. Generates cinematic 'what if' matchup videos from concept to YouTube — research, script, voice, character-consistent video, publish. ~$1.43/video.

AI-powered automated video reel generator · Python pipeline · input to output

A self-hosted video processing pipeline — queue, transcode, store, deliver.

Local-first 2D comic to 2.5D motion-comic video workflow with Remotion, FFmpeg, QA gates, and a Codex skill

Perception receipts for AI video pipelines. Cross-writer bit-exact under default settings (SHA-256 stable across writers in any language). Zero runtime dependencies; pure stdlib core. ~1.1 KB per video; per-frame CRC32 + schema + versioning. Useful now, improving continuously.

AI-driven vertical video pipeline — ElevenLabs STT + editorial subagent rough cut + Silero VAD + particle-burst Thai captions + AI B-roll, rendered with HyperFrames. Multi-template, v88.

Audio-reactive lyric visualization pipeline with subtitle alignment, rendering, and release automation.

Multimodal video annotation pipeline — local GPU end-to-end (audio, vision, OCR, faces, brands, chat, music). Turns any long-form video with people into a time-aligned event corpus for synthetic-data construction, training-set curation, and analysis.

Queue-based AI video rendering worker with voice, subtitles, ffmpeg and upload flow.

面向 OpenClaw 的课程/会议视频采集、Whisper 转写、关键帧/OCR、云端处理、飞书回传与笔记校验流水线。 / Window capture, Whisper transcription, keyframe/OCR extraction, cloud processing, Feishu delivery, and validated note generation pipeline for OpenClaw-powered course and meeting videos.