AI video generation

Sistema de recomendacion de videos basado en Deep Learning. CNN, YOLOv8, Transfer Learning, KNN. Proyecto de Fin de Master.

Wan2.2 video, one click in Pinokio, any NVIDIA GPU (12GB+): text/image-to-video, restyle, talking characters; and a Gym that trains both video and joint audio+video (MOVA) LoRAs, then continues MOVA clips past their native length. These are the frames you're looking for.

MCP server + CLI to generate image, video, music and speech through Chutes, saved straight into your project.

Practical prompt patterns for image-to-video and text-to-video workflows.

KupkaProd Music Video Pipeline — AI-assisted music video production (keyframes → LTX 2.3 ia2v → assembled with master audio). Zero-setup portable launcher.

Cortes verticais 9:16 pra gameplay — grátis, open source e 100% no seu PC. Sem cadastro, com a sua chave de IA.

Simple AI skills to turn one long video into short-form clips and carousels for X, Instagram Reels, TikTok, LinkedIn, and YouTube Shorts. Offline, CPU-only, on your own brand.

Deforum-style animation for ComfyUI: math keyframe schedules, audio reactivity, camera warp, prompt travel, kaleidoscope and a native realtime Live Sampler. SDXL/Flux/SD3.5/Wan 2.2.

Open-source AI video clipping tool for turning long-form videos into short clips with local or self-hosted processing.

WRBench: camera-controlled generation and diagnostic evaluation of video world models.

You built it. Now brag. Turn the project you just created into a short, shareable launch video with one command.

Master camera movements, 3D design, and video effects with this professional prompt engineering framework for AI video models (Seedance 2.0, Sora, Kling). Features a scene-by-scene video prompt structure and a 250-base cinematography dictionary. Let's gen it!

A single all-in-one ComfyUI node — **SCAIL-2 Infinity (auto window)** — that turns the core `WanSCAILToVideo` chunked workflow into one node that generates **arbitrarily long** SCAIL-2 video automatically.

MaineCoon: Pursuing a Real-Time Audio-Visual Social World Model — technical report & project links. 🌐 https://mainecoon.tech/

Give an AI eyes for video — turn a clip into a numbered frame grid + transcript a vision LLM can read.

Generate 16:9 & 9:16 videos with your HeyGen avatar, animated backgrounds (HyperFrames), music, SFX and Hormozi captions — then publish them to every social network. Reusable skill.

Open-source AI ad asset system and AI UGC batch production factory

Reusable skills, scripts, and production workflows for agent-led video creation with HyperFrames, FFmpeg, captions, audio sync, and render QA. Community project from real HyperFrames video work; not an official HyperFrames or HeyGen repository.