vibe-knowledge: a Claude Code skill for sourced explainers
vibe-knowledge is a Claude Code skill for sourced explainers: fact checks, narration and 1080p60 rendering, with optional Renoise credits for selected shots.
Published entries across all sections carrying the “Video generation” tag, newest first by publication date on this site.
47 entries
vibe-knowledge is a Claude Code skill for sourced explainers: fact checks, narration and 1080p60 rendering, with optional Renoise credits for selected shots.
threerocks' MIT-licensed Agent Skill turns an article or topic into a narrated hand-drawn explainer: storyboard timed to the voice, strokes drawn in order.
Wired’s Nov 8 report maps the world-model field: models that simulate physics for robotics, self-driving and games, and LeCun’s startup past $1B raised.
Google shipped Gemini Omni 1.2 Flash on November 5: clips stretch from 10 to 15 seconds, 720p video costs $0.07 per second, and it is generally available.
Vincentwei1021's MG library: fifteen motion-design styles, one 10-second film each, all written as code by Claude Opus 5.5, prompts and source included. MIT.
Lanshu's agent skill runs the full presenter-video line — script, voice, digital human, lip-sync, render, QA — plus a 12-style route. MIT, 2,924 stars.
An open-source agent skill turning Chinese stories into 3:4 hand-drawn flipbook MP4s — 327 style assets, hand-written text in the art, Remotion rendering, MIT.
Genie 4, DeepMind's new real-time world model: native audio, mid-session text edits, Gemini 3.8 Flash in the loop — research preview now, Project Genie next.
Grok Imagine posted the first seven minutes of its AI Odyssey on October 23. The full-length promise became a series; TechCrunch calls it "completely airless".
Deep-Live-Cam is an AGPL-3.0 real-time face swap tool driven by a single photo, with an ethics statement and content checks in the README. Consent required.
Lemo-Opuscar is an MIT-licensed film-style toolbox: 59 ready styles where Claude draws frames with canvas and WebGL and cuts with ffmpeg, no video model.
StreamEval is an Apache-2.0 benchmark for interactive streaming video: five tasks, 300 cases and 15–300 second sessions, with prompts and code public.
SuperCMO Skills is Apache-2.0: 23 marketing skills plus a local MCP server that turn a product photo and a brief into UGC or ad videos, with your own keys.
fal launched FLUX 3 Max on October 19: 720p at a promotional $0.0425 per second through November 7 (list $0.17), and an independent board ranks it second.
EdenLive, from VAST, renders gray-box video into detailed frames in real time for game prototypes. Code is Apache-2.0; weight licenses vary.
Murea Labs released InWorld on Oct 17: a 42 GB 8-step Murea-Fast users can download, while WBench's top row is an unreleased 50-step Murea-Pro.
huashu-motion is an MIT agent skill: one sentence becomes a launch film written as code, scored locally, and editable by pointing at a frame.
13 installable agent skills cover the shoppable-short-video pipeline, and the final cut is rendered locally with ffmpeg — no API key anywhere.
An ECC skill with one rule — define the core relationship, split it into scenes, render the smallest cut — Manim explainers where the animation argues.
Kuaishou put Kling 4.0 into full release on October 15: 30-second native generations, up to 10 keyframes, 8,000-token prompts, and no API yet.
ManimGX keeps the Manim CE Python API but renders on Rust and wgpu: 36.2 seconds of video in 3.08 seconds, 90.6x faster than ManimCE per its benchmark.
ComfyUI exposes every step of a diffusion pipeline as nodes: models, samplers and parameters all adjustable, with the largest open models runnable on 4GB VRAM.
animate is a Claude Code skill that draws short videos in canvas code, renders one MP4, and ships seven built-in art styles — no video model in the loop.
brag is an open-source agent skill from latent-spaces: one command reads your project and renders a 20-second launch video with music, motion and share copy.
From $6,000 agency quotes to $19 a video to free open source: the seven-layer market for product launch videos, and the new code-rendered branch inside it.
An open-source agent skill by Huashu packing 35 art style recipes and 9 explainer grammars to generate frame-accurate Canvas animations with code.
video-shotcraft is a skill that turns Claude Code into a product-video studio: 157 shot recipe cards, a validated Remotion template, sound design included.
Digital Samba's MIT toolkit has Claude Code script, voice, score and render videos with Remotion; the AI models run on your own Modal or RunPod GPU.
hypit-ai's open-source video skill: give your agent a reference clip and it rebuilds the captions, B-roll and effects as an editable, re-runnable project.
MoneyPrinterTurbo is an open-source AI video generator: give it a topic and it writes the script, matches footage, adds voiceover and renders a 1080p cut. MIT.
NarratorAI's official skill: your agent runs narrator-ai-cli from search to render, voice cloning included, asking at each step. Needs an API key and credits.
openstoryline-use, from FireRedTeam, has Claude Code or OpenClaw start the local OpenStoryline service, edit video by chat and revise it across turns.
We read the ten most-starred video skills. Stars belong to the whole repo, so pick by what the skill outputs. Includes a picker and the real limits of each.
Tavus unveiled Griffin on Oct 1, a full-duplex video-to-video model; 26 of 54 testers took it for a person after a one-minute call. Preview only.
Pixelle-Video is Alibaba's open-source AI engine that turns a topic into a finished short video: script, visuals, voiceover and music in one run. Apache-2.0.
LiveTalking by lipku is a real-time streaming digital human: synced audio-video, interruptible speech, multi-session, low-latency WebRTC, Apache-2.0.
Meituan's LongCat team open-sourced a model that turns one photo and one audio track into a talking video — Whisper lip sync, 8-step distillation, MIT.
HeyGen turns a clip of you into a lip-synced AI avatar for videos in 175+ languages. Free: 3 videos a month, 1 minute each, watermarked. Paid starts at $29/mo.
OpenMontage turns your AI coding assistant into a video studio: 12 pipelines, a storyboard approval gate with per-asset cost, free without any API key.
Anthropic never advertised video for Opus 5.5. Within a week users made it a category: 1,401 videos, four public bills, one fight over whether it is video.
geeklee's MIT agent skill turns SRT subtitles into whiteboard animation: 25–35 s scenes, strokes synced to the narration, built for explainer videos.
AiToEarn is an open-source AI agent that publishes your content to 14 platforms, auto-replies to comments, and settles brand deals — via web, MCP, or Docker.
Open-source SparkDiffusion pushes 720P-14B video generation to 265x on one RTX 5090 via sparse attention, distillation and FP8; VBench-2.0 drops 0.5 points.
html-explainer is an open-source Agent Skill for Claude Code, Codex and other coding agents: give it a topic and it runs research, narration, voiceover, subtitles, frame-by-frame rendering and covers end to end, producing a hard-subtitled MP4. Scenes are written in HTML/CSS/GSAP and rendered with a deterministic seek renderer, so audio and animation stay locked in sync. The default edge-tts voiceover is free and everything runs locally.
A copy-ready motion showreel prompt: an identity challenge with time-driven hard constraints. We ran it on GLM-5.3; coding models like Opus 5.5 take it well.
Skillry's gallery has 389 viral Claude Opus 5.5 videos with original prompts and the site's own remakes; the most reused is a one-line showreel challenge.
The open-source tool Story-Flicks takes nothing but a story theme and automatically produces a complete short video with AI illustrations, narration, and subtitles; the text model can connect to DeepSeek, Alibaba Cloud, OpenAI, and other providers, with one-command Docker deployment and multi-language output.