ClipForge is an open‑source AI tool that turns a single product image (or a short text prompt) into a ready‑to‑publish short video for Douyin, Kuaishou, Xiaohongshu, TikTok, etc. It automates script writing, storyboard creation, image‑to‑video synthesis, TTS, subtitles, BGM, and final FFmpeg stitching. Two tracks exist – a completely free path using public assets and Edge TTS, and a paid AI‑generation path that charges per second of generated content. Features include director vs. beginner modes, cross‑shot consistency, selective re‑generation, a 391‑template library, hot‑topic auto‑generation, batch production, built‑in compliance (AIGC labeling, ad‑law word scanning), CLI/MCP/agent integration, and an AGPL‑3.0 license. Ideal for e‑commerce sellers, marketers, creators, and developers who need fast, low‑cost product videos.

AI Story is a Docker‑based web app that automates the whole pipeline from a story prompt to a finished short video, using multiple AI models for script writing, storyboard creation, image generation, camera‑move planning, and video rendering.

A practical node suite for ComfyUI that simplifies MiniMax H3 video generation, offering unified media management and tools for creating long, coherent videos via context segments.

SparkVSR is an interactive video super-resolution framework that allows users to guide the restoration process using sparse high-quality keyframes to ensure better temporal consistency and controllable results.

An agent-first AI video production pipeline that replaces one-shot prompting with a governed workflow of planning, approval gates, and verified rendering.

A local web app that turns a silent face‑cam clip into a full talking‑head video using Alibaba Bailian VideoRetalk for lip‑sync, TTS from Bailian or Volcengine, optional DeepSeek script generation, and FFmpeg for final rendering.

A custom ComfyUI node set for Minimax H3 that provides neural latent upscaling and tiled re-sampling to accelerate high-resolution video generation while avoiding VAE round-trip overhead.

ComfyUI‑H3‑FaceRefine is a custom‑node pack for ComfyUI that fixes MiniMax H3’s poor rendering of small faces in video. It detects faces, crops them to a larger canvas, runs H3 on the crops, and stitches the refined faces back. Includes auto‑ and manual‑face‑selection modes, hard‑cut detection, per‑frame denoise, and ready‑to‑use example workflows.

Pireel Studio is an open-source AI video editor that lets users create videos using a combination of manual timeline editing, chat-based descriptions, and AI agents.

A ComfyUI extension for MiniMax H3 that enables seamless chaining of video and audio clips by using latent-based continuity to prevent quality loss and motion and sound jumps.

An agent-driven video editing pipeline that allows coding agents to transcribe, design, and render MP4 videos based on natural language descriptions.

An efficient portrait animation tool that animates static images of humans and animals using driving videos or images with precise stitching and retargeting control.

An Agent-driven video creation platform that integrates scriptwriting, storyboarding, and AI image/video generation into a unified workspace.

Timeline Studio is a browser‑only, local‑first AI video editor that runs on WebGPU/ONNX. It offers multilingual TTS, AI‑generated music, automatic captions, smart framing, watermark removal, vocal separation, and digital‑human avatars, all without uploading media. Projects are saved as portable `.timeline` files and can be edited via a rich UI or a head‑less CLI skill that lets LLM agents inspect, plan, and apply edits programmatically. The code is MIT‑licensed; model weights are mirrored on Hugging Face and ModelScope under their original licenses.

A free, open-source AI video generator that uses cloud APIs to create multi-scene videos with narration and subtitles, eliminating the need for expensive GPUs or subscriptions.

LTX Desktop is an open‑source Electron app for generating and editing videos (and images) with LTX diffusion models. It runs locally on NVIDIA GPUs (≥16 GB VRAM) or Apple‑silicon Macs (≥15 GB free RAM) using the LTX 2.5 Fast or 2.3 Fast models, and automatically switches to a paid cloud API (LTX 2.5/2.3 Pro) on unsupported hardware. Features include text‑/image‑/audio‑to‑video, video retake/extend, LoRA style adapters, prompt enhancement via Gemini, and a timeline‑based video editor. Installation is via a GitHub release installer; the app stores data in standard OS‑specific folders and requires a free LTX API key for cloud text encoding. The codebase (Apache‑2.0) is split into React UI, Electron shell, and a Python FastAPI backend, with full dev scripts for local building. Optional anonymous telemetry can be disabled.

SCAIL-2 is an open-source model for end-to-end character animation and replacement, removing the need for intermediate pose representations to support complex motions and diverse identities.

A conversational AI video creation tool that automates scriptwriting, media sourcing, and editing through natural language prompts.

Flow Kit is a Python‑FastAPI + Chrome‑extension system that automates end‑to‑end AI video creation via Google Flow, handling reference images for visual consistency, scene generation, TTS, up‑scaling, thumbnailing and YouTube upload.

An on-policy self-distillation framework for post-training few-step autoregressive video generators to reduce error accumulation and improve motion dynamics in long videos.

An open-source world simulator that generates high-fidelity, interactive video environments with real-time interactivity and long-term temporal consistency.

A video direction skill for Dreamina/Jimeng Seedance 2.5 that transforms creative ideas and reference images into structured video scripts and optimized prompts.

A meta-layer for turning text, articles, or GitHub repos into animated MP4 videos using local coding agents and pluggable HTML-based rendering engines.

HunyuanVideo is a large-scale open-source video foundation model with over 13 billion parameters that generates high-quality videos with superior motion and text alignment.

A curated library of AI video prompts and a Claude Code skill that turn any idea into a ready‑to‑run, multi‑shot prompt for 2026 text‑to‑video models. Includes genre templates, camera‑move libraries, negative‑prompt prefabs, a web‑based no‑install builder, and detailed docs on the 5‑stage prompt structure.

myAiVideos is an open‑source, Docker‑compose‑based system that automates the whole short‑video creation workflow (topic → script → visuals → audio → post‑production → distribution) for Chinese content. It uses a FastAPI orchestrator plus a Java Spring‑Boot gateway for auth, routing, circuit‑breaking and metering, and integrates multiple LLM and multimodal models (DeepSeek, GLM, Kling, TTS services). The pipeline is layered, fail‑over capable, and fully observable via Langfuse and Prometheus.

LightX2V is an open‑source inference framework for fast image and video generation (T2V, I2V, T2I, I2I, T2AV, etc.). It supports many state‑of‑the‑art models (MiniMax‑H3, Wan, HunyuanVideo, Qwen‑Image, etc.) and provides speed‑up techniques such as 4‑step distilled LoRAs, FP8/NVFP4 quantization, tensor/sequence parallelism, and disaggregated deployment on a wide range of hardware. Benchmarks show up to 3.9× faster inference than competing frameworks on H100 GPUs. The project offers Docker images, pip install, Gradio/ComfyUI front‑ends, extensive docs, and an online demo.

A collection of plug‑ins that let AI coding assistants (Codex, Claude Code, Grok Bot, Cursor) edit ChatCut video projects via natural‑language prompts—import media, add graphics, generate audio, transcribe, export, etc. Requires a ChatCut account and one of the supported hosts; authentication is handled through ChatCut’s MCP endpoint.

An open-source workbench for AI short drama and video production that manages the pipeline from scriptwriting and asset generation to final video synthesis.

A local deployment skill for MiniMax H3 that enables low-VRAM NVIDIA GPUs on Windows to generate videos with native audio via AI agents.

A local-first AI video creation workstation that automates the workflow from material analysis and scriptwriting to voiceover generation and audio-visual synchronization.

cs-board is a locally‑run AI video‑creation workstation that turns Chinese text, a reference audio clip, and optional style/character images into a fully‑rendered whiteboard‑style MP4. It handles voice cloning (via IndexTTS), script segmentation, AI‑generated illustrations, hand‑drawn animation, subtitles, and audio‑video sync, offering 12 visual templates, custom character/style support, dynamic infographics, and LAN‑based collaborative queues.

An AI-powered video recap system that transforms raw videos into narrated summaries by automating video understanding, scriptwriting, voiceover generation, and editing.

An open-source, AI-powered video clipping tool that converts long-form videos into viral vertical clips with automatic face-cropping, subtitles, and virality scoring.

An AI director system that automates the entire creative video production pipeline from scriptwriting and character design to storyboarding and final editing.

A 114B-parameter unified audio-video generation model that produces 1080p video clips with synchronized sound from text or image prompts.

A cross-platform GUI application for AI-powered video frame interpolation and upscaling, supporting multiple GPU backends and a variety of specialized models.

An all-in-one agentic framework for understanding, editing, and generating creative videos through natural language prompts.

FlashVSR is a one-step streaming diffusion framework for real-time video super-resolution that achieves high-speed upscaling and scalability to ultra-high resolutions.

A tool that turns short voiceover lines into editorial halftone paper-collage B-roll animations using a three-stage approval workflow and Gemini Omni Flash.

A set of open-source agent skills that automate the full video production pipeline, transforming text, images, or URLs into finished multi-shot videos with music and subtitles.

A tool for creating short vertical story videos by animating the transition from hand-drawn line art to colored images.

A collection of ComfyUI workflows for MiniMax H3 Director, enabling text-to-video, image-to-video, and advanced video-to-video editing with reference materials.

VBench is an open‑source benchmark suite that automatically evaluates video‑generation models across dozens of quality dimensions (technical, aesthetic, and trustworthiness). It includes prompt collections, metric pipelines, human‑aligned scores, and public leaderboards for T2V, I2V, long‑video, and intrinsic‑faithfulness evaluation.

An automated pipeline that transforms a topic into a professional 4K video podcast by integrating AI research, TTS audio, and Remotion-based video rendering.

Twinny is a free VS Code extension that adds AI‑driven code completion, an interactive chat sidebar, workspace‑wide context via embeddings, and optional P2P inference sharing. It works with many LLM providers (OpenAI, Anthropic, Mistral, etc.) and can run locally, offering customizable prompts and features like diff view, commit‑message generation, and offline operation.

An open-source AI video ad studio for creating realistic UGC vertical ads using multiple SOTA video models, designed as a self-hostable alternative to Arcads and MakeUGC.

director is an AI‑agent skill that guides a language model through the full video‑production pipeline—script, visual style, characters, voice, shot‑by‑shot prompts—and uses LibTV or 即梦 CLI tools to generate ready‑to‑edit video clips. It supports three modes (Animated Explainer, Storytime Animation, Cinematic Drama) and is installed as a skill directory for agents like Codex.