Video generation

OpenMontage is an open-source, agentic video production system that automates end-to-end video creation from natural language prompts—handling...

html-video converts HTML/CSS into animated MP4 videos programmatically, designed for AI coding agents to generate video content from web articles,...

YouTube Automation Agent is a complete, ready-to-use platform that automates YouTube channel management end-to-end using AI agents—from content...

Pixelle-Video is an end-to-end AI video generation platform that automates short-form video creation from a text topic, handling scriptwriting,...

This is a curated collection of 2000+ video generation prompts specifically designed for ByteDance's Seedance 2.0 AI video platform, covering...

ArcReel is an open-source AI video generation workbench that automates the pipeline from narrative text to finished video, using AI Agents to...

LingBot-World is an open-source world model for video generation and simulation that produces high-fidelity, interactive environments with...

A curated collection of 50+ open-source generative AI applications—including image generators, video tools, virtual try-ons, and SaaS...

A specialized toolkit that provides AI agents (Claude, Cursor, Gemini) with skills to generate, edit, and display professional-grade images, videos,...

Toonflow is an open-source desktop application that converts novels and scripts into animated short-form videos using AI-powered tools for...

ViMax is an end-to-end agentic AI system for video generation that automates the entire creative pipeline—scriptwriting, storyboarding, character...

PrintFilm is an AI-powered end-to-end platform for generating short dramas, motion comics, and animated storyboards from text scripts. It specializes...

vLLM-Omni is a framework for efficient serving of multimodal and omni-modality models (supporting text, audio, image, video, and world models) built...

Helios is a real-time long video generation model achieving minute-scale video synthesis at 19.5 FPS on a single H100 GPU without relying on...

waoowaoo is an industrial-grade AI platform for automating video and short-drama production workflows, converting novel text into storyboards,...

LightX2V is a lightweight inference framework for image and video generation supporting multiple state-of-the-art models (LTX, Wan, Qwen, etc.)...

HunyuanVideo is a large-scale framework for text-to-video generation using diffusion transformers, developed by Tencent. It serves researchers and...

LongLive 2.0 is a specialized infrastructure for generating long-duration videos using NVIDIA's FP4 quantization and parallel training/inference...

TurboDiffusion is a video generation acceleration framework that speeds up diffusion-based video synthesis by 100–200× on high-end GPUs while...

FastVideo is a unified framework for accelerated video generation that combines post-training and real-time inference optimization. It serves...

SANA is a specialized research framework for efficient high-resolution image and video generation using linear diffusion transformers, developed by...

muapi-cli is the official command-line interface for muapi.ai, enabling users to generate images, videos, and audio from the terminal using 14...

SageAttention is a specialized CUDA library implementing quantized attention mechanisms (8-bit, FP8, and FP4 variants) that accelerates inference for...

Wan2.2 is an open-source large-scale video generative model that generates videos from text and images using advanced diffusion techniques. It serves...

Bernini is a unified framework for video generation and editing that combines a multimodal language model-based semantic planner with a diffusion...

Video Podcast Maker is an automated pipeline that generates professional 4K video podcasts from topics, combining research, script generation,...

MAGI-1 is an autoregressive video generation model designed to scale video synthesis tasks. It combines autoregressive and diffusion-based approaches...

Lance is a 3-billion-parameter unified multimodal model developed by ByteDance for image and video understanding, generation, and editing tasks. It...

VideoClaw is an AI director system for automated end-to-end creative video production, transforming ideas into complete films through a multi-stage...

SpargeAttn is a training-free sparse attention mechanism that accelerates inference for language models, vision transformers, and video generation...