Open source. Open possibilities.

HunyuanVideo is an open-source large-scale text-to-video generation model framework by Tencent, featuring a unified image-video architecture, 3D VAE, and prompt rewriting capabilities.

Wan2.2 is an open-source large-scale video generation model suite supporting text-to-video, image-to-video, speech-to-video, and character animation tasks with MoE architecture and 720P output.

SANA is NVIDIA's open-source family of efficient diffusion models for high-resolution image and video generation, with training and inference code, linear attention, DC-AE compression and 4-bit deployment.

vos is an open programmatic video engine that treats video as a deterministic function of time, allowing for resolution-independent rendering and data-driven editing.

Duix.Avatar is an open-source AI digital human toolkit for offline video generation and avatar cloning, supporting text/voice-driven synthesis with multi-language support.

EncodeX is a cross-platform multimedia conversion tool that provides a modern desktop interface for FFmpeg, supporting video/audio conversion, cutting, and image compression.

CogVideoX is an open-source video generation model series supporting text-to-video, image-to-video, and video continuation tasks. It includes 2B and 5B parameter models with diffusers and SAT inference frameworks.

Y.A.W.N is a cross-platform digital audio workstation (DAW) inspired by Ableton Live, featuring session and arrangement views, VST3 hosting, and integrated AI audio tools.

ViMax is an agentic video creation framework that automates the pipeline from concept to finished video, handling scriptwriting, storyboarding, character consistency, and final assembly.

Sonder Editor is a timeline-based video editor for ComfyUI designed for iterative long-form generation, allowing users to arrange scenes, clips, and prompts within a node-graph workflow.

Toonflow is an open-source AI-powered short drama production platform that provides a complete workflow from novel import to video generation, featuring an infinite canvas editor and a three-layer Agent collaboration system.

Pixelle-Video is an AI-powered automatic short video generation engine that creates videos from a single theme, including scripts, images, voiceovers, and background music, supporting multiple AI models and workflows.

Velo AI Studio is an open-source, browser-based video creation tool designed to assemble narrated videos from scripts, audio, and AI-generated visual assets.

bili_add_on is a command-line tool for overlaying Bilibili danmaku on videos. It supports automatic danmaku retrieval via video IDs or local XML files and provides hardware-accelerated encoding support.

OpenMontage is an open-source, agentic video production system that transforms AI coding assistants into full video studios, supporting end-to-end pipelines from research to final render.

LivePortrait is an open-source PyTorch implementation for efficient portrait animation, supporting humans, cats and dogs. It offers image and video driven modes, stitching and retargeting control, motion templates, a Gradio interface, and pretrained weights.