Open-source alternative to AI video platforms — Free AI image & video generation studio with 200+ models (Flux, Midjourney, Kling, Sora, Veo). No content filters. Self-hosted, MIT licensed.

Light Image Video Generation Inference Framework

[ICML 2026] Official codebase for "Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation" & Causal Forcing++

rCM & Causal-rCM: Best Algorithms/Infrastructures for Bidirectional/Autoregressive Video Diffusion Distillation at Scale

Reinforcement Learning Framework for Visual Generation

ComfyUI workflows to create smooth transitions between video clips using Wan VACE. Works with video from any model or other source-LTX-2, drone footage, stock video, personal recordings, etc.

ComfyUI nodes designed to help make common video editing tasks with Wan VACE less complicated. Smooth transitions, extensions, outpainting.

Session-scoped Claude Code agent for ComfyUI video production — 12 specialized skills for image gen, video, voice cloning, LoRA training, and publishing

KsanaDiT: High-Performance DiT (Diffusion Transformer) Inference Framework for Video & Image Generation

This allows you to utilize Google Colab (or other notebooks) to run wan2.2 image to video

Accelerate Video Diffusion Inference via Sketching-Rendering Cooperation

Custom tool set mostly for Hunyuan Video, but includes some WAN and FramePack Video nodes.

Avernus API server and client for LLM, SDXL, FLUX, Qwen-Image, WAN, and Ace-Step inference and many other architectures.

⚡️ Generate light video content effortlessly with LightX2V, a streamlined framework for fast and efficient video generation and inference.

🎥 Generate videos from images effortlessly with the Wan 2.2 Google Colab template, featuring one-click setup and optimized workflows for free GPU use.

AI Art Generator is a high-performance tool for instant high-fidelity image creation. It features elite neural models and granular style control for professional-grade visual storytelling.

🎨 Build and train reinforcement learning models for advanced visual content generation with a scalable, modular framework.

Build PackForcing for long video sampling and long-context inference with short video training and benchmark code