A python tool that uses GPT-4, FFmpeg, and OpenCV to automatically analyze videos, extract the most interesting sections, and crop them for an improved viewing experience.

[CSUR] A Survey on Video Diffusion Models

Generate video from text using AI

Codes for ID-Specific Video Customized Diffusion

Video Diffusion Alignment via Reward Gradients. We improve a variety of video diffusion models such as VideoCrafter, OpenSora, ModelScope and StableVideoDiffusion by finetuning them using various reward models such as HPS, PickScore, VideoMAE, VJEPA, YOLO, Aesthetics etc.

[SIGGRAPH Asia 2025] WorldExplorer: Towards Generating Fully Navigable 3D Scenes

[CVPR 2024 Highlight] ViVid-1-to-3: Novel View Synthesis with Video Diffusion Models

[CVPR 2025] Official code for Using Diffusion Priors for Video Amodal Segmentation

[NeurIPS 2024] Motion Consistency Model: Accelerating Video Diffusion with Disentangled Motion-Appearance Distillation

This is the project for 'Any2Caption', Interpreting Any Condition to Caption for Controllable Video Generation

[3DV 2025] MotionDreamer: Exploring Semantic Video Diffusion features for Zero-Shot 3D Mesh Animation

Text to Video API generation documentation

Track Anything Behind Everything: Zero-Shot Amodal Video Object Segmentation

📹 Generate automated, engaging YouTube Shorts and TikToks from a single topic with scriptwriting, voiceovers, and video editing—all in one pipeline.

Open-source, self-hosted video platform (Mux alternative). Upload, transcode to multi-quality HLS (360p–4K), stream via S3-compatible storage. Built-in dashboard, analytics, AI transcription/chapters, comments, team management & optional Stripe billing. Single Docker image, zero external deps.

A curated and auto-updated collection of video diffusion / video generation papers from arXiv, covering text-to-video, image-to-video, controllable generation, world models, video editing, and 16+ research categories.

WebUI for the FastVideo

🎶 Replace YouTube channel audio with custom generator sounds, target multiple channels, and enjoy a seamless listening experience while browsing videos.

🎥 Generate cinematic videos from text prompts 100% offline with OpenSora, empowering creators and researchers without relying on cloud services.