Malnyun Faces alternatives for AI agents.

Bernini is a unified framework for video generation and editing that combines an MLLM-based semantic planner with a DiT-based renderer.

Seamlessly extend any image in any direction with AI. Open-source web app powered by Gemini via OpenRouter, with Poisson-blended seams and best-of-3 variant picker.

Bring portraits to life!

"ViMax: Agentic Video Generation (Director, Screenwriter, Producer, and Video Generator All-in-One)"

Wan: Open and Advanced Large-Scale Video Generative Models

🚀 AI 全自动短视频引擎 | AI Fully Automated Short Video Engine

Advancing Open-source World Models

[CVPR 2026] PersonaLive! : Expressive Portrait Image Animation for Live Streaming

TensorFlow Implementation of Unsupervised Cross-Domain Image Generation

HunyuanVideo: A Systematic Framework For Large Video Generation Model

Official PyTorch implementation for the paper High-Resolution Virtual Try-On with Misalignment and Occlusion-Handled Conditions (ECCV 2022).

HunyuanVideo-1.5: A leading lightweight video generation model

PHP library allowing thumbnail, snapshot or PDF generation from a url or a html page. Wrapper for wkhtmltopdf/wkhtmltoimage

VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models

[ICLR 2026] A Training-free Iterative Framework for Long Story Visualization

Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the future state of the world in the form of video.