Dark Light Viewer - a tool to conduct change detection over time using VIIRS night lights data.

HunyuanVideo-I2V: A Customizable Image-to-Video Model based on HunyuanVideo

Advancing Open-source World Models

A fast AI Video Generator for the GPU Poor. Supports Wan 2.1/2.2, Qwen Image, Hunyuan Video, LTX Video and Flux.

HunyuanVideo GP: Large Video Generation Model - GPU Poor version

Qwen-Image-Layered: Layered Decomposition for Inherent Editablity

Additional non-node based UI for ComfyUI focused on inference. Stable UI states; presets; and advanced queue. Based on Gradio

Kimi K2 is the large language model series developed by Moonshot AI team

The new Dev Home experience for Windows!

Enabling the Windows Subsystem for Linux to include support for Wayland and X server related scenarios

Training and evaluating encoding models to predict fMRI brain responses to naturalistic video stimuli

Low-latency AI engine for mobile devices & wearables

The ultimate training toolkit for finetuning diffusion models

An extension for SwarmUI that adds Kohya Deep Shrink to the interface

The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.

Used for AI model generation, next-generation Blender rendering engine, texture enhancement&generation (based on ComfyUI)

A SOTA open-source image editing model, which aims to provide comparable performance against the closed-source models like GPT-4o and Gemini 2 Flash.

Official repository for LTX-Video

Lets make video diffusion practical!

Official PyTorch implementation of One-Minute Video Generation with Test-Time Training

A ComfyUI extension for chatting with your images with LLaVA. Runs locally, no external services, no filter.

ComfyUI Ollama integrates the Ollama API into the ComfyUI environment, enabling users to interact with various language models provided by Ollama.

Wan: Open and Advanced Large-Scale Video Generative Models

An extension for SwarmUI that allows you to connect to Ollama, OpenAI, and OpenRouter to use vision models for image analysis to create image prompts.

SkyReels V1: The first and most advanced open-source human-centric video foundation model