Stars
Refine high-quality datasets and visual AI models
NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Retrieval and Retrieval-augmented LLMs
Teams-first Multi-agent orchestration for Claude Code
AI agents running research on single-GPU nanochat training automatically
A Library for Advanced Deep Time Series Models for General Time Series Analysis.
The official implementation of the paper titled "StableV2V: Stablizing Shape Consistency in Video-to-Video Editing".
HunyuanVideo GP: Large Video Generation Model - GPU Poor version
Implementation of ColorizeDiffusion
A Unified Toolkit for Deep Learning Based Document Image Analysis
A user-friendly plug-in that makes it easy to generate stable diffusion images inside Photoshop using either Automatic or ComfyUI as a backend.
Create transparent image with Diffusers!
Implementation of layer diffuse inference using refiners
SCEPTER is an open-source framework used for training, fine-tuning, and inference with generative models.
[WIP] Layer Diffusion for WebUI (via Forge)
This repository contains demos I made with the Transformers library by HuggingFace.
[ECCV'2024] Gaussian Grouping for open-world Anything reconstruction, segmentation and editing.
[ICLR 2025] Official implementation of MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance
[EMNLP2024 Demo], [ICASSP 2025], [ICASSP 2026] A user-friendly library for reproducible video moment retrieval and highlight detection. It also supports audio moment retrieval.
[ICLR 2025] CatVTON is a simple and efficient virtual try-on diffusion model with 1) Lightweight Network (899.06M parameters totally), 2) Parameter-Efficient Training (49.57M parameters trainable) …
text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)
[CVPR 2024] code release for "DiffusionLight: Light Probes for Free by Painting a Chrome Ball"
LayerDiffuse in pure diffusers without any GUI
[ECCV 2024] InstructIR: High-Quality Image Restoration Following Human Instructions https://huggingface.co/spaces/marcosv/InstructIR