A recreation of Neuro-Sama originally created in 7 days.

Cook up amazing multimodal AI applications effortlessly with MiniCPM-o

A powerful data recovery utility for Linux with many advanced features based on Scott Dwyer's HDDSuperClone.

Newelle - Your Ultimate Virtual Assistant

Official Implementation of LaViDa: :A Large Diffusion Language Model for Multimodal Understanding

[ArXiv 2025] DiffusionVL: Translating Any Autoregressive Models into Diffusion Vision Language Models

Adaptive FNO transformer - official Pytorch implementation

Large Kernel Vision Mamba UNet for Medical Image Segmentation

Official code for ICCV 2025 paper, X2I: Seamless Integration of Multimodal Understanding into Diffusion Transformer via Attention Distillation

GLM-Image: Auto-regressive for Dense-knowledge and High-fidelity Image Generation.

[CVPR 2025] DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention

Dungeon procedural generator similar to whatabou's "One Page Dungeon"

[ICCV 2025] Enhancing spatial understanding in text-to-Image diffusion models

[NeurIPS 2024] The official code of "U-DiTs: Downsample Tokens in U-Shaped Diffusion Transformers"

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

LTX-Video Support for ComfyUI

Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.

Swiftly get tons of images from indexed tars on Huggingface

Hydra is a framework for elegantly configuring complex applications

Home Made Diffusion Models

Reflection Removal through Efficient Adaptation of Diffusion Transformers

Reference PyTorch implementation and models for DINOv3

Official PyTorch Implementation of "SVG-T2I: Scaling up Text-to-Image Latent Diffusion Model Without Variational Autoencoder".

[NeurIPS 2025 Oral]Infinity⭐️: Unified Spacetime AutoRegressive Modeling for Visual Generation

[NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". A…

GLM-4.6V/4.5V/4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning

A high-throughput and memory-efficient inference and serving engine for LLMs

verl: Volcano Engine Reinforcement Learning for LLMs

MoH: Multi-Head Attention as Mixture-of-Head Attention

D2 is a modern diagram scripting language that turns text to diagrams.