Stars
A latent text-to-image diffusion model
High-Resolution Image Synthesis with Latent Diffusion Models
Bringing stable diffusion models to web browsers. Everything runs inside the browser with no server support.
cluster data collected from production clusters in Alibaba for cluster management research
A PyTorch implementation of the paper "All are Worth Words: A ViT Backbone for Diffusion Models".
Large scale K-means and K-nn implementation on NVIDIA GPU / CUDA
Implementation of Paint-with-words with Stable Diffusion : method from eDiff-I that let you generate image from text-labeled segmentation map.
Source code and datasets for Ekya, a system for continuous learning on the edge.
The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS 2025]
A demo for mapping class labels from ImageNet to COCO.