Sayak Paul

End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 training).

Contains my explorations of TensorFlow 2.x

Probing the representations of Vision Transformers.

This project shows how to serve an ONNX-optimized image classification model as a web service with FastAPI, Docker, and Kubernetes.

Inference-time scaling of diffusion-based image and video generation models.

This repository contains notebooks that show the usage of TensorFlow Lite for quantizing deep neural networks.

PyTorch implementation of CLIP Maximum Mean Discrepancy (CMMD) for evaluating image generation models.

Just another reasonably minimal repo for class-conditional training of pixel-space diffusion transformers.

This repository implements the idea of "caption upsampling" from DALL-E 3 with Zephyr-7B and gathers results with SDXL.

Implementation of MAXIM in TensorFlow.