How to quickly clone your voice with TorToiSe Text-To-Speech
In this tutorial, we show how to clone voices with TorToise TTS, and discuss necessary steps to ensure ideal cloning takes place.
a year ago
James Skelton
James is an ML Engineer and Head of Engagement Marketing at Paperspace, who has spent 4 years as a Machine Learning marketing specialist. BSc in Psychology from University of St. Andrews, Scotland.
Stable Diffusion
public
Training a LoRA model for Stable Diffusion XL
In this tutorial, we go over training a LoRA model on Stable Diffusion XL using your own images.
a year ago
MusicGen: the most powerful, easy to use music generator running on Paperspace
This tutorial walks through the MusicGen demo and shows how to run it in a Gradient Notebook.
a year ago
LLaMA 2: A Model Overview and Tutorial
This tutorial shows how the LLaMA 2 model has improved upon the previous versions of LLaMa, and details how to run it using a Jupyter Notebook.
a year ago
DragDiffusion with Paperspace
In this blog post, we walk through the DragDiffusion project for image editing with Diffusion models. We also show how to run the project in a Gradient Notebook.
a year ago
Stable Diffusion XL with Paperspace
Follow this tutorial to run Stable Diffusion XL on a Gradient Notebook!
a year ago
Navigating the Large Language Model revolution with Paperspace
In this article, we attempt to navigate the rapidly expanding ecosystem of LLM's by identifying and explaining relevant key terms and upcoming models. We concluded by showing how to launch any HuggingFace Space, a popular host for LLMs, within Paperspace.
a year ago
Automatic image labeling for object detection datasets with Segment Anything and Dolly, part 2: AutoYOLO
This blog post covers the release of AutoYOLO, a new Gradio based application for automatically labeling images, training, and running inference with Ultralytics YOLOv8
2 years ago
Automatic image labeling for object detection datasets with Segment Anything and Dolly, part 1: Introduction to Segment Anything
In this blog post we take a look at the Segment Anything Model (SAM), and get a first look at our application that integrates SAM with Dolly v2 and YOLOv8 to enable a fully automated image detection pipeline.
2 years ago
