RunPod Blog

Groundbreaking H100 NVidia GPUs Now Available On RunPod

The demand for generative AI models continues to explode, as does the need for hardware capable of harnessing their ever-escalating performance requirements. While consumer-grade GPUs typically used for gaming are great for learning, tinkering, or hobbyist pursuits, as noted in our previous blog the computational demands can quickly outstrip the

Introducing our Faster-Whisper Serverless Endpoint

You read the title! Whisper just got faster with RunPod's new Faster-Whisper serverless endpoint. What is Whisper? For those who haven't used it before, Whisper is an AI speech recognition model trained on hundreds of thousands of hours of multilingual human speech. It's great for audio captioning (things like podcasts,

How To Remix Your Artwork with ControlNet And Stable Diffusion

While you're undoubtedly familiar with the functions that Stable Diffusion includes that lets you derive images using other images such as input (img2img) you may find there's a certain level of being at the mercy of the model and simply constantly reiterating until you get something close to what you

Creating a Vlad Diffusion Template for RunPod

The default Pod templates and models are pretty cool (if we say so ourselves), but play with them for too long and you'll start to get used to them. If you're looking for something new and exciting again, it might be time to create a new custom template. Here, I'll

Text Generation

How to Work With Long Term Memory In Oobabooga and Text Generation

As fun as text generation is, there is regrettably a major limitation in that currently Oobabooga can only comprehend 2048 tokens worth of context, due to the exponential amount of compute required for each additional token considered. This context consists of everything provided on the Character tab, along with as

Audio

How to Create Convincing Human Voices With Bark AI

The Bark AI model is an innovative technology that can be used to generate realistic human voices. This technology takes advantage of the latest advancements in natural language processing, deep learning, and voice synthesis. By combining these technologies, it is able to accurately replicate the nuances and inflections of real

News

Run huggingface spaces on RunPod!

You can run any Huggingface space on Runpod! As every Huggingface space has options to run it with docker now this gives the option of running the space locally, which we can use to run the image with runpod here, 1. 7860 is the port being forwarded here in the

Art

Reduce Your Serverless Automatic1111 Start Time

I've found that many users are using the Automatic1111 stable diffusion repo not only as a GUI interface, but as an API layer. If you're trying to scale a service on top of A1111, shaving off a few seconds from your start time can be really important. If you need

Text Generation

Pygmalion-7b from PygmalionAI has been released, and it's amazing

Last month, the latest iteration of the Pygmalion model was released. Although it is not that much larger as it is still only a 7b model compared to the commonly used 6b version, what it does with that parameter space has also been improved by leaps and bounds, especially with

Art

Kohya LoRA on RunPod

Our good friend SECourses has made some amazing videos showcasing how to run various genative art projects on RunPod. His latest video, titled "Kohya LoRA on RunPod", is a great introduction on how to get into using the powerful technique of LoRA (Low Rank Adaptation). Here's the paper if you're

Stable Diffusion

Use DeepFloyd To Create Actual English Text Within AI!

If you've ever tried to generate text in images in packages like Stable Diffusion, you're probably familiar with the positively haunting facsimile of language it manages to produce. It looks so much like it could be a real language, and ultimately manages to be gibberish - something like you might

Stable Diffusion

Creating an Animated GIF from an Existing Image with the RunPod Stable Diffusion Template

Many of you have probably seen this tutorial for creating a GIF image from a still artwork. Wondering how to do it with RunPod? Here's how! Following similar steps, I've used our Stable Diffusion template to animate the river for this still image, but the possibilities are endless. Let's get

Stable Diffusion

Using Stable Diffusion Scripts and Extensions

Looking to "extend" the functionality of your Stable Diffusion instance? Look no further! This guide will show you how to install and use custom scripts and extensions with our Stable Diffusion endpoint. I'll assume you already have a Pod instance with the Stable Diffusion template; if you don't and need

Releases Featured

The New and Improved RunPod Login Experience

Today we've rolled out a huge improvement to how login works at RunPod. In the process, we've introduced some new features that many of you have been asking for. A few things to note: 1) First and foremost, if you had a password on your normal username/password type account,

Animation

Upscaling videos using VSGAN and TensorRT

In today's increasingly digital age, enhancing video quality has become more important than ever. With the help of VSGAN, a repository dedicated to super resolution models and video frame interpolation, we aim to achieve the fastest inference possible while maintaining high-quality results. Before diving into this guide, it's essential to

Art

Guide to Using the Kohya_ss Template with Runpod

Introduction: In this post, we will discuss the process of utilizing the Kohya_ss template with Runpod. The Kohya_ss template is designed for desktop CUDA and supports applications like Kohya_ss. We will provide a step-by-step guide to help you get started. It is recommended to use the NVIDIA

News

Four Reasons To Set Up A Network Volume In the RunPod Secure Cloud

Network Storage is a new RunPod feature (currently in beta) that works with our Secure Cloud data center-hosted pods. Normally, volumes for pods are destroyed irrecoverably after you terminate the pod, but this allows storage to persist and even be reassigned to different pods if needed. Here are several reasons

News

Ada Architecture Pods Are Here - How Do They Stack Up Against Ampere?

The Ada architecture is the latest architecture developed by Nvidia that is capable of achieving vastly improved performance on AI and HPC workloads compared to previous Nvidia GPU architectures. Ada also comes equipped with a new generation of Tensor Cores, which greatly accelerate matrix operations commonly used in deep learning

Text Generation

The Beginner's Guide to Textual Worldbuilding With Oobabooga and Pygmalion

Pygmalion is an unfiltered chatbot AI model that you can interact with to ask questions, talk to for fun, or even roleplay with. One of the best parts about Pygmalion is that it is capable of "learning" over time in that it will refer to its available output and incorporate

Stable Diffusion

Unveiling Kandinsky 2.1: The Revolutionary AI-Powered Art Generator

Introduction: Artificial intelligence is transforming the world of digital art, and we at RunPod.io are excited to introduce the latest AI masterpiece, Kandinsky 2.1! This powerful model inherits the best practices from Dall-E 2 and Latent Diffusion while introducing innovative ideas to push the boundaries of AI-generated art.

News

Spin up a Text Generation Pod with Vicuna And Experience a GPT-4 Rival

Why use Vicuna? The primary benefit of Vicuna is that it has a level of performance rivaled only by ChatGPT and Google Bard. The model has been tested across a wide variety of scenarios, including Fermi problems, roleplay scenarios, and math tasks, and a framework graded by GPT-4 showed that

Stable Diffusion

Using OpenPose to Annotate Poses Within Stable Diffusion

Describing poses in a text prompt, other than the most basic notation, can often feel like an exercise in frustration. "Sitting in an office chair" isn't too hard to work with, but when it comes to accurately describing things like raising arms in certain directions and proportions, leg positioning, and

Stable Diffusion

Why Altering the Resolution in Stable Diffusion Gives Strange Results

Stable Diffusion was originally designed to create images that are exactly 512 by 512. It does let you create images that are up to 2048 by 2048 (GPU resources permitting). However, when you try, you are very likely to get results that appear to be fighting against your prompt. Why

Art

Hybridize Images With Image Mixer Before Running Through img2img

Stable Diffusion has a powerful feature (img2img) that allows you to generate images using another image as a prompt. However, it has a weakness in that you can only supply a single image to use in that prompt – so if you want to include facets of a group of images,

Runpod Platform

Avoid Errors By Selecting The Proper Resources For Your Pod

RunPod instances are billed at a rate commensurate with the resources given to them. Naturally, an A100 requires more infrastructure to power and support it than, say, an RTX 3070, which explains why the A100 is at a premium in comparison. While the speed of training and using models is