Blog

Runpod Blog

Our team’s insights on building better and scaling smarter.
All
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
The Effects of Rank, Epochs, and Learning Rate on Training Textual LoRAs

The Effects of Rank, Epochs, and Learning Rate on Training Textual LoRAs

Learn how rank, learning rate, and training epochs impact the output of textual LoRAs—and how to balance these settings for coherent, stylistically faithful results.
Read article
AI Workloads
Runpod RoundUp 3 – AI Music and Stock Sound Effect Creation

Runpod RoundUp 3 – AI Music and Stock Sound Effect Creation

This week’s Runpod RoundUp highlights Meta’s Audiocraft for AI-generated music and sound effects, new Chinese LLMs from Alibaba, and Salesforce’s DialogStudio dataset hub for building conversational AI.
Read article
AI Workloads
Runpod RoundUp 2 – 32k Token Context LLMs and New StabilityAI Offerings

Runpod RoundUp 2 – 32k Token Context LLMs and New StabilityAI Offerings

This week’s Runpod RoundUp covers major releases including Llama-2 with 32k context support, SDXL 1.0’s public release, and StabilityAI’s new Stable Beluga LLMs—all now available to run on Runpod.
Read article
AI Workloads
Stable Diffusion XL 1.0 Released And Available On Runpod

Stable Diffusion XL 1.0 Released And Available On Runpod

Stable Diffusion XL 1.0 is now live on Runpod with full support in the Fast Stable Diffusion template. Users can generate higher-resolution, more anatomically accurate, and text-capable images with simplified prompts using AUTOMATIC1111 via a streamlined Jupyter setup.
Read article
AI Workloads
RunPod Partners With OpenCV to Empower the Next Gen of AI Builders

RunPod Partners With OpenCV to Empower the Next Gen of AI Builders

RunPod has teamed up with OpenCV to provide free GPU access for students building the future of computer vision. Learn how the partnership works and who it supports.
Read article
AI Workloads
Meta and Microsoft Release Llama 2 as Open Source

Meta and Microsoft Release Llama 2 as Open Source

Llama 2 is now open source, offering a native 4k context window and strong performance. This post walks through how to download it from Meta or use TheBloke’s quantized versions.
Read article
Hardware & Trends
Runpod Roundup: High-Context LLMs, SDXL, and Llama 2

Runpod Roundup: High-Context LLMs, SDXL, and Llama 2

This Runpod Roundup covers the arrival of 8k–16k token context models, the release of Stable Diffusion XL, and the launch of Llama 2 by Meta and Microsoft. All are now available to run on Runpod.
Read article
Hardware & Trends

Build what’s next.

The most cost-effective platform for building, training, and scaling machine learning models—ready when you are.