Baseten Blog | Page 9
SDXL inference in under 2 seconds: the ultimate guide to Stable Diffusion optimization
SDXL 1.0 initially takes 8-10 seconds for a 1024x1024px image on A100 GPU. Learn how to reduce this to just 1.92 seconds on the same hardware.
Build your own open-source ChatGPT with Llama 2 and Chainlit
Llama 2 rivals GPT-3.5 in quality and powers ChatGPT. Chainlit helps build ChatGPT-like interfaces. This guide shows creating such interfaces with Llama 2.
AudioGen: deploy and build today!
AudioGen, part of the AudioCraft family of models from Meta AI, is now available in the Baseten model library.
New in July 2023
Llama 2 and SDXL shake up foundation model leaderboards (plus: Langchain, autoscaling, and more)
AI infrastructure: build vs. buy
AI infrastructure, ML infrastructure, build vs. buy, model deployment
Build a chatbot with Llama 2 and LangChain
Build a ChatGPT-style chatbot with open-source Llama 2 and LangChain in a Python notebook.
Deploying and using Stable Diffusion XL 1.0
Deploy Stable Diffusion XL 1.0 for free to generate images from text prompts and invoke Stable Diffusion with the Baseten Python client.
Models We Love: July 2023
Explore open source foundation models: Llama 2 (Meta/Microsoft), FreeWilly1/2, SDXL 1.0 (Stability AI), LayoutLM (Inspira), NSQL 350M (Number Station).
Model autoscaling features on Baseten
Scale replica count up and down in response to traffic, with scale to zero and fast cold starts.
