Deploy Stable Diffusion XL (SDXL) Inference on SaladCloud | GPU | Salad Portal
In this video, Bob Miles - CEO at Salad, shows how to deploy Stable Diffusion XL (SDXL) across consumer GPUs like the RTX 3090 & 4090 on SaladCloud.
Serving inference at scale for GPU-hungry use cases like text-to-image or speech-to-text is expensive today.
AI-focused GPUs are expensive, hard-to-get and require long wait times or prepaid contracts.
Distributed clouds with consumer GPUs like SaladCloud can save more than 50% on your cloud cost for serving AI/ML inference at scale.
Learn more: https://salad.com
Try for yourself: https://portal.salad.com/
Get a Demo: https://salad.com/get-a-demo