Private Preview
Access AWS Inferentia2 on OctoAI
What will you build using the world’s fastest Stable Diffusion 2.1 and AWS Inferentia2 ?
World’s Fastest Stable Diffusion + AWS Inferentia2
AWS Inferentia2 is the latest addition to OctoAI’s list of supported hardware targets.
OctoAI provides customers a library of the fastest open source software (OSS) foundation models, and multiple tiers of hardware targets on which to run generative AI models. The addition of AWS Inferentia2 increases price-performance flexibility for models like Stable Diffusion, bringing developers more choice and optionality as they run generative AI applications.