· 3 days ago· Dev.to
Revolutionizing product photography with semantic caching in VLM process
TL;DR: We put Bifrost in front of the VLM step that captions and rewrites prompts for our product-photo diffusion pipeline. Semantic caching cut that bill by ~62% in three weeks. The diffusion side, where the GPUs live, was never the cost we should have been worrying about. Our pipeline at Photoroom
#cloud-computing#semantic-caching#product-photography#diffusion-models