initial commit

README.md

@@ -2,41 +2,3 @@
 #Stable Diffusion Xl Refiner 1.0
 
 Our goal is to generate high quality fashion items (with models) based on the prompt.
-
-###Steps (POC)
-- submit prompt on the UI to our AWS Lambda endpoint
-- take the prompt and feed to an LLM model to check if it's fashion related prompt.
-- If no, return an error.
-- if yes,
-  - increment distributed cache by 1. Return error when reaching 10 requests per hour. 
-  - feed the prompt to the HuggingFace Spaces endpoint
-- generate image, return image to the lambda 
-- save image in S3.
-- return image to the front-end
-- Any errors shown to the user, also show a subscription form to notify the user when we go live.
-
-What I need:
-- Serverless Framework
-- Fast API service unik-ml
-- Fast API service unik-huggingface-sd
-- S3 bucket
-- smallest distributed cache
-- Pulumi:
-  - Redis
-  - s3 bucket
-  - 
-
-emoji: 📈
-
-colorFrom: pink
-
-colorTo: gray
-
-sdk: docker
-
-pinned: false
-
-license: openrail
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference