Upload README.md with huggingface_hub

README.md

@@ -1,20 +1,32 @@
+---
+title: LoRA Preprocess UI
+emoji: 🧑‍🎨
+colorFrom: indigo
+colorTo: gray
+sdk: gradio
+sdk_version: 4.21.0
+python_version: "3.10"
+app_file: app.py
+pinned: false
+---
+
 # LoRA Preprocess UI (Gradio)
 
-One-click preprocessing UI for preparing face/body photos for LoRA fine-tuning:
-- Face detection & aligned crops
-- Background removal (u2netp)
-- Neutral face-only variant to reduce clothing/jewelry imprint
-- Optional Florence-2 captioning (set `FLORENCE_URL` and `FLORENCE_KEY`)
-- Outputs `captions.jsonl` plus clean/face-masked images
+Upload ~8 photos (selfies + body), get aligned/clean/face-neutral variants and `captions.jsonl` for LoRA fine-tuning.
+
+## Features
+- Face detection & aligned crops (OpenCV SSD)
+- Background removal (rembg u2netp)
+- Face-only neutralized variant to avoid memorizing clothes/jewelry
+- Optional Florence-2 captioning (set `FLORENCE_URL`, `FLORENCE_KEY` env vars)
+- Outputs saved under `outputs/preprocessed/` inside the container
 
-## How to run (locally)
+## Run locally
 ```
 pip install -r requirements.txt
 python3 app.py
 ```
 
-## Space env vars (optional)
-- `FLORENCE_URL` : endpoint accepting `POST /` with image file, returns JSON with `caption`
-- `FLORENCE_KEY` : bearer token for that endpoint
-
-Files are saved to `outputs/preprocessed/` inside the Space container.
+## Env vars (optional)
+- `FLORENCE_URL`: endpoint that returns JSON with `caption`/`text`
+- `FLORENCE_KEY`: bearer token for that endpoint