Upload README.md with huggingface_hub

README.md

@@ -30,14 +30,12 @@ For a production Hugging Face Space, use GPU hardware and set:
 
 ```text
 SYNLAYERS_MODEL_REPO=SynLayers/Bbox-caption-8b
-SYNLAYERS_BASE_MODEL=black-forest-labs/FLUX.1-dev
 ```
 
 This lets the Space:
 
-- load the bbox detector from your uploaded model repo
-- load the SynLayers adapter, LoRA, transparent VAE, and `step_120000` checkpoint from your uploaded repo
-- use the official Hugging Face FLUX base model instead of re-downloading your own uploaded copy
+- load the bbox detector from your uploaded model repo root
+- load SynLayers Pipeline
 
 ## Local Run