Upload README.md with huggingface_hub

README.md

@@ -7,8 +7,11 @@ sdk: gradio
 python_version: "3.10"
 app_file: app.py
 suggested_hardware: a100-large
+startup_duration_timeout: 2h
+short_description: "GPU Space for SynLayers real-world layer decomposition"
 models:
   - SynLayers/Bbox-caption-8b
+  - black-forest-labs/FLUX.1-dev
 pinned: false
 ---
 
@@ -21,6 +24,21 @@ This folder now contains a unified real-world inference demo:
 3. `demo/real_world_pipeline.py` stitches the two stages together for one uploaded image.
 4. `demo/app.py` provides a Gradio interface that can be used locally or adapted for a Hugging Face Space.
 
+## Full GPU Space
+
+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
+
 ## Local Run
 
 From the `SynLayers` root: