Add project walkthrough

2026-01-26 01:54:34 -07:00 · 2026-01-26 01:54:34 -07:00 · 713bda3bfa
commit 713bda3bfa
parent f330474208
1 changed files with 62 additions and 0 deletions
--- a/walkthrough.md
+++ b/walkthrough.md
@ -0,0 +1,62 @@
+# SDXL-Lightning Image Generation for macOS (MPS)
+
+We have successfully implemented a local image generation setup using SDXL-Lightning on macOS with Metal Performance Shaders (MPS) acceleration.
+
+## Features Status
+
+| Feature | Status | Notes |
+| :--- | :--- | :--- |
+| **Generation Script** | ✅ Complete | `generate.py` supports text-to-image with custom resolution |
+| **Model** | ✅ Integrated | SDXL-Lightning 4-step UNet + SDXL Base Refiner components |
+| **Optimization** | ✅ Applied | Attention slicing enabled for 16GB RAM compatibility |
+| **Download** | ✅ Robust | Uses `hf_transfer` for fast, resilient model downloading |
+| **Git** | ✅ Pushed | Project initialized and pushed to remote repository |
+
+## Usage Guide
+
+To generate an image, open your terminal and run:
+
+```bash
+# Activate virtual environment
+source venv/bin/activate
+
+# Run generation (first run will download models)
+HF_HUB_ENABLE_HF_TRANSFER=1 python generate.py "A futuristic cityscape, cyberpunk style" --width 1024 --height 1024
+```
+
+> **Note**: The first run requires downloading ~5-6GB of model weights. We use `HF_HUB_ENABLE_HF_TRANSFER=1` to accelerate this process. Subsequent runs will be instant.
+
+## Project Structure
+
+- `generate.py`: Main script. Handles model loading, optimization, and generation.
+- `models/`: Stores the SDXL-Lightning UNet checkpoint.
+- `hf_cache/`: Stores the Diffusers cache (base model components).
+- `requirements.txt`: Python dependencies.
+
+## Optimizations Logic
+
+To ensure smooth performance on macOS:
+1.  **MPS Device**: Automatically selects `mps` (Metal) for GPU acceleration.
+2.  **Attention Slicing**: Enabled via `pipe.enable_attention_slicing()` to reduce peak memory usage during generation.
+3.  **Resolution**: Defaults to `1920x1080` (customizable) or `1024x1024` (recommended). Note that higher resolutions use more RAM.
+4.  **Local Caching**: `HF_HOME` is set to `./hf_cache` to avoid permission issues and keep the project self-contained.
+
+## Verification
+
+The script has been verified to:
+- Download necessary components automatically.
+- Load the custom Lightning UNet correctly.
+- Execute the diffusion loop (4 steps).
+- Save images to `~/Documents/Image Generations/`.
+
+![Workflow Diagram](https://mermaid.ink/img/pako:eNpVkE1rwzAMhv9KoFMO26XruWwH220wGEsvgx1CimNrqyNgyUlpKfvfJyljsN1EeT8eeR_0gDUWQQl9a6y8Yx8C3yObKe-94_w4HlE8j9Fqg1fbH8aA9-h8hU_Gk9nZ0-S8M_Z0PL9gz_Z0vFzhzXih12a4Q_8FfTigJ_uKfTmgZ_tS8HLFrxhe0A-HF_TjwSuKVyOvFl4zvGbcWrw2XC_x6uHdw3uA9wQfAT4SfCT4yPCR4aPAR4GPAl8Fvgp8Nfiq8dXgq8HXgG8A3xB-Q_hN4TeF3wy-OXxz-C3gt4LfCn4r-K3gt4LfCn4r-G_C7y9q1xK2)
+<!-- above diagram text:
+graph TD
+    A[Start Script] --> B{Check HF_HOME};
+    B --> C[Set Local Cache];
+    C --> D[Load Lightning UNet];
+    D --> E[Load Base Pipeline];
+    E --> F[Apply Optimizations];
+    F --> G[Generate Image];
+    G --> H[Save to Documents];
+-->