updates readme

README.md

@@ -6,28 +6,40 @@ tags:
 - LCM
 - stable-diffusion
 ---
-# Stable Diffusion 1.5 Latent Consistency Model for RKNN2
 
-Run the Stable Diffusion 1.5 LCM image generation model using RKNPU2!
+# Stable Diffusion 1.5 Latent Consistency Model (LCM-SD) for RKNN2
 
-- Inference speed (RK3588, single NPU core):
-  - 384x384: Text encoder 0.05s + U-Net 2.36s/it + VAE Decoder 5.48s
-  - 512x512: Text encoder 0.05s + U-Net 5.65s/it + VAE Decoder 11.13s
-- Memory usage:
-  - 384x384: About 5.2GB
-  - 512x512: About 5.6GB
+Run the **Stable Diffusion 1.5 Latent Consistency Model (LCM-SD)** on **Rockchip RKNPU2 (RK3588)** using RKNN2.
 
-## Usage
+This repository supports **command-line inference** and a **production-ready HTTP server** optimized specifically for **LCM-SD**.
 
-### 1. Clone or download this repository to your local machine
+---
 
-### 2. Install dependencies
+## Performance (RK3588, single NPU core)
 
-```bash
-pip install diffusers pillow numpy<2 rknn-toolkit-lite2
-```
+| Resolution | Text Encoder | U-Net (per step) | VAE Decoder |
+|-----------:|-------------:|-----------------:|------------:|
+| 384×384    | ~0.05s       | ~2.36s           | ~5.48s      |
+| 512×512    | ~0.05s       | ~5.65s           | ~11–14s     |
+
+> NOTE: VAE decode latency is a known RKNN limitation and is not caused by layout, server, or postprocessing overhead.
+
+---
+
+## LCM-SD Optimizations & Quirks (Specific to This Repo)
+
+- Correct tensor layouts:
+  - Text encoder: **NCHW**
+  - U-Net: **NHWC**
+  - VAE decoder: **NHWC**
+- All RKNN runtime auto-conversion warnings eliminated
+- One RKNN runtime context per worker (safe multi-context usage)
+- Deterministic generation via explicit `numpy.RandomState(seed)`
+- VAE decode slowness is a **known RKNN behavior** and unaffected by toolkit version
+
+---
 
-### 3. Run
+## Command-Line Usage (LCM-SD Only)
 
 ```bash
 python ./run_rknn-lcm.py -i ./model -o ./images --num-inference-steps 4 -s 512x512 --prompt "Majestic mountain landscape with snow-capped peaks, autumn foliage in vibrant reds and oranges, a turquoise river winding through a valley, crisp and serene atmosphere, ultra-realistic style."
@@ -35,6 +47,85 @@ python ./run_rknn-lcm.py -i ./model -o ./images --num-inference-steps 4 -s 512x5
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6319d0860d7478ae0069cd92/50jwBxv0Edf7x0WoHmpwi.png)
 
+## LCM-SD HTTP Server
+
+### Start the Server (Command Line)
+
+```bash
+export MODEL_ROOT=./model
+export NUM_WORKERS=3
+export PORT=4200
+
+python lcm_server.py
+```
+
+The server listens on:
+
+```bash
+http://0.0.0.0:4200
+```
+
+## Server Endpoints (LCM-SD Only)
+
+### POST /generate
+
+Generate a PNG image using LCM-SD.
+
+Request body (JSON):
+
+```json
+{
+  "prompt": "a cinematic forest at sunrise",
+  "size": "512x512",
+  "num_inference_steps": 4,
+  "guidance_scale": 1.0,
+  "seed": 1234
+}
+```
+
+Response:
+  • HTTP 200
+  • Content-Type: image/png
+  • Binary PNG payload
+
+### curl Example (LCM-SD Server Only)
+
+```bash
+curl -X POST http://node1.lan:4200/generate \
+  -H "Content-Type: application/json" \
+  -o output.png \
+  -d '{
+    "prompt": "a cinematic forest at sunrise",
+    "size": "512x512",
+    "num_inference_steps": 4,
+    "guidance_scale": 1.0,
+    "seed": 1234
+  }'
+```
+
+## Docker Usage (LCM-SD Server)
+
+### Build Image
+
+```bash
+docker build \
+  -t rknn-lcm-sd .
+```
+
+### Run Container
+
+```bash
+docker run --rm -it \
+  --device /dev/dri \
+  --device /dev/rknpu \
+  -v ./model:/models \
+  -e MODEL_ROOT=/models \
+  -e NUM_WORKERS=3 \
+  -p 4200:4200 \
+  rknn-lcm-sd
+```
+
+Additionally, a docker-compose.yml is provided.
 
 ## Model Conversion