Update README.md

README.md

@@ -43,12 +43,7 @@ Each quantization level offers a trade-off between speed and quality. **Q4_K_S**
 
 ## Usage
 
-This model can be used with any **GGUF-compatible** inference engine, such as **llama.cpp**, **Kohya's SDXL GGUF loader**, or **custom scripts supporting GGUF-based SDXL inference**.
-
-Example (using a compatible loader):
-```bash
-python infer.py --model sdxl-unet-q5_ks.gguf --vae sdxl-vae-fp16.gguf --clip sdxl-clip-fp16.gguf --prompt "A futuristic city at sunset"
-```
+This model can be used with any **GGUF-compatible** inference engine, such as **ComfyUI**, **Kohya's SDXL GGUF loader**, or **custom scripts supporting GGUF-based SDXL inference**.
 
 ## Hardware Requirements