Upload README.md with huggingface_hub

README.md

@@ -15,26 +15,26 @@ widget:
     url: "https://huggingface.co/APRKDEV/argus-pro/resolve/main/argus_pro_core.safetensors"
 ---
 
-# 🛰️ Argus-Pro Vision Kernel
+# Argus-Pro Vision Kernel
 
-The flagship vision engine of the **Neonaut Laboratory**. Engineered for ultra-high-fidelity cinematic synthesis and photorealistic monochrome imagery.
+The flagship vision engine of the Neonaut Laboratory. Engineered for ultra-high-fidelity cinematic synthesis and photorealistic monochrome imagery.
 
-## 🦾 Sovereign Specifications
-- **Kernel Architecture**: Argus-12B (Proprietary Vision Core)
-- **Base Lineage**: Sovereign Neonaut Weights
-- **Training Aesthetic**: Cinematic Monochrome / Neonaut Laboratory
-- **Optimal Resolution**: 512px - 1024px
-- **Precision**: bfloat16
+## Sovereign Specifications
+- Kernel Architecture: Argus-12B (Proprietary Vision Core)
+- Base Lineage: Sovereign Neonaut Weights
+- Training Aesthetic: Cinematic Monochrome / Neonaut Laboratory
+- Optimal Resolution: 512px - 1024px
+- Precision: bfloat16
 
-## 🚀 Usage Protocol
-This is a proprietary Neonaut artifact. 
+## Usage Protocol
+This is a proprietary Neonaut artifact. Use the following code for synthesis:
 
 ```python
 from diffusers import AutoPipelineForText2Image
 import torch
 
-# Load the sovereign base and the Argus-Pro kernel
-pipe = AutoPipelineForText2Image.from_pretrained("APRKDEV/argus-pro-base", torch_dtype=torch.bfloat16)
+# Load the Argus Vision Core and the Argus-Pro kernel
+pipe = AutoPipelineForText2Image.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16)
 pipe.load_lora_weights("APRKDEV/argus-pro", weight_name="argus_pro_core.safetensors")
 pipe.to("cuda")
 
@@ -43,5 +43,5 @@ image = pipe(prompt, num_inference_steps=30, guidance_scale=3.5).images[0]
 image.save("neonaut_synthesis.png")
 ```
 
-## ⚖️ License
-Authorized under the **Icarus Open-Source License (IOSL)**. Managed by **APRK**.
+## License
+Authorized under the Icarus Open-Source License (IOSL). Managed by APRK.