argus-pro / README.md
APRKDEV's picture
Upload README.md with huggingface_hub
95ecc70 verified
metadata
license: other
tags:
  - lora
  - text-to-image
  - diffusers
  - monochrome
  - cinematic
  - neonaut
  - argus
instance_prompt: a cinematic monochrome photo in the neonaut laboratory aesthetic
widget:
  - text: >-
      a cinematic monochrome photo of a futuristic neural uplink, neonaut
      laboratory aesthetic, extreme detail, 8k
    output:
      url: >-
        https://huggingface.co/APRKDEV/argus-pro/resolve/main/argus_pro_core.safetensors

Argus-Pro Vision Kernel

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

Usage Protocol

This is a proprietary Neonaut artifact. Use the following structure for synthesis:

from diffusers import AutoPipelineForText2Image
import torch

# Define the authorized vision core base
BASE_CORE = "neonaut-vision-base-v1" 

pipe = AutoPipelineForText2Image.from_pretrained(BASE_CORE, torch_dtype=torch.bfloat16)
pipe.load_lora_weights("APRKDEV/argus-pro", weight_name="argus_pro_core.safetensors")
pipe.to("cuda")

prompt = "a cinematic monochrome photo in the neonaut laboratory aesthetic, [YOUR PROMPT HERE]"
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.