import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("fill-in-base-model", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("APRKDEV/argus-pro")
prompt = "a cinematic monochrome photo of a futuristic neural uplink, neonaut laboratory aesthetic, extreme detail, 8k"
image = pipe(prompt).images[0]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.
- Downloads last month
- 562