KANIBUS - Advanced Eye Tracking ControlNet System on 10GB GPU

kanibus image_generationvideo 2048MB VRAM

Compatible with 10GB GPU

This node will run on RTX 3080 (10GB) and similar GPUs with 10GB VRAM.

Optimized Settings for 10GB

VRAM Utilization

20%

You're using 20% of your 10GB VRAM, leaving 8.0GB headroom.

Recommended Batch Size

8

Start with batch size of 8 for optimal performance.

Suggested Resolution

1024x1024 or higher

Best balance of quality and performance for 10GB.

Performance Tips

  • Close other GPU-intensive applications
  • Low VRAM mode available
  • Monitor GPU usage with nvidia-smi

🚀 Deploy ComfyUI on Vast.ai

Need low-cost, high-performance cloud GPUs to run ComfyUI and this custom node? Rent instantly on Vast.ai starting at pennies per hour.

Deploy on Vast.ai

🚀 Deploy ComfyUI on RunPod

Need high-performance cloud GPUs to run ComfyUI and this custom node? Rent instantly on RunPod starting at just a few cents per hour.

Deploy on RunPod

VRAM Requirements

Base VRAM Requirement:
2048MB (2.00GB)
Your GPU (10GB):
10240MB (10GB) - RTX 3080 (10GB)
VRAM Utilization:
20%
Available Headroom:
8.00GB
Low VRAM Mode:
✓ Supported
Estimation Confidence:
MEDIUM

Python Dependencies

  • accelerate>=0.25.0 # For model optimization
  • albumentations>=1.3.0
  • diffusers>=0.24.0 # For T2I-Adapter support
  • gputil>=1.4.0
  • imageio>=2.31.0
  • imageio-ffmpeg>=0.4.9
  • mediapipe>=0.10.8
  • numba>=0.58.0
  • numpy>=1.24.0
  • opencv-contrib-python>=4.8.1.78

+ 16 more dependencies

View for Different GPU