ComfyUI-Goofer on 4GB GPU
Compatible with 4GB GPU
This node will run on RTX 3050, GTX 1650 and similar GPUs with 4GB VRAM.
Optimized Settings for 4GB
VRAM Utilization
100%
You're using 100% of your 4GB VRAM, leaving 0.0GB headroom.
Recommended Batch Size
1
Start with batch size of 1 for optimal performance.
Suggested Resolution
512x512
Best balance of quality and performance for 4GB.
Performance Tips
- Close other GPU-intensive applications
- Limited headroom - reduce batch size if OOM occurs
- 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 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.
VRAM Requirements
- Base VRAM Requirement:
- 4096MB (4.00GB)
- Your GPU (4GB):
- 4096MB (4GB) - RTX 3050, GTX 1650
- VRAM Utilization:
- 100%
- Available Headroom:
- 0.00GB
- Low VRAM Mode:
- ✗ Not supported
- Estimation Confidence:
- MEDIUM
Python Dependencies
accelerate>=0.26.0 # Required for Qwen2.5 float16 loadingbasicsr>=1.4.2 # Required by Real-ESRGANcinemagoer>=2023.5.1 # IMDb data (goofs, metadata) — no API key requirednumpy>=1.24.0 # Array ops (already in ComfyUI)opencv-python>=4.8.0 # Optional: denoise/frame prep (graceful fallback)pillow>=10.0.0 # CPU frame generation (already in ComfyUI)pretty_midi>=0.2.10 # MIDI synthesis for background musicrealesrgan>=0.3.0 # Real-ESRGAN upscaler (auto-downloads ~64 MB model)torch>=2.0.0 # Tensor ops (already in ComfyUI)transformers>=4.37.0 # Qwen2.5-Instruct + MusicGen