HYPIR Image Restoration for ComfyUI

By EricRolleiView on GitHub →

Custom ComfyUI nodes for HYPIR image restoration using Stable Diffusion 2.1. Restores and upscales scanned or generated images with optional LM Studio prompt enhancement and tiled VAE processing for large resolutions.

How much VRAM does HYPIR Image Restoration for ComfyUI require?

Direct Answer: The ComfyUI node HYPIR Image Restoration for ComfyUI requires a minimum base VRAM of 3072MB and is optimized for GPUs with at least 8GB of VRAM. Low VRAM mode is fully supported for resource-constrained setups.

Very High (4-8GB)
Base VRAM:
3072MB (3.0GB)
Recommended GPU:
8GB+ VRAM
Low VRAM Mode:
✓ Supported
Estimation Confidence:
MEDIUM

Interactive VRAM Compatibility Estimator

Estimated Total VRAM: 3.00 GBTarget: 8 GB
✅ Comfortable Fit

Your GPU has plenty of headroom. You can run this node safely with your active configurations!

Deploy on High-Performance GPUs

Need more VRAM to run ComfyUI with this node? Rent low-cost, high-performance GPUs on Vast.ai instantly.

🚀 Deploy on Vast.ai

Deploy on Cloud GPUs

Need more VRAM to run ComfyUI with this node? Rent low-cost, high-performance cloud GPUs on RunPod instantly.

🚀 Deploy on RunPod

What Python packages are required for HYPIR Image Restoration for ComfyUI?

Direct Answer: Running HYPIR Image Restoration for ComfyUI requires installing the following Python package dependencies: accelerate>=1.4.0, diffusers>=0.32.0, numpy, peft>=0.14.0, pillow, requests, torch>=2.1, tqdm, transformers>=4.49.0. This node specifically requires PyTorch version 2.1 or newer.

requirements.txt
accelerate>=1.4.0
diffusers>=0.32.0
numpy
peft>=0.14.0
pillow
requests
torch>=2.1
tqdm
transformers>=4.49.0

Interactive Setup & Dependency Resolver

Operating System:
Environment Type:
Run this terminal command in your ComfyUI root folder:
# Loading command...

Special Environment Requirements:

Requires PyTorch version 2.1+.

To update PyTorch for your selected setup, run:
# Loading PyTorch command...

Related Custom Nodes

The following custom nodes run in the same PyTorch / CUDA environment and share similar categories or workflows:

flux2-resolution-guard
by xmarre12.0GB VRAM
ComfyUI-FlowMatching-Upscaler
by ttulttul3.0GB VRAM
ComfyUI-INT-Crush
by ThunderFun128MB VRAM
Skoogeer-Noise
by ttulttul256MB VRAM

Frequently Asked Questions

How much VRAM does HYPIR Image Restoration for ComfyUI require?

HYPIR Image Restoration for ComfyUI requires a minimum of 3072MB (3.0GB) of VRAM for base operation. For optimal performance, a GPU with at least 8GB of VRAM is recommended. This node supports low VRAM mode for resource-constrained setups.

Can I run HYPIR Image Restoration for ComfyUI on an RTX 3060, RTX 4070, or RTX 4090?

✅ RTX 3060 (12GB): Yes, fully compatible with 7.8GB headroom. ✅ RTX 4070 (12GB): Yes, fully compatible with 7.8GB headroom. ✅ RTX 4070 Ti (16GB): Yes, fully compatible with 11.4GB headroom. ✅ RTX 4090 (24GB): Yes, fully compatible with 18.6GB headroom

What PyTorch version does HYPIR Image Restoration for ComfyUI need?

HYPIR Image Restoration for ComfyUI requires the following PyTorch-related packages: torch>=2.1. Ensure your ComfyUI environment has these installed. Ensure your PyTorch installation matches your CUDA version (use torch.version.cuda to check).

What Python packages are required for HYPIR Image Restoration for ComfyUI?

To run HYPIR Image Restoration for ComfyUI, you need to install: accelerate>=1.4.0, diffusers>=0.32.0, numpy, peft>=0.14.0, pillow, requests, torch>=2.1, tqdm, transformers>=4.49.0. You can install these using pip or add them to your requirements.txt file.

How can I reduce VRAM usage when running HYPIR Image Restoration for ComfyUI?

HYPIR Image Restoration for ComfyUI supports low VRAM mode. To reduce memory usage: (1) Enable --lowvram or --medvram flags in ComfyUI, (2) Reduce batch size to 1, (3) Use fp16 or fp8 precision if supported, (4) Close other GPU applications.

How do I install HYPIR Image Restoration for ComfyUI in ComfyUI?

To install HYPIR Image Restoration for ComfyUI: (1) Navigate to your ComfyUI/custom_nodes directory, (2) Clone the repository: git clone https://github.com/EricRollei/HYPIR-ComfyUI, (3) Install dependencies: pip install -r requirements.txt (if present), (4) Restart ComfyUI. Alternatively, use ComfyUI Manager for one-click installation.