ComfyUI-InferenceTimeScaling
Inference-time techniques to enhance diffusion-based image generation quality through random search and zero-order optimization algorithms
How much VRAM does ComfyUI-InferenceTimeScaling require?
Direct Answer: The ComfyUI node ComfyUI-InferenceTimeScaling requires a minimum base VRAM of 128MB and is optimized for GPUs with at least 4GB of VRAM. Low VRAM mode is fully supported for resource-constrained setups.
- Base VRAM:
- 128MB (0.1GB)
- Recommended GPU:
- 4GB+ VRAM
- Low VRAM Mode:
- ✓ Supported
- Estimation Confidence:
- MEDIUM
Interactive VRAM Compatibility Estimator
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 Cloud GPUs
Need more VRAM to run ComfyUI with this node? Rent low-cost, high-performance cloud GPUs on RunPod instantly.
What Python packages are required for ComfyUI-InferenceTimeScaling?
Direct Answer: Running ComfyUI-InferenceTimeScaling requires installing the following Python package dependencies: clip@ git+https://github.com/openai/CLIP.git, fairscale>=0.4.0, huggingface_hub==0.27.1, image_reward==1.5, numpy>=1.24.0, open-clip-torch>=2.20.0, outlines==0.2.0, pillow==11.1.0, pydantic==2.10.6, timm==0.6.13, torch>=2.5.1, torchvision>=0.20.1, transformers==4.49.0. This node specifically requires PyTorch version 2.5.1 or newer.
clip@ git+https://github.com/openai/CLIP.git
fairscale>=0.4.0
huggingface_hub==0.27.1
image_reward==1.5
numpy>=1.24.0
open-clip-torch>=2.20.0
outlines==0.2.0
pillow==11.1.0
pydantic==2.10.6
timm==0.6.13
torch>=2.5.1
torchvision>=0.20.1
transformers==4.49.0Interactive Setup & Dependency Resolver
# Loading command...Special Environment Requirements:
Requires PyTorch version 2.5.1+.
# Loading PyTorch command...Frequently Asked Questions
How much VRAM does ComfyUI-InferenceTimeScaling require?
ComfyUI-InferenceTimeScaling requires a minimum of 128MB (0.1GB) of VRAM for base operation. For optimal performance, a GPU with at least 4GB of VRAM is recommended. This node supports low VRAM mode for resource-constrained setups.
Can I run ComfyUI-InferenceTimeScaling on an RTX 3060, RTX 4070, or RTX 4090?
✅ RTX 3060 (12GB): Yes, fully compatible with 10.7GB headroom. ✅ RTX 4070 (12GB): Yes, fully compatible with 10.7GB headroom. ✅ RTX 4070 Ti (16GB): Yes, fully compatible with 14.3GB headroom. ✅ RTX 4090 (24GB): Yes, fully compatible with 21.5GB headroom
What PyTorch version does ComfyUI-InferenceTimeScaling need?
ComfyUI-InferenceTimeScaling requires the following PyTorch-related packages: open-clip-torch>=2.20.0, torch>=2.5.1, torchvision>=0.20.1. 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 ComfyUI-InferenceTimeScaling?
To run ComfyUI-InferenceTimeScaling, you need to install: clip@ git+https://github.com/openai/CLIP.git, fairscale>=0.4.0, huggingface_hub==0.27.1, image_reward==1.5, numpy>=1.24.0, open-clip-torch>=2.20.0, outlines==0.2.0, pillow==11.1.0, pydantic==2.10.6, timm==0.6.13, torch>=2.5.1, torchvision>=0.20.1, 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 ComfyUI-InferenceTimeScaling?
ComfyUI-InferenceTimeScaling 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 ComfyUI-InferenceTimeScaling in ComfyUI?
To install ComfyUI-InferenceTimeScaling: (1) Navigate to your ComfyUI/custom_nodes directory, (2) Clone the repository: git clone https://github.com/YRIKKA/ComfyUI-InferenceTimeScaling, (3) Install dependencies: pip install -r requirements.txt (if present), (4) Restart ComfyUI. Alternatively, use ComfyUI Manager for one-click installation.