CLIPSeg
The CLIPSeg node generates a binary mask for a given input image and text prompt. NOTE:This custom node is a forked custom node with hotfixes applied from the [a/original repository](https://github.com/biegert/ComfyUI-CLIPSeg), which is no longer maintained.
How much VRAM does CLIPSeg require?
Direct Answer: The ComfyUI node CLIPSeg requires a minimum base VRAM of 2048MB and is optimized for GPUs with at least 6GB of VRAM. Low VRAM mode is fully supported for resource-constrained setups.
- Base VRAM:
- 2048MB (2.0GB)
- Recommended GPU:
- 6GB+ 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 CLIPSeg?
Direct Answer: Running CLIPSeg requires installing the following Python package dependencies: matplotlib==3.7.1, matplotlib-inline==0.1.6, numpy==1.24.2, open-clip-torch==2.16.0, opencv-python==4.7.0.72, pillow==9.4.0, pytorch-lightning==2.0.0, torch==2.0.0+cu118, torchaudio==2.0.1+cu118, torchdiffeq==0.2.3, torchmetrics==0.11.4, torchsde==0.2.5, torchvision==0.15.1+cu118, transformers==4.27.1. Ensure your ComfyUI environment has these packages active before launching.
matplotlib==3.7.1
matplotlib-inline==0.1.6
numpy==1.24.2
open-clip-torch==2.16.0
opencv-python==4.7.0.72
pillow==9.4.0
pytorch-lightning==2.0.0
torch==2.0.0+cu118
torchaudio==2.0.1+cu118
torchdiffeq==0.2.3
torchmetrics==0.11.4
torchsde==0.2.5
torchvision==0.15.1+cu118
transformers==4.27.1Interactive Setup & Dependency Resolver
# Loading command...Frequently Asked Questions
How much VRAM does CLIPSeg require?
CLIPSeg requires a minimum of 2048MB (2.0GB) of VRAM for base operation. For optimal performance, a GPU with at least 6GB of VRAM is recommended. This node supports low VRAM mode for resource-constrained setups.
Can I run CLIPSeg on an RTX 3060, RTX 4070, or RTX 4090?
✅ RTX 3060 (12GB): Yes, fully compatible with 8.8GB headroom. ✅ RTX 4070 (12GB): Yes, fully compatible with 8.8GB headroom. ✅ RTX 4070 Ti (16GB): Yes, fully compatible with 12.4GB headroom. ✅ RTX 4090 (24GB): Yes, fully compatible with 19.6GB headroom
What PyTorch version does CLIPSeg need?
CLIPSeg requires the following PyTorch-related packages: open-clip-torch==2.16.0, pytorch-lightning==2.0.0, torch==2.0.0+cu118, torchaudio==2.0.1+cu118, torchdiffeq==0.2.3, torchmetrics==0.11.4, torchsde==0.2.5, torchvision==0.15.1+cu118. Ensure your ComfyUI environment has these installed. CUDA 11.8 is required. Compatible with RTX 2000 and 3000 series GPUs.
What Python packages are required for CLIPSeg?
To run CLIPSeg, you need to install: matplotlib==3.7.1, matplotlib-inline==0.1.6, numpy==1.24.2, open-clip-torch==2.16.0, opencv-python==4.7.0.72, pillow==9.4.0, pytorch-lightning==2.0.0, torch==2.0.0+cu118, torchaudio==2.0.1+cu118, torchdiffeq==0.2.3, torchmetrics==0.11.4, torchsde==0.2.5, torchvision==0.15.1+cu118, transformers==4.27.1. You can install these using pip or add them to your requirements.txt file.
How can I reduce VRAM usage when running CLIPSeg?
CLIPSeg 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 CLIPSeg in ComfyUI?
To install CLIPSeg: (1) Navigate to your ComfyUI/custom_nodes directory, (2) Clone the repository: git clone https://github.com/time-river/ComfyUI-CLIPSeg, (3) Install dependencies: pip install -r requirements.txt (if present), (4) Restart ComfyUI. Alternatively, use ComfyUI Manager for one-click installation.