ComfyUI-VL-Nodes

By dimtoneffView on GitHub →

A collection of custom nodes for ComfyUI that integrates various Vision-Language (VL) models, including Xiaomi MiMo-VL, LiquidAI LFM2-VL, Kwai Keye-VL, AIDC-AI Ovis2.5 and Ovis-U1. Tested with models: AIDC-AI/Ovis2.5-2B, AIDC-AI/Ovis2.5-9B, Kwai-Keye/Keye-VL-8B-Preview, MiMo-VL-7B-RL-GGUF, LiquidAI/LFM2-VL-450M, LiquidAI/LFM2-VL-1.6B, AIDC-AI/Ovis-U1-3B.

How much VRAM does ComfyUI-VL-Nodes require?

Direct Answer: The ComfyUI node ComfyUI-VL-Nodes requires a minimum base VRAM of 256MB and is optimized for GPUs with at least 4GB of VRAM. Low VRAM mode is fully supported for resource-constrained setups.

High (2-4GB)
Base VRAM:
256MB (0.3GB)
Recommended GPU:
4GB+ VRAM
Low VRAM Mode:
✓ Supported
Estimation Confidence:
HIGH

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 ComfyUI-VL-Nodes?

Direct Answer: Running ComfyUI-VL-Nodes requires installing the following Python package dependencies: accelerate, bitsandbytes, flash-attn>=2.7.4, huggingface_hub, keye-vl-utils, numpy>=1.25.0,<2.0.0, pillow, qwen-vl-utils, scipy>=1.11.3, sentencepiece, transformers>=4.55.0. Ensure your ComfyUI environment has these packages active before launching.

requirements.txt
accelerate
bitsandbytes
flash-attn>=2.7.4
huggingface_hub
keye-vl-utils
numpy>=1.25.0,<2.0.0
pillow
qwen-vl-utils
scipy>=1.11.3
sentencepiece
transformers>=4.55.0

Interactive Setup & Dependency Resolver

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

Related Custom Nodes

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

AITocha Vision
by aitocha128MB VRAM
AI_Text_Comfyui
by Zch6111256MB VRAM
AK XZ Axis (XY for any KSampler)
by akawana256MB VRAM
ArtyClaw Comfy Nodes
by artyclaw256MB VRAM

Frequently Asked Questions

How much VRAM does ComfyUI-VL-Nodes require?

ComfyUI-VL-Nodes requires a minimum of 256MB (0.3GB) 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-VL-Nodes on an RTX 3060, RTX 4070, or RTX 4090?

✅ RTX 3060 (12GB): Yes, fully compatible with 10.6GB headroom. ✅ RTX 4070 (12GB): Yes, fully compatible with 10.6GB headroom. ✅ RTX 4070 Ti (16GB): Yes, fully compatible with 14.2GB headroom. ✅ RTX 4090 (24GB): Yes, fully compatible with 21.4GB headroom

What Python packages are required for ComfyUI-VL-Nodes?

To run ComfyUI-VL-Nodes, you need to install: accelerate, bitsandbytes, flash-attn>=2.7.4, huggingface_hub, keye-vl-utils, numpy>=1.25.0,<2.0.0, pillow, qwen-vl-utils, scipy>=1.11.3, sentencepiece, transformers>=4.55.0. You can install these using pip or add them to your requirements.txt file.

How can I reduce VRAM usage when running ComfyUI-VL-Nodes?

ComfyUI-VL-Nodes 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-VL-Nodes in ComfyUI?

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