ComfyUI_DiffusionModel_fp8_converter

By Shiba-2-shibaView on GitHub →

This is a custom node to convert only the Diffusion model part or CLIP model part to fp8 in ComfyUI. VAE fp8 conversion is not supported. The advantage of this node is that you do not need to separate unet/clip/vae in advance when converting to fp8, but can use the safetenros files that ComfyUI provides.

How much VRAM does ComfyUI_DiffusionModel_fp8_converter require?

Direct Answer: The ComfyUI node ComfyUI_DiffusionModel_fp8_converter 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.

High (2-4GB)
Base VRAM:
128MB (0.1GB)
Recommended GPU:
4GB+ 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

Related Custom Nodes

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

AAA Metadata System
by EricRollei128MB VRAM
Animatediff MotionLoRA Trainer
by kijai4.0GB VRAM
Arc2Face ComfyUI Node Library
by caleboleary128MB VRAM
Arthemy Live Tuner - SDXL
by aledelpho8.0GB VRAM
BokehDiffusionComfyUI
by jrabek256MB VRAM

Frequently Asked Questions

How much VRAM does ComfyUI_DiffusionModel_fp8_converter require?

ComfyUI_DiffusionModel_fp8_converter 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_DiffusionModel_fp8_converter 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

How can I reduce VRAM usage when running ComfyUI_DiffusionModel_fp8_converter?

ComfyUI_DiffusionModel_fp8_converter 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_DiffusionModel_fp8_converter in ComfyUI?

To install ComfyUI_DiffusionModel_fp8_converter: (1) Navigate to your ComfyUI/custom_nodes directory, (2) Clone the repository: git clone https://github.com/Shiba-2-shiba/ComfyUI_DiffusionModel_fp8_converter, (3) Install dependencies: pip install -r requirements.txt (if present), (4) Restart ComfyUI. Alternatively, use ComfyUI Manager for one-click installation.