Save 4 hours! We auto-setup your workflow! Free!

Drop your workflow.json — we handle every dependency, custom node, and model. Just open the link and run.

Auto-Setup Workflow Json (Free) Now!
ComfyUI > Nodes > RocM Ninodes

ComfyUI Extension: RocM Ninodes

Repo Name

rocm-ninodes

Author
iGavroche (Account age: 1806 days)
Nodes
View all nodes(1)
Latest Updated
2026-10-25
Github Stars
0.05K

How to Install RocM Ninodes

Install this extension via the ComfyUI Manager by searching for RocM Ninodes
  • 1. Click the Manager button in the main menu
  • 2. Select Custom Nodes Manager button
  • 3. Enter RocM Ninodes in the search bar
After installation, click the Restart button to restart ComfyUI. Then, manually refresh your browser to clear the cache and access the updated list of nodes.

Visit ComfyUI Online for ready-to-use ComfyUI environment

  • Free trial available
  • 16GB VRAM to 80GB VRAM GPU machines
  • 400+ preloaded models/nodes
  • Freedom to upload custom models/nodes
  • 200+ ready-to-run workflows
  • 100% private workspace with up to 200GB storage
  • Dedicated Support

Run ComfyUI Online

RocM Ninodes Description

RocM Ninodes offers high-performance VAE decode and sampling nodes optimized for ComfyUI, specifically designed for AMD GPUs with ROCm support, focusing on the gfx1151 architecture.

rocm-ninodes Introduction

rocm-ninodes is an extension designed to enhance the performance of ComfyUI, a user interface for AI models, specifically for users with AMD GPUs utilizing ROCm (Radeon Open Compute). This extension provides a set of optimized nodes that improve the efficiency and speed of various AI tasks, such as VAE decoding, sampling, and model loading. By leveraging the capabilities of ROCm, rocm-ninodes offers significant performance boosts and better memory management, making it an ideal choice for AI artists looking to maximize their hardware's potential.

How rocm-ninodes Works

At its core, rocm-ninodes works by replacing standard nodes in ComfyUI with versions that are optimized for AMD GPUs. These nodes are fine-tuned to take advantage of ROCm's advanced features, such as improved memory handling and precision optimizations. For example, the VAE decode node is optimized to handle large images more efficiently by using advanced tiling techniques, which break down images into smaller, more manageable pieces. This approach not only speeds up processing but also reduces the likelihood of running out of memory.

rocm-ninodes Features

  • ROCm-Optimized VAE Decode: This feature enhances the decoding of Variational Autoencoders (VAEs) by optimizing tile sizes and memory management, ensuring faster and more efficient processing.
  • ROCm-Optimized KSampler: Provides a sampling method that is tailored for AMD GPUs, offering options to optimize for video and adjust precision modes for better performance.
  • Performance Monitoring: Built-in nodes that track and analyze the performance of your GPU, providing recommendations for optimal settings.
  • Quantized Model Support: Automatically detects and optimizes models that use quantization, such as FP8 and INT8, to ensure compatibility and efficiency.

rocm-ninodes Models

rocm-ninodes supports various models, including those that use quantization techniques. It can handle FP8, BFloat16, INT8, and INT4 formats, automatically adjusting settings to maintain performance and prevent errors. This flexibility allows AI artists to work with a wide range of models without worrying about compatibility issues.

What's New with rocm-ninodes

The latest version, v2.0.11, introduces several enhancements:

  • ROCm Text Generate LTX2 Prompt: A new node for generating text prompts, optimized for ROCm, which improves speed and memory handling.
  • Generative AI Category: Organizes nodes under a new category for easier access and management.

Previous updates have included improvements like checkpoint caching to reduce load times and fixes for video processing issues, ensuring smoother and more reliable performance.

Troubleshooting rocm-ninodes

If you encounter issues while using rocm-ninodes, here are some common solutions:

  • Nodes Not Appearing: Restart ComfyUI and clear the cache if nodes do not appear after installation.
  • Out of Memory Errors: Reduce tile sizes or disable aggressive memory optimizations for large models.
  • Windows Pagination Errors: Use the Windows Pagination Diagnostic node to automatically detect and fix these issues.

For more detailed troubleshooting, consider checking the performance monitor nodes for specific recommendations tailored to your hardware setup.

Learn More about rocm-ninodes

To further explore the capabilities of rocm-ninodes, you can access additional resources such as tutorials and community forums. These platforms provide valuable insights and support, helping you make the most of this powerful extension. For installation and setup guidance, refer to the comprehensive documentation available on the rocm-ninodes GitHub page.

RocM Ninodes Related Nodes

RunComfy
Copyright 2025 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.