Extensions/Elvax Nodes
ComfyUI Extension

Elvax Nodes

Convenience nodes for ComfyUI! - LLM TURBO : Faster Local LLM all within Comfy - Faster Image Load/Crop in one node - Faster Upscale + Interpolate+ Film Grain in one node - Dynamic Pipes to tidy WFs (supports get/set nodes and reroutes) And more...

By younestft·Created 3 months ago·Updated 19 days ago· 11
younestft/Elvax-nodes
Nodes—
On cloudLocal install
Stars11
Updated19 days ago
Readme

Elvax Nodes

Convenience nodes for ComfyUI!

  • LLM TURBO: Run local LLMs faster, directly in ComfyUI
  • Load, crop, rotate, and scale images faster in one node
  • Upscale, interpolate, and add film grain in one node
  • Compare videos, images, or audio and inspect their generation differences
  • Tidy workflows with Dynamic Pipes, supporting Set/Get nodes and reroutes
  • Extend Minimax H3 Videos

And much more...

LLM Turbo

Run local GGUF models directly inside ComfyUI at blazing speed through the llama.cpp backend, with no external LLM app, setup, or headache!

Use dynamically growing image or audio inputs, including image batches, and use MTP (speculative decoding) where supported to speed things even more.

Track your generation speed through stats.

Put your GGUF models in models/LLM or models/text_encoders

Image and audio inputs require a compatible model and projector (mmproj).

<table> <tr> <td><img src="assets/llm-turbo-1.gif" alt="LLM Turbo example 1" width="100%"></td> <td><img src="assets/llm-turbo-2.gif" alt="LLM Turbo example 2" width="100%"></td> </tr> </table>

| Platform | Supported backends | |---|---| | Windows x64 | CUDA, Vulkan, ROCm, Custom* | | Linux x64 | CUDA, Vulkan, ROCm, Custom* | | macOS | Metal, Custom* | | Windows ARM64 | CUDA, Vulkan, Custom* | | Linux ARM64 | CUDA, Vulkan, Custom* |

*Custom lets you supply your own llama.cpp build.

Load/Crop Image

Load, crop, rotate, and scale images in one node. Refine the crop interactively, then send the image and matching mask downstream, or restore the original with one click.

Load/Crop Image

Turbo Post Processing

Upscale with Lanczos to improve quality, interpolate with RIFE 4.9 to smooth motion, and add film grain to reduce the digital AI look, all in one fast node, with extra VRAM Optimizations to prevent OOM.

Turbo Post Processing

Media Compare Pro

Compare videos, single images, or audio and inspect their generation differences. Drag and drop media or load connected inputs manually or automatically. (Audio compares with audio only)

<table> <tr> <td align="center"><img src="assets/media-compare-pro-drop-v2.jpg" alt="Media Compare Pro drag-and-drop view" width="100%"></td> <td align="center"><img src="assets/media-compare-pro-v2.jpg" alt="Media Compare Pro comparison view" width="100%"></td> </tr> </table>

Fast Group Controls

Toggle groups on or off to enable or bypass their nodes. Click the pin to pin or unpin a group.

Right-click the switch to hide its controls. To restore them, right-click the group's upper-right corner and choose Show Elvax Group Controls.

Fast Group Toggles

Generation Queue Manager

Manage ComfyUI's generation queue. Reorder, pause, resume, or cancel jobs. Stop a running job and keep it saved to run again. Paused jobs remain saved across restarts.

Generation Queue Manager

Dynamic Pipe In / Dynamic Pipe Out

Tidy your complex workflows with Dynamic Pipes : Dynamic Pipe In grows as you connect values; Dynamic Pipe Out unpacks them into separate outputs in their original order, Supports Set/Get nodes and Reroutes!

Dynamic Pipe In and Dynamic Pipe Out

Circuit Switch / Reroute Switch

Circuit Switch: Open or close the connected path. Closed passes the input; open blocks it.

Reroute Switch: Choose which connected path runs. The inactive path is blocked.

Reroute Switch / Circuit Switch

Prompt Edit / Preview

Preview and edit text in one node. Edit the preview text with one click, Supports the browser’s built-in spell checker to detect and correct spelling and grammar errors.

Prompt Edit / Preview

Prompt Template Builder / JSON Prompt Splitter

Build a structured JSON prompt that you can feed to your favourite LLM with editable/nested fields, customizable field colours. Save/load preserves everything in the JSON including hidden fields and colours.

JSON Prompt Splitter splits a JSON prompt into the selected number of videos, as specified in Prompt Template Builder, and bypasses unused stages in groups named Group 1, Group 2, and so on.

Prompt Template Builder

H3 Staged Samplers

Build a MiniMax H3 generation as a configurable stage-by-stage chain. Set shared generation parameters once in H3 Chain Settings, then tailor each stage with H3 Stage Settings. Use H3 Sampler Preview to sample the stage, optionally show a live tiny-VAE preview or decode the full video, and pass the accumulated latent into the next stage. Motion Context continues from prior latent context; Hard Cut starts a fresh joined segment.

H3 Chain Settings: Configure the shared settings for a MiniMax H3 extension chain.

H3 Stage Settings: Configure each stage of a MiniMax H3 extension chain independently (supports custom Loras for each stage)

H3 Sampler Preview: Sample a stage, optionally show a live tiny-VAE preview during sampling or decode a full video preview, and pass the accumulated latent to the next stage. The preview_result toggle controls full video decoding; live previews are available when a tiny VAE is selected. With preview_result enabled, select this node as an output in App Builder to play its finished video in App Mode. Live tiny-VAE previews use the graph player.

H3 References: Bundle picture, video, and audio references with MiniMax H3 token labels for use in H3 Stage Settings. Audio slots 1–3 pair with their matching connected video slots; remaining audio slots are standalone.

H3 Stage Samplers

H3 Custom Extension Sampler

Seamlessly extend a MiniMax H3 generation from one sampler stage to the next, with controls to customize exactly how you want it built. Sampling stays lightweight: the node returns the accumulated chain_latent and this stage's stage_latent without decoding, so you can connect your preferred preview or decode workflow.

H3 Custom Extension Sampler

Installation

ComfyUI Manager

Open Manager → Custom Nodes Manager, search for Elvax Nodes, and select Install. Restart ComfyUI.

Manual installation

Clone this repository into ComfyUI/custom_nodes:

git clone https://github.com/younestft/Elvax-nodes.git

Install the Python dependency with the Python environment used by ComfyUI:

python -m pip install -r ComfyUI/custom_nodes/Elvax-nodes/requirements.txt

Restart ComfyUI. The nodes appear under the Elvax category.

License and credits

This repository is licensed under GNU GPL v3 or later; see LICENSE.

Many nodes in this pack are based on or inspired by ComfyUI's native nodes. Credit to the Comfy Org team for ComfyUI and its native node implementations. The H3 tiny-VAE preview is credited to Kijai and KJNodes.

LLM Turbo is adapted from the GPL-3.0-licensed ComfyUI-LLM-text-processor by KingManiya. with added Audio and MTP support + further UI and quality of life improvements.

The H3 Extension Sampler is a modified derivative of ComfyUI-H3-Motion-Context by NikoDemon80.

The bundled H3 References node is adapted from the GPL-3.0-licensed ComfyUI-H3-Prompt-IDE by Ethan Fel.

Turbo Post Processing brings together ComfyUI's native Lanczos image scaling, RIFE 4.9 interpolation from Fill-Nodes by filliptm, and Fast Film Grain from VRGameDevGirl's nodes and adds further performance and VRAM optimizations.