LOW_VRAM_Workflows

Rebel AI: Low VRAM ComfyUI Workflows

IMPORTANT! Some workflow folders contain READMEs to help install custom nodes or models you may not have that are required to run the workflows!

Repository Description

This is the official repository for Rebel AI (RealRebelAI), containing a comprehensive collection of ComfyUI workflows engineered specifically for high-end AI generation on mid-range hardware. It includes all workflows featured on the Rebel AI YouTube channel, alongside exclusive, unreleased configurations.

This repository is actively maintained and updated as new workflows are developed.

• Repository Owner: RealRebelAI
• Focus: Low-VRAM Optimization, Photorealistic & Cinematic AI Generation
• License: Apache 2.0

Hardware Target & Optimization

All .json workflows provided here are stress-tested and strictly optimized for 8GB VRAM environments (specifically targeting setups similar to an NVIDIA RTX 3070 paired with 16GB of system RAM).

To prevent out-of-memory (OOM) errors and ensure fast generation, these architectures utilize advanced offloading strategies and heavy quantization techniques, including GGUF, FP8, NVFP4, and INT4.

Supported Models & Frameworks

These workflows cover a wide variety of state-of-the-art open-source image and video frameworks, inherently tuned to output DSLR raw quality, 8k detail, and high-fidelity cinematic lighting. Optimized configurations include:

• Flux & Z-Image
• LTX-Video (including implementations utilizing Unsloth Dynamic (UD) models)
• Ernie Image
• HiDream-O1-Image-Dev
• SenseNova-u1

...And Many More!

Dependencies

Depending on the specific file, you may need to install custom node suites via the ComfyUI Manager. Many of these workflows natively integrate with custom nodes developed for the channel:

• Rebels Animated Nodes
• Rebels Audio Nodes
• Rebels Prompt Enhancer
• Rebels RIB Nodes (Note: This is a singular project node, distinct from the broader node sets)

Usage Instructions

1. Navigate to the Files and versions tab of this repository.
2. Download the desired workflow .json file.
3. Drag and drop the .json file directly into your ComfyUI workspace.
4. Use the ComfyUI Manager and click "Install Missing Custom Nodes" if prompted.
5. Ensure your local file paths for Checkpoints, LoRAs, and VAEs are routed correctly before queuing your prompt.