LOW_VRAM_Workflows by Rebel AI: Open-Weight Model

Model Card

By Rebel AI, published under apache-2.0, revision bbc548525aad.

Read Rebel AI's full model card

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

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

Identity and Version

Repository: realrebelai/LOW_VRAM_Workflows
Publisher: Rebel AI
Task: Text to image
Modality: Image
Library: Not stated by the source
Parameters: Not stated by the source
Languages: low-vram
Revision: 779df103f4f9d446fc5486b4d819a6ec69a40fb9
First published: 2026-03-20
Last updated: 2026-10-22

Files and Weights

108 files, 5.3 MB in total.

Configuration96 files · 3.4 MB

Documentation6 files · 22.9 KB

Other5 files · 1.9 MB

Repository1 file · 1.8 KB

Every file

File	Type	Size	SHA-256
ACESTEP/ACE-Step 1.5.json	Configuration	17.9 KB	—
BOOGU-IMAGE/BIT + ZIT.json	Configuration	27.8 KB	—
BOOGU-IMAGE/Boogu-Image-Base.json	Configuration	11.1 KB	—
BOOGU-IMAGE/Boogu-Image-Edit.json	Configuration	21.5 KB	—
BOOGU-IMAGE/Boogu-Image-Turbo.json	Configuration	11.1 KB	—
Bernini/BERNINI GGUF.json	Configuration	32.2 KB	—
CAPYBARA/Capybara T2I.json	Configuration	38.2 KB	—
Chroma/SPARK.Chroma V1.json	Configuration	16.8 KB	—
Dual Pass Workflows/AsymFLUX.2 + ZIT.json	Configuration	26.4 KB	—
Dual Pass Workflows/EIT + ZIT refiner (GGUF).json	Configuration	19.5 KB	—
Dual Pass Workflows/Ernie base + Z BASE.json	Configuration	20.8 KB	—
Dual Pass Workflows/ErnieTurbo + ZimageTurbo refiner (GGUF).json	Configuration	19.5 KB	—
Dual Pass Workflows/HiDream + ZIT Refine.json	Configuration	28.4 KB	—
Dual Pass Workflows/Kandinsky + Z-Image_BASE.json	Configuration	56.2 KB	—
Dual Pass Workflows/Klein 4b + ZIB .json	Configuration	52.5 KB	—
Dual Pass Workflows/LLADA + KREA.json	Configuration	25.5 KB	—
Dual Pass Workflows/MAGE + KREA.json	Configuration	57.1 KB	—
Dual Pass Workflows/SPARK.Chroma + ZIT.json	Configuration	30.9 KB	—
FIREREDIMAGE/Rebels FireRed Image Edit 1.1.json	Configuration	24.2 KB	—
FLUX2/AsymFLUX.2 WORKFLOW.json	Configuration	18.8 KB	—
FLUX2/Flux KLEIN 4B.json	Configuration	27.5 KB	—
FLUX2/Rebels Flux 2 GGUF.json	Configuration	46.7 KB	—
FLUX2/Rebels Flux 2 KLEIN.json	Configuration	41.6 KB	—
FLUX2/Rebels Flux Klein 9b-KV.json	Configuration	101.7 KB	—
FasH3---T2V_ONLY_Extender_Nodes.json	Configuration	54.7 KB	—
FastH3/FastH3---FL2VA.json	Configuration	25.7 KB	—
FastH3/FastH3---T2V---LongVideo_Node.json	Configuration	78.8 KB	—
FastH3/FastH3---T2V.json	Configuration	33.5 KB	—
FastH3/FastH3---T2V_ONLY_Extender_Nodes.json	Configuration	54.7 KB	—
HiDream-01/Hidream-01 dev + Multi Reference.json	Configuration	8.9 KB	—
HiDream-01/Rebels HiDream-01-Image DEV_WORKFLOW.json	Configuration	3.5 KB	—
JoyAI_Image_Edit/JoyAI_Image_Edit_LOWVRAM _(Workflow).json	Configuration	14.9 KB	—
KANDINSKY/Rebels Kandinsky T2I.json	Configuration	15.6 KB	—
KREA-2/KREA-2 (LOW VRAM WORKFLOW).json	Configuration	10.2 KB	—
KREA-2/KREA-2-INT8(+NSFW).json	Configuration	13.0 KB	—
KREA-2/KREAMAGINE gguf workflow.json	Configuration	48.7 KB	—
KREA-2/Kreamagine Workflow.json	Configuration	29.8 KB	—
KREA-2/krea2 Identity Edit (NSFW+).json	Configuration	33.2 KB	—
KREA-2/krea2 Identity Edit 1.2.json	Configuration	25.5 KB	—
LANCE/LANCE-3B.json	Configuration	14.5 KB	—
LONGCAT/LONGCAT EDIT TURBO.json	Configuration	27.1 KB	—
LONGCAT/Rebels LongCat Image.json	Configuration	15.7 KB	—
LTX2.3/LTX 2.3 HDR IC LoRA WORKFLOW.json	Configuration	49.5 KB	—
LTX2.3/PROMPT RELAY DISTILLED.json	Configuration	60.1 KB	—
LTX2.3/REBELS LTX 2.3 - First-Last Frame.json	Configuration	52.5 KB	—
LTX2.3/Rebels LTX-2 Dev GGUF.json	Configuration	113.0 KB	—
LTX2.3/Rebels LTX-2.3 AUDIO TO VIDEO.json	Configuration	83.4 KB	—
LTX2.3/Rebels LTX-2.3 DEV gguf.json	Configuration	104.0 KB	—
MICROSOFT/ LENS.json	Configuration	18.4 KB	—
MR_FLOW/Krea2_4x_MrFlow_workflow.json	Configuration	19.1 KB	—
MR_FLOW/Krea2_MrFlow_workflow.json	Configuration	19.3 KB	—
MR_FLOW/ZIT_4x_MrFlow_workflow.json	Configuration	19.6 KB	—
MR_FLOW/ZIT_MrFlow_workflow.json	Configuration	19.1 KB	—
Mage-Flow/MAGE + KREA.json	Configuration	26.7 KB	—
Mage-Flow/Mage-Flow BASE.json	Configuration	8.0 KB	—
Mage-Flow/Mage-Flow-edit.json	Configuration	10.8 KB	—
Ming-Image/MING-IMAGE-EDIT (Workflow).json	Configuration	25.8 KB	—
Ming-Image/MING-IMAGE-GGUF (Workflow).json	Configuration	16.3 KB	—
MiniMax/MINIMAX REF2V.json	Configuration	36.8 KB	—
MiniMax/MiniMax FL2V GGUF (WORKFLOW).json	Configuration	37.8 KB	—
QWEN/OLD QWEN/Qwen Image 2512.json	Configuration	21.4 KB	—
QWEN/OLD QWEN/REBELS Qwen Image 2512 - 2steps.json	Configuration	24.0 KB	—
QWEN/OLD QWEN/Rebels Qwen Edit 2511 (v2).json	Configuration	32.3 KB	—
QWEN/OLD QWEN/Rebels Qwen Image Edit 2509 + Enhance LoRA.json	Configuration	28.4 KB	—
QWEN/QWEN-IMAGE-2.1/QWEN 2.1 pruna-image-2.1-5STEP (COMFY LORA).json	Configuration	14.0 KB	—
QWEN/QWEN-IMAGE-2.1/QWEN 2.1 pruna-image-2.1-8STEP (COMFY LORA).json	Configuration	15.2 KB	—
QWEN/QWEN-IMAGE-2.1/QWEN IMAGE 2.1 EDIT (WORKFLOW).json	Configuration	22.5 KB	—
QWEN/QWEN-IMAGE-2.1/QWEN IMAGE 2.1 T2I (Workflow).json	Configuration	14.8 KB	—
QWEN/QWEN-IMAGE-2.1/Qwen 2.1 VIGGLE LoRA (6STEP).json	Configuration	70.2 KB	—
QWEN/QWEN-IMAGE-2.1/Qwen Image 2.1 + UPSCALE (single image).json	Configuration	34.7 KB	—
QWEN/QWEN-IMAGE-2.1/Qwen-Image-2.1 T2I (PROMPT ENHANCER).json	Configuration	18.2 KB	—
REBEL-NODES_Flows/PROMPT CYCLER.json	Configuration	7.3 KB	—
REBEL-NODES_Flows/Rebels Audio Nodes V2.json	Configuration	9.6 KB	—
REBELSCOMFYGAMES/Games.json	Configuration	27.0 KB	—
RIMAGEBASE/Rebels R-Image-Base.json	Configuration	55.4 KB	—
RTX/Video_and_Image_Upscaler.json	Configuration	6.4 KB	—
SCAIL-2/SCAIL-2 GGUF Workflow.json	Configuration	43.1 KB	—
SEFI-IMAGE/SeFi-Image_workflow.json	Configuration	7.9 KB	—
SEFI-IMAGE/sefi_TURBO_workflow.json	Configuration	7.7 KB	—
SenseNova-u1/SenseNova-U1.json	Configuration	11.7 KB	—
Sulphur_2/Sulphur 2 (GGUF).json	Configuration	45.1 KB	—
Viggle/Viggle 4-step T2I_V1.json	Configuration	35.8 KB	—
WAN/Rebel's Wan 2.2 FMLF.json	Configuration	34.2 KB	—
WAN/Rebels Wan Animate GGUF.json	Configuration	102.1 KB	—
WAN/Rebels Wan I2V + Cam Lora.json	Configuration	29.9 KB	—
WAN/Wan I2V PAINTER.json	Configuration	33.3 KB	—
WAN/Wan-Animate-2 (GGUF).json	Configuration	208.3 KB	—
WAN/WanAnimate.json	Configuration	140.1 KB	—
YUE2/Yue2 - Comfy Nodes.json	Configuration	32.5 KB	—
YUE2/Yue2 - FL Piano Roll Nodes.json	Configuration	25.5 KB	—
YUE2/Yue2 - Song-To-ABC.json	Configuration	25.4 KB	—
Z-ANIME/Z-ANIME (CHECKPOINT).json	Configuration	7.5 KB	—
ZIMAGE/Rebels Z-Image + DyPE upscaler.json	Configuration	38.5 KB	—
ZIMAGE/Rebels Z-Image BASE.json	Configuration	40.9 KB	—
ZIMAGE/Rebels Z-Image-Turbo.json	Configuration	13.0 KB	—
ideogram4/REBELS Ideogram 4.json	Configuration	76.8 KB	—
HiDream-01/README.md	Documentation	4.8 KB	—
MR_FLOW/README.md	Documentation	4.8 KB	—
README.md	Documentation	2.6 KB	—
SEFI-IMAGE/README.md	Documentation	5.1 KB	—
Sulphur_2/README.md	Documentation	4.4 KB	—
ideogram4/readme_ideogram.md	Documentation	1.3 KB	—
Sulphur_2/Example__00001_.mp4	Other	433.6 KB	27a5182df71d
Sulphur_2/Example__00002_.mp4	Other	390.2 KB	8e0cfaeb10df
Sulphur_2/Example__00003_.mp4	Other	404.0 KB	215b7be0275d
Sulphur_2/Example__00004_.mp4	Other	394.5 KB	24c4d07abf71
Sulphur_2/Example__00005_.mp4	Other	323.2 KB	f9c3907ed0f7
.gitattributes	Repository	1.8 KB	—

License and Download

License: apache-2.0
Access: Open weights, no gate

Download from Rebel AI

Released by Rebel AI through its official repository on Hugging Face. Read the license.

Questions About LOW_VRAM_Workflows

Can I use LOW_VRAM_Workflows commercially?

Yes. LOW_VRAM_Workflows is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.

Similar Models

Model · Text to image

Qwen-Image-2.1-Uncensored-Quantized

Ahmet Benzer

GGUF, Safetensors, and MLX quantized formats of Qwen/Qwen-Image-2.1 for local image generation using the original upstream base weights. Q4KM is recommended for the best balance of size and quality for GGUF. INT8 ConvRot and NVFP4 offer high performance on supported GPUs, while MLX formats are optimized for Apple Silicon. Companion model files packaged for ComfyUI: Use the model with ComfyUI and ComfyUI-GGUF. All required companion files (GGUF transformer, text encoder, and VAE) are hosted directly in this repository. Download the files and place them in their respective ComfyUI directories: 1. Install ComfyUI-GGUF: Use the maintained fork with native Qwen-Image 2.1 support by cloning…

Open weights other gguf

View model

Model · Text to image

Qwen-Image-2.1-Uncensored-GGUF

Ahmet Benzer

GGUF quantizations of Qwen/Qwen-Image-2.1 for local image generation using the original upstream base weights. Q4KM is recommended for the best balance of size and quality. Companion model files packaged for ComfyUI: Use the model with ComfyUI and ComfyUI-GGUF. All required companion files (GGUF transformer, text encoder, and VAE) are hosted directly in this repository. Download the files and place them in their respective ComfyUI directories: 1. Install ComfyUI-GGUF: Use the maintained fork with native Qwen-Image 2.1 support by cloning leejet/ComfyUI-GGUF into your custom nodes: (Note: If you have the older city96/ComfyUI-GGUF installed and encounter an Unknown model architecture! error…

Open weights other gguf

View model

Model · Text to image

Qwen-Image-2.1-GGUF

Unsloth AI

This is a GGUF quantized version of Qwen-Image-2.1. unsloth/Qwen-Image-2.1-GGUF uses Unsloth Dynamic 2.0 methodology for SOTA performance. - Important layers are upcasted to higher precision, per tensor, from a measured sensitivity scan. - Run these with Unsloth Desktop, stable-diffusion.cpp and more. A GGUF is the denoiser only, so it needs the VAE and the Qwen3-VL text encoder alongside it. See below for image editing operating inside of Unsloth Desktop: Rendered with the Q4KM denoiser and the Q4KM text encoder, 1024x1024, 20 steps, cfg 6.0, euler. We are excited to open-source Qwen-Image-2.1, a unified text-to-image generation and image editing model in the Qwen family. With just 7B…

Open weights other

View model

Model · Text to image

Z-Image-Turbo-GGUF

Unsloth AI

Welcome to the official repository for the Z-Image（造相）project! Z-Image is a powerful and highly efficient image generation model with 6B parameters. Currently there are three variants: - Z-Image-Turbo – A distilled version of Z-Image that matches or exceeds leading competitors with only 8 NFEs (Number of Function Evaluations). It offers sub-second inference latency on enterprise-grade H800 GPUs and fits comfortably within 16G VRAM consumer devices. It excels in photorealistic image generation, bilingual text rendering (English & Chinese), and robust instruction adherence. - Z-Image-Base – The non-distilled foundation model. By releasing this checkpoint, we aim to unlock the full potential…

Open weights apache-2.0 ggml

View model

Model · Text to image

Juggernaut-XL-v9

RunDiffusion

The SDXL ecosystem is the single most mature corner of open image generation, and v9 is its most refined photorealism checkpoint. Choose Juggernaut XL v9 when you want: - Photorealism that holds up under scrutiny — skin texture, micro-contrast, and natural lighting that translates from concept to print. - Reasonable hardware — runs comfortably on 8 GB of VRAM, unlike newer DiT-based models that demand 16+ GB. - The full SDXL toolbox — drop-in compatibility with the thousands of SDXL ControlNets, IP-Adapter variants, AnimateDiff, regional prompting tools, and LoRAs already in your workflow. - Battle-tested reliability — 26+ months in production, used in agencies, studios, and shipping…

Open weights creativeml-openrail-m diffusers

View model

Model · Text to image

Qwen-Image-Lightning

Lightx2v

Please refer to Qwen-Image-Lightning github to learn how to use the models. make sure to install diffusers from main (pip install git+https://github.com/huggingface/diffusers.git)

Open weights apache-2.0 diffusers

View model