license: fair-noncommercial-research-license
base_model: aoxo/flux.1dev-abliteratedv2
library_name: gguf
tags:
- flux
- flux.1-dev
- gguf
- quantized
- image-generation
- text-to-image
- comfyui
- comfyui-gguf
- abliterated
FLUX.1-dev Abliterated V2 — Q4_K_M GGUF
A GGUF Q4_K_M quantization of aoxo/flux.1dev-abliteratedv2, optimized for local inference with limited VRAM.
This repository provides a Q4_K_M GGUF version of the FLUX.1-dev Abliterated V2 model.
The goal of this quantization is to make the model significantly more accessible on consumer hardware while retaining the overall capabilities and characteristics of the original model.
✨ Model
Base model: aoxo/flux.1dev-abliteratedv2
Original architecture: FLUX.1-dev
Quantization: Q4_K_M
Format: GGUF
Intended use: Local image generation / text-to-image
Primary frontend: ComfyUI + ComfyUI-GGUF
📦 File
| File | Quantization | Format |
|---|---|---|
flux-abliterated-v2-Q4_K_M.gguf |
Q4_K_M | GGUF |
The Q4_K_M quantization is intended to provide a practical balance between model size, memory usage and generation quality.
🚀 ComfyUI
This model is designed to work with ComfyUI using ComfyUI-GGUF.