---
title: CyberRealistic-Flux-SVDQ
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/CyberRealistic-Flux-SVDQ"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/CyberRealistic-Flux-SVDQ.md"
repository: AI-ModelScope/CyberRealistic-Flux-SVDQ
last_updated: 2025-10-23
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
parameters: 21.3B
tensor_type:
  - I32
  - BF16
  - F8_E4M3
  - I8
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 112
stars: 0
tags:
  - Flux1
  - SVDQaunt
  - SVDQ
  - Quantization
  - CyberRealistic
---

# CyberRealistic-Flux-SVDQ

> CyberRealistic-Flux-SVDQ - AI-ModelScope 在 ModelScope 开源的模型。This repository contains Nunchaku-quantized (SVDQ) versions of CyberRealistic Flux, a text-to-image model based on Flux.1 Dev by Cyberdelia

- **Repository**: AI-ModelScope/CyberRealistic-Flux-SVDQ
- **Tasks**: text-to-image-synthesis
- **Parameters**: 21.3B
- **Tags**: Flux1, SVDQaunt, SVDQ, Quantization, CyberRealistic
- **Downloads**: 112
- **Stars**: 0
- **Last updated**: 2025-10-23

Source: https://www.modelscope.cn/models/AI-ModelScope/CyberRealistic-Flux-SVDQ

---

This repository contains Nunchaku-quantized (SVDQ) versions of [CyberRealistic Flux](https://civitai.com/models/1799857/cyberrealistic-flux), a text-to-image model based on Flux.1 Dev by [Cyberdelia](https://civitai.com/user/Cyberdelia)

If you like the model, please consider liking, reviewing and tipping the creator. 

Model Files
- [svdq-int4_r32-CyberRealistic-Flux-V2.5.safetensors](https://huggingface.co/spooknik/CyberRealistic-Flux-SVDQ/blob/main/svdq-int4_r32-CyberRealistic-Flux-V2.5.safetensors): SVDQuant INT4 (rank 32) CyberRealistic Flux V2.5 model. For users with non-Blackwell GPUs (pre-50-series).
- [svdq-fp4_r32-CyberRealistic-Flux-V2.5.safetensors](https://huggingface.co/spooknik/CyberRealistic-Flux-SVDQ/blob/main/svdq-fp4_r32-CyberRealistic-Flux-V2.5.safetensors): SVDQuant NVFP4 (rank 32) CyberRealistic Flux V2.5. For users with Blackwell GPUs (50-series).


### Quality Evaluation

Below is the quality and similarity evaluated with 256 samples from MJHQ-30K dataset. (BF16 is the unqauntized model. INT W4A4 is INT4 and NVFP4 is FP4)

| Model                      | Precision |  Method   | FID                | IR              | LPIPS                | PSNR              |
|----------------------------|-----------|-----------|--------------------|-----------------|----------------------|-------------------|
| CyberRealistic-Flux-V2.5   | BF16      | --        | 173.06             | 0.909           | --                   | --                |
| (30 Steps)                 | INT W4A4  | SVDQ      | 173.07             | 0.902           | 0.215                | 21.04             |
|                            | NVFP4     | SVDQ      | 173.54             | 0.901           | 0.222                | 20.55             |

If you find my work useful please consider: <a href='https://ko-fi.com/B0B21MPRDT' target='_blank'><img height='36' style='border:0px;height:36px;' src='https://storage.ko-fi.com/cdn/kofi6.png?v=6' border='0' alt='Buy Me a Coffee at ko-fi.com' /></a>