---
title: CenKreChro-SVDQ
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/CenKreChro-SVDQ"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/CenKreChro-SVDQ.md"
repository: AI-ModelScope/CenKreChro-SVDQ
last_updated: 2025-11-05
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
base_model:
  - Tiwaz/CenKreChro
base_model_relation: quantized
parameters: 32.4B
tensor_type:
  - I8
  - I32
  - BF16
  - F8_E4M3
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 126
stars: 0
tags:
  - Flux1
  - Chroma
  - Krea
  - SVDQaunt
  - CenKreChro
  - SVDQ
  - Quantization
---

# CenKreChro-SVDQ

> CenKreChro-SVDQ - AI-ModelScope 在 ModelScope 开源的模型。This repository contains Nunchaku-quantized (SVDQ) versions of CenKreChro, a text-to-image model based on Chroma and Flux Krea merged by TiwazM

AI-ModelScope/CenKreChro-SVDQ 是 ModelScope 魔搭社区上的 32.4B 参数text-to-image-synthesis模型，基于 Tiwaz/CenKreChro 构建。

- **Repository**: AI-ModelScope/CenKreChro-SVDQ
- **Tasks**: text-to-image-synthesis
- **Parameters**: 32.4B
- **Base model**: Tiwaz/CenKreChro
- **Tags**: Flux1, Chroma, Krea, SVDQaunt, CenKreChro, SVDQ, Quantization
- **Downloads**: 126
- **Stars**: 0
- **Last updated**: 2025-11-05

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

---

This repository contains Nunchaku-quantized (SVDQ) versions of [CenKreChro](https://civitai.com/models/1836040/cenkrechro), a text-to-image model based on Chroma and Flux Krea merged by [TiwazM](https://civitai.com/user/TiwazM)

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

Model Files
- [svdq-int4_r32-CenKreChro.safetensors](https://huggingface.co/spooknik/CenKreChro-SVDQ/blob/main/svdq-int4_r32-CenKreChro.safetensors): SVDQuant INT4 (rank 32) CenKreChro 1.0 model. For users with non-Blackwell GPUs (pre-50-series).
- [svdq-fp4_r32-CenKreChro.safetensors](https://huggingface.co/spooknik/CenKreChro-SVDQ/blob/main/svdq-fp4_r32-CenKreChro.safetensors): SVDQuant NVFP4 (rank 32) CenKreChro 1.0 model. For users with Blackwell GPUs (50-series).
- [svdq-int4_r32-CenKreChro-V2.3.safetensors](https://huggingface.co/spooknik/CenKreChro-SVDQ/blob/main/svdq-int4_r32-CenKreChro-V2.3.safetensors): SVDQuant INT4 (rank 32) CenKreChro 2.3 model. For users with non-Blackwell GPUs (pre-50-series).
- [svdq-fp4_r32-CenKreChro-V2.3.safetensors](https://huggingface.co/spooknik/CenKreChro-SVDQ/blob/main/svdq-fp4_r32-CenKreChro-V2.3.safetensors): SVDQuant NVFP4 (rank 32) CenKreChro 2.3 model. 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              |
|----------------------------|-----------|-----------|--------------------|-----------------|----------------------|-------------------|
| CenKreChro (25 Steps)      | BF16      | --        | 135.52             | 0.842           | --                   | --                |
|                            | INT W4A4  | SVDQ      | 135.50             | 0.795           | 0.255                | 20.64             |
|                            | NVFP4     | SVDQ      | 134.19             | 0.849           | 0.219                | 21.30             |

If you find these 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>