Modelpublic

QuantFunc/Krea-2-QuantFunc-4bit

sourceHugging Faceotherupdated 6d agoView on Hugging Face

2likes5.1kdownloads

Model Card

<p align="center"> 🌐 <a href="https://www.quantfunc.com/">Website</a>  |  🐙 <a href="https://github.com/QuantFunc/ComfyUI-QuantFunc">GitHub</a>  |  🤗 <a href="https://huggingface.co/QuantFunc">Hugging Face</a>  |  🤖 <a href="https://www.modelscope.cn/profile/QuantFunc">ModelScope</a>  |  🎨 <a href="https://civitai.com/user/quantfunc">Civitai</a>  |  🎮 <a href="https://discord.gg/jCp9TpFWcn">Discord</a> </p>

Krea-2-QuantFunc-4bit

4x compression, quality held.

QuantFunc INT4 compresses Krea-2-Turbo to about a quarter of its 16-bit size. In our visual comparisons, composition, detail, color and style stay close to the 16-bit baseline, roughly on par with FP8 and INT8 ConvRot.

Showcase

All images below were generated by Krea-2-QuantFunc-4bit.

Portrait photography	Sci-fi scene

Impasto art	Watercolor illustration

Fast denoising, fast end-to-end too

High-VRAM

On an RTX 4090, same workflow and generation settings:

Stage	QuantFunc INT4	FP8	Speedup
Denoising	1.6s	5.0s	3.13x
End-to-end	2.5s	6.5s	2.6x

End-to-end includes text encoder, denoising and VAE. Text encoder and VAE are not part of the QuantFunc plugin's acceleration path today. Actual speed varies with resolution, steps, driver, software version and hardware.

Low-VRAM

On 8 GB / 12 GB and similar VRAM-constrained setups, 4-bit weights cut weight-bandwidth demand significantly, adding extra speedup — up to roughly 11x. Actual gains depend on VRAM capacity/bandwidth, offload behavior and generation settings.

Swap one loader, keep your workflow

1.Install or update ComfyUI-QuantFunc.
2.Download the r128 or r32 weights.
3.Swap your model loader for the QuantFunc loader and pick the matching weight file.

Every other node, connection and generation parameter stays as-is.

Krea-2-Turbo is a distilled turbo model — use fewer sampling steps and turn CFG off (guidance 1.0).

RTX 20-series through GB300, one build covers it all

Runs on every NVIDIA SM75+ GPU: RTX 20/30/40/50-series, A100, H100, H200, B100, B200, GB300.

Choose a model

Variant	File	Size	Use case
r128	`krea2-turbo-quantfunc-int4-r128.safetensors`	~8.3 GB	Quality-first, recommended
r32	`krea2-turbo-quantfunc-int4-r32.safetensors`	~7.8 GB	Size/VRAM-first

Loading

Weights use QuantFunc's own safetensors format — load with ComfyUI-QuantFunc or the QuantFunc inference engine, not as a drop-in Diffusers checkpoint. (This repo declares library_name: diffusers purely so Hugging Face counts real downloads of the flat .safetensors files above — see HF's download-stats docs — not because the files load via the diffusers package.)

Source & license

This repository distributes derived quantized weights produced from:

—Base model: krea/Krea-2-Turbo
—Pretrained base: krea/Krea-2-Raw

Weights follow the Krea 2 Community License — please read the original model's license terms before use.