Modelpublic

spooknik/Fluxmania-SVDQ

sourceHugging Faceupdated 11mo agoView on Hugging Face

31likes611downloads

Model Card

This repository contains Nunchaku-quantized (SVDQ) versions of Fluxmania Legacy, a text-to-image model based on Flux.1 Dev by Adel_AI

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

Model Files

—svdq-int4_r32-fluxmania-legacy.safetensors: SVDQuant INT4 (rank 32) Fluxmania Legacy model. For users with non-Blackwell GPUs (pre-50-series).
—svdq-fp4_r32-fluxmania-legacy.safetensors: SVDQuant NVFP4 (rank 32) Fluxmania Legacy model. For users with Blackwell GPUs (50-series).

Comfyui Workflow

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
Fluxmania Legacy (25 step)	BF16	--	175.08	0.895	--	--
	INT W4A4	SVDQ	174.84	0.795	0.222	22.84
	NVFP4	SVDQ	173.10	0.884	0.192	23.38

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>