--- pipeline_tag: text-to-image tags: - Flux1 - SVDQaunt - SVDQ - Quantization - CyberRealistic language: - en base_model_relation: quantized library_name: diffusers --- 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: Buy Me a Coffee at ko-fi.com