--- pipeline_tag: text-to-image tags: - Flux1 - SVDQaunt - SVDQ - Quantization - Fluxmania - Legacy language: - en base_model_relation: quantized library_name: diffusers --- This repository contains Nunchaku-quantized (SVDQ) versions of [Fluxmania Legacy](https://civitai.com/models/778691?modelVersionId=1769925), a text-to-image model based on Flux.1 Dev by [Adel_AI](https://civitai.com/user/Adel_AI) If you like the model, please consider liking, reviewing and tipping the creator. Model Files - [svdq-int4_r32-fluxmania-legacy.safetensors](https://huggingface.co/spooknik/Fluxmania-SVDQ/blob/main/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](https://huggingface.co/spooknik/Fluxmania-SVDQ/blob/main/svdq-fp4_r32-fluxmania-legacy.safetensors): SVDQuant NVFP4 (rank 32) Fluxmania Legacy model. For users with Blackwell GPUs (50-series). [Comfyui Workflow ](https://huggingface.co/spooknik/Fluxmania-SVDQ/blob/main/fluxmania_workflow.json) ### 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: Buy Me a Coffee at ko-fi.com