Hybrid-Sensitivity-Weighted-Quantization (HSWQ)
High-fidelity ConvRot NVFP4 quantization for diffusion models (SDXL). HSWQ uses sensitivity and importance analysis instead of naive uniform cast. This is highly useful for users who need to strictly manage their VRAM resources while maintaining maximum image quality.
ComfyUI Load Diffusion Model nvfp4 pack with FULL ConvRot (Linear→NVFP4, Conv2d→INT8 int8_tensorwise) after DualMonitor + V4 pack-MSE FP16 protection under a fixed 600 MiB budget. Keep ratio is 0 (r0); calib writes NVFP4 .input_scale. SDXL pack scripts: hswq_convert_nvfp4_1.0.py (HSWQ) and native_convert_nvfp4.py (native).
Technical details: https://github.com/ussoewwin/Hybrid-Sensitivity-Weighted-Quantization
How to quantize (SDXL ConvRot NVFP4): md/How to quantize SDXL NVFP4.md
ComfyUI Loader for ConvRot NVFP4: To use these models in ComfyUI, please use this custom node: ComfyUI-HSWQ-Loader-and-Tools
SDXL ConvRot NVFP4 Benchmark Test Results (published tables): benchmark result/benchmark_convrotnvfp4.md
Benchmark (Reference)
| Model | SSIM (Avg) | File size | Compatibility |
|---|---|---|---|
| Original FP16 | 1.0000 | 100% | High |
| HSWQ ConvRot NVFP4 | 0.92-0.98 | 60% (FP16 mixed) | High (ComfyUI NVFP4) |
📦 Available Models
| Filename | Base Model | Version | License |
|---|---|---|---|
animemix_v80_hswq_r32_1off_nvfp4.safetensors | AnimeMix | v8.0 | Fair AI Public License 1.0-SD |
epicrealismXL_pureFix_hswq_r32_1off_convrot_nvfp4.safetensors | epiCRealism XL | pureFix | CreativeML Open RAIL++-M |
koronemixIllustrious_v70_hswq_r32_1off_convrot_nvfp4.safetensors | koronemixIllustrious | v70 | Fair AI Public License 1.0-SD |
koronemixVpred_v20_hswq_r32_1on_convrot_nvfp4.safetensors | koronemixVpred | v2.0 | CreativeML Open RAIL++-M |
perfectionRealisticILXL_80_r32_1on_convrot_nvfp4.safetensors | Perfection Realistic ILXL | v8.0 | Fair AI Public License 1.0-SD |
realvisxlV50_v40Bakedvae_hswq_r32_1off_nvfp4.safetensors | RealVisXL V5.0 (Lightning) | v4.0 BakedVAE | CreativeML Open RAIL++-M |
realvisxlV50_v50Bakedvae_hswq_r32_1off_convrot_nvfp4.safetensors | RealVisXL V5.0 (Lightning) | v5.0 BakedVAE | CreativeML Open RAIL++-M |
unholyDesireMixSinister_v80_hswq_r32_1off_nvfp4.safetensors | Unholy Desire Mix Sinister | v8.0 | Fair AI Public License 1.0-SD |
waiIllustriousSDXL_v170_hswq_r32_1off_convrot_nvfp4.safetensors | Illustrious-XL v1.7 (WAI-illustrious-SDXL) | v17.0 (HF weight) | Fair AI Public License 1.0-SD |
📜 Credits & License
🏆 Special Acknowledgement
We extend our deepest respect and gratitude to the Nunchaku Team for their groundbreaking work on SVDQ quantization and for sharing their models with the community. This collection relies heavily on their research and original implementation.
- Original Repository: nunchaku-tech/nunchaku-sdxl
Base Models
These models are derivatives of their respective creators. All credit for aesthetic tuning and model training belongs to the original creators.
- AnimeMix / koronemixIllustrious / koronemixVpred: Created by koronen.
- epiCRealism XL: Created by epinikion.
- Perfection Realistic ILXL: Created by 6tZ.
- RealVisXL V5.0: Created by SG_161222.
- Unholy Desire Mix Sinister: Created by UnholyDesiresStudio.
- WAI-illustrious-SDXL: Created by WAI0731.
Disclaimer: These models are provided for optimization and research purposes. Please adhere to the original licenses of the base models.