Update README.md

README.md

@@ -25,12 +25,12 @@ tags:
 > 
 > 🪶 = Custom quantized / Int8 ConvRot converted version,
 > 
-> Some of these INT8 versions were converted by me using the following tools:
+> These INT8 versions were converted by me using the following tools:
 > - [silveroxides/convert_to_quant](https://github.com/silveroxides/convert_to_quant) 
 > - [Comfy-Org/comfy-model-tools](https://github.com/Comfy-Org/comfy-model-tools) (`quant_int8_convrot.py`) 
 > - [Starnodes2024/comfyui-starnodes-modelconverter](https://github.com/Starnodes2024/comfyui-starnodes-modelconverter)
 >
-> Based on testing, INT8 quantized versions of SD1.5 and SDXL architectures (including Pony, Illustrious, etc.) are actually slower than the original models due to VRAM bandwidth bottlenecks and the overhead of runtime dequantization. Since SD1.5 is already lightweight and SDXL architectures are already fast, the speed gains from quantization are negligible.In my simple benchmarks, only the Illustrious (IL) INT8 version showed a positive speed optimization, while all other INT8 versions were slower.
+> Based on testing, INT8 quantized versions of SD1.5 and SDXL architectures (including Pony) are actually slower than the original models due to VRAM bandwidth bottlenecks and the overhead of runtime dequantization. Since SD1.5 is already lightweight and SDXL architectures are already fast, the speed gains from quantization are negligible.In my simple benchmarks, only the Illustrious (IL) INT8 version showed a positive speed optimization, while all other INT8 versions were slower.
 >
 > Furthermore, for SDXL variants, the dual-CLIPs are tightly integrated with the UNet—splitting them would cause severe storage bloat (e.g., requiring 60 CLIP-L+ 60 CLIP_G files for 60 checkpoints). However, I still provide these converted versions specifically for low-VRAM environments or testing, allowing users with limited hardware to run models that would otherwise OOM."