Update README.md
Browse files
README.md
CHANGED
|
@@ -27,6 +27,7 @@ tags:
|
|
| 27 |
> - [Starnodes2024/comfyui-starnodes-modelconverter](https://github.com/Starnodes2024/comfyui-starnodes-modelconverter)
|
| 28 |
|
| 29 |
> **Note on my quantized/ INT8 conversions:**
|
|
|
|
| 30 |
> 🪶 = Custom quantized / Int8 ConvRot converted version,
|
| 31 |
>
|
| 32 |
> 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.
|
|
|
|
| 27 |
> - [Starnodes2024/comfyui-starnodes-modelconverter](https://github.com/Starnodes2024/comfyui-starnodes-modelconverter)
|
| 28 |
|
| 29 |
> **Note on my quantized/ INT8 conversions:**
|
| 30 |
+
>
|
| 31 |
> 🪶 = Custom quantized / Int8 ConvRot converted version,
|
| 32 |
>
|
| 33 |
> 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.
|