Update README.md

README.md

@@ -1,24 +1,26 @@
----
-license: apache-2.0
-language:
-- en
-pipeline_tag: text-to-image
-library_name: diffusers
-tags:
-- comfyui
-- comfy
-- z-img
-- fp8
-- quantized
----
+---
+license: apache-2.0
+language:
+- en
+pipeline_tag: text-to-image
+library_name: diffusers
+tags:
+- comfyui
+- comfy
+- z-img
+- fp8
+- quantized
+---
 
 # 🔢 FP8 Quantized Version - ComfyUI Compatible
 
 This is the **fp8_e4m3fn** and **fp8_e5m2** quantized version of the Z-Image model, optimized for ComfyUI workflows. These quantized formats significantly reduce VRAM requirements while maintaining high image quality, making the model more accessible for consumer-grade GPUs.
 
 **Quantization Formats:**
-- `fp8_e4m3fn`: 4-bit exponent, 3-bit mantissa format
-- `fp8_e5m2`: 5-bit exponent, 2-bit mantissa format
+- `fp8-e4m3fn-scaled`
+- `fp8-e4m3fn`
+- `fp8_e5m2-scaled`
+- `fp8_e5m2`
 
 **Benefits:**
 - Reduced memory footprint (~50% VRAM savings)