Update README

README.md

@@ -11,6 +11,8 @@ tags:
 pipeline_tag: text-to-image
 extra_gated_eu_disallowed: true
 ---
+
+
 [中文阅读](./README_CN.md)
 
 <p align="center">
@@ -203,10 +205,9 @@ From the results, HunyuanImage 2.1 achieved a relative win rate of -1.36% agains
 
   **Minimum requrement for now:** 36 GB GPU memory for 2048x2048 image generation.
   
-  > ✨ An FP8-quantized model is coming soon, enabling even lower GPU memory requirements for inference, stay tuned 👀!
+  > ✨ FP8-quantized models are coming soon, enabling even lower GPU memory requirements for inference, stay tuned 👀!
   
   > **Note:** The memory requirements above are measured with model CPU offloading enabled. If your GPU has sufficient memory, you may disable offloading for improved inference speed.
-
 - Supported operating system: Linux.
 
 
@@ -259,8 +260,8 @@ image = pipe(
     # For the distilled model, use 8 steps for faster inference.
     # For the non-distilled model, use 50 steps for better quality.
     num_inference_steps=8 if "distilled" in model_name else 50, 
-    guidance_scale=3.5,
-    shift=5,
+    guidance_scale=3.25 if "distilled" in model_name else 3.5,
+    shift=4 if "distilled" in model_name else 5,
     seed=649151,
 )
 

README_CN.md

@@ -237,8 +237,8 @@ image = pipe(
     # 对于蒸馏版模型，建议使用 8 步以加快推理速度
     # 对于非蒸馏版模型，建议使用 50 步以获得更高画质
     num_inference_steps=8 if "distilled" in model_name else 50, 
-    guidance_scale=3.5,
-    shift=5,
+    guidance_scale=3.25 if "distilled" in model_name else 3.5,
+    shift=4 if "distilled" in model_name else 5,
     seed=649151,
 )