Update README.md

README.md

@@ -29,15 +29,15 @@ Recommended 6-10 steps. Greatly improved quality compared to other Flux.1 model.
 
 ![](./compare.jpg)
 
-GGUF Q8_0 量化版本模型文件，经过几天的测试，没问题。其出图质量与 fp8 相同，在某些细节体现方面，略优于 fp8 格式，GGUF 模型文件加载方式和模型转换方法，已在下面附加描述。另：应网友要求，正在准备 GGUF Q4_1 格式模型，初步测试情况如下图：
+GGUF Q8_0 量化版本模型文件，经过几天的测试，没问题。其出图质量与 fp8 相同，在某些细节体现方面，略优于 fp8 格式，GGUF 模型文件加载方式和模型转换方法，已在下面附加描述。另：应网友要求，已转换和上传了 GGUF Q4_1 格式模型，与 Q8_0 的对比测试情况如下图所示：
 
-GGUF Q8_0 quantized model file, had tested, no problem. The quality of the image is the same as fp8 format, and in some details, it is slightly better than the fp8 format, and the loading method of GGUF model and conversion method are described below. Another: At the request, the GGUF Q4_1 format model is being prepared, and the preliminary test situation is as follows:.
+GGUF Q8_0 quantized model file, had tested, no problem. The quality of the image is the same as fp8 format, and in some details, it is slightly better than the fp8 format, and the loading method of GGUF model and conversion method are described below. Another: At the request, the GGUF Q4_1 format model had uploded, and the test result compare with Q8_0 show as follows:
 
 ![](./Q8_0&Q4_1.jpg)
 
-初步测试结果看：Q4_1 模型在人物等较大对象的输出时，表现较好，但在需要体现更多细节时，发现细节丢失较多，因此，建议网友们如果硬件允许，尽量选择 fp8/Q8_0 模型，Q4_1 模型经测试完成后会尽快上传，NF4格式由于已经失去支持，所以不会提供。
+初步测试结果看：Q4_1 模型在人物等较大对象的输出时，表现较好，但在需要体现更多细节时，发现细节丢失较多，因此，建议网友们如果硬件允许，尽量选择 fp8/Q8_0 模型，Q4_1 模型经初步测试后已上传，NF4格式由于已经失去支持，所以不会提供。
 
-According to the preliminary test results, the Q4_1 model performs well in the output of larger objects such as characters, but when it is necessary more details, it is found that more details are lost, so it is recommended try to choose the FP8/Q8_0 model if the hardware allows, and the Q4_1 model will be uploaded as soon as possible. The NF4 format will not be available as it has deprecated.
+According to the preliminary test results, the Q4_1 model performs well in the output of larger objects such as characters, but when it is necessary more details, it is found that more details are lost, so it is recommended try to choose the FP8/Q8_0 model if the hardware allows, and the Q4_1 model had uploaded. The NF4 format will not be available as it has deprecated.
 
 过度量化将失去本高精细模型的优势，所以，除 Q4_1 外，将不再提供别的量化版本，如有需要，朋友们可根据下面提示信息，自己下载 fp8 后量化。