Update README.md

README.md

@@ -35,9 +35,8 @@ Recommended 6-10 steps. Greatly improved quality compared to other Flux.1 model.
 
 At the request, GGUF Q8_0 quantified version of the model file is provided, for this version of the model file, due to the time relationship, no detailed test has been done, the details of the drawing may be slightly different from the fp8 model, but it should not be much different, at the same time, the model file loading method and model conversion method have been described below.
 
-![](./gguf-sample.png)
-----
-
+![](./gguf-sample.jpg)
+------
 # Recommend:
 
 **UNET versions** (Model only) need Text Encoders and VAE, I recommend use below CLIP and Text Encoder  model, will get better prompt guidance:
@@ -47,7 +46,7 @@ At the request, GGUF Q8_0 quantified version of the model file is provided, for
 - VAE: https://huggingface.co/black-forest-labs/FLUX.1-schnell/tree/main/vae
 - GGUF Version: you need install GGUF model support nodes, https://github.com/city96/ComfyUI-GGUF
 
-**Simple workflow **: a very simple workflow as below, needn't any other comfy custom nodes(For GGUF version, please use UNET Loader(GGUF) node of city96's):
+**Sample workflow**: a very simple workflow as below, needn't any other comfy custom nodes(For GGUF version, please use UNET Loader(GGUF) node of city96's):
 
 ![](./workflow.png)