Update README.md

README.md

@@ -36,12 +36,15 @@ ggc q8
 ![screenshot](https://raw.githubusercontent.com/calcuis/gguf-pack/master/q8.png)
 
 - `ggc q8` accepts multiple image input (see picture above; two images as input)
-- as lite lora auto applied (for both `ggc q8` and `ggc q7`), able to generate output with merely 8 steps instead of the default 40 steps; save up to 80% loading time
+- as lite lora auto applied, able to generate output with merely 8 steps instead of the default 40 steps; save up to 80% loading time
 
 ![screenshot](https://raw.githubusercontent.com/calcuis/gguf-pack/master/q8a.png)
 
 - up to 3 pictures plus customize prompt as input (above is 3 images input demo)
-- or you could opt the legacy `ggc q7`; similar to image-edit model before
+
+![screenshot](https://raw.githubusercontent.com/calcuis/gguf-pack/master/q8a.png)
+
+- though `ggc q8` is accepting single image input (see above), you could opt the legacy `ggc q7` (see below); similar to image-edit model before
 
 ```
 ggc q7